[llvm] [IR] Autoupgrade trivial VP intrinsics to their non-VP counterparts (PR #212490)
Luke Lau via llvm-commits
llvm-commits at lists.llvm.org
Tue Jul 28 07:49:46 PDT 2026
https://github.com/lukel97 updated https://github.com/llvm/llvm-project/pull/212490
>From 532c3fa358954aa20085526a42e6859024772e93 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 28 Jul 2026 18:27:38 +0800
Subject: [PATCH 1/2] Precommit test
---
llvm/test/Assembler/auto_upgrade_vp.ll | 148 +++++++++++++++++++++++++
1 file changed, 148 insertions(+)
create mode 100644 llvm/test/Assembler/auto_upgrade_vp.ll
diff --git a/llvm/test/Assembler/auto_upgrade_vp.ll b/llvm/test/Assembler/auto_upgrade_vp.ll
new file mode 100644
index 0000000000000..e914815afd527
--- /dev/null
+++ b/llvm/test/Assembler/auto_upgrade_vp.ll
@@ -0,0 +1,148 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -S < %s | FileCheck %s
+
+define void @f(<4 x i32> %x, <4 x i32> %y, <4 x i32> %z, <4 x float> %fx, <4 x float> %fy, <4 x float> %fz, <4 x ptr> %px, <4 x i1> %mask, i32 %evl) {
+; CHECK-LABEL: define void @f(
+; CHECK-SAME: <4 x i32> [[X:%.*]], <4 x i32> [[Y:%.*]], <4 x i32> [[Z:%.*]], <4 x float> [[FX:%.*]], <4 x float> [[FY:%.*]], <4 x float> [[FZ:%.*]], <4 x ptr> [[PX:%.*]], <4 x i1> [[MASK:%.*]], i32 [[EVL:%.*]]) {
+; CHECK-NEXT: [[TMP1:%.*]] = call <4 x i32> @llvm.vp.select.v4i32(<4 x i1> [[MASK]], <4 x i32> [[X]], <4 x i32> [[Y]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.vp.sub.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.vp.mul.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP5:%.*]] = call <4 x i32> @llvm.vp.ashr.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP6:%.*]] = call <4 x i32> @llvm.vp.lshr.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP7:%.*]] = call <4 x i32> @llvm.vp.shl.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP8:%.*]] = call <4 x i32> @llvm.vp.or.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP9:%.*]] = call <4 x i32> @llvm.vp.and.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP10:%.*]] = call <4 x i32> @llvm.vp.xor.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP11:%.*]] = call <4 x i32> @llvm.vp.abs.v4i32(<4 x i32> [[X]], i1 false, <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP12:%.*]] = call <4 x i32> @llvm.vp.smax.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP13:%.*]] = call <4 x i32> @llvm.vp.smin.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP14:%.*]] = call <4 x i32> @llvm.vp.umax.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP15:%.*]] = call <4 x i32> @llvm.vp.umin.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP16:%.*]] = call <4 x float> @llvm.vp.copysign.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP17:%.*]] = call <4 x float> @llvm.vp.minnum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP18:%.*]] = call <4 x float> @llvm.vp.maxnum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP19:%.*]] = call <4 x float> @llvm.vp.minimum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP20:%.*]] = call <4 x float> @llvm.vp.maximum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP21:%.*]] = call <4 x float> @llvm.vp.fadd.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP22:%.*]] = call <4 x float> @llvm.vp.fsub.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP23:%.*]] = call <4 x float> @llvm.vp.fmul.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP24:%.*]] = call <4 x float> @llvm.vp.fdiv.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP25:%.*]] = call <4 x float> @llvm.vp.frem.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP26:%.*]] = call <4 x float> @llvm.vp.fneg.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP27:%.*]] = call <4 x float> @llvm.vp.fabs.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP28:%.*]] = call <4 x float> @llvm.vp.sqrt.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP29:%.*]] = call <4 x float> @llvm.vp.fma.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x float> [[FZ]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP30:%.*]] = call <4 x float> @llvm.vp.fmuladd.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x float> [[FZ]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP31:%.*]] = call <4 x i16> @llvm.vp.trunc.v4i16.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP32:%.*]] = call <4 x i64> @llvm.vp.zext.v4i64.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP33:%.*]] = call <4 x i64> @llvm.vp.sext.v4i64.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP34:%.*]] = call <4 x half> @llvm.vp.fptrunc.v4f16.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP35:%.*]] = call <4 x double> @llvm.vp.fpext.v4f64.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP36:%.*]] = call <4 x i32> @llvm.vp.fptoui.v4i32.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP37:%.*]] = call <4 x i32> @llvm.vp.fptosi.v4i32.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP38:%.*]] = call <4 x float> @llvm.vp.uitofp.v4f32.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP39:%.*]] = call <4 x float> @llvm.vp.sitofp.v4f32.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP40:%.*]] = call <4 x i32> @llvm.vp.ptrtoint.v4i32.v4p0(<4 x ptr> [[PX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP41:%.*]] = call <4 x ptr> @llvm.vp.inttoptr.v4p0.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP42:%.*]] = call <4 x i1> @llvm.vp.fcmp.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], metadata !"oeq", <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP43:%.*]] = call <4 x i1> @llvm.vp.icmp.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], metadata !"eq", <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP44:%.*]] = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP45:%.*]] = call <4 x float> @llvm.vp.floor.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP46:%.*]] = call <4 x float> @llvm.vp.rint.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP47:%.*]] = call <4 x float> @llvm.vp.nearbyint.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP48:%.*]] = call <4 x float> @llvm.vp.round.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP49:%.*]] = call <4 x float> @llvm.vp.roundeven.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP50:%.*]] = call <4 x float> @llvm.vp.roundtozero.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP51:%.*]] = call <4 x i32> @llvm.vp.lrint.v4i32.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP52:%.*]] = call <4 x i64> @llvm.vp.llrint.v4i64.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP53:%.*]] = call <4 x i32> @llvm.vp.bitreverse.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP54:%.*]] = call <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP55:%.*]] = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP56:%.*]] = call <4 x i32> @llvm.vp.ctlz.v4i32(<4 x i32> [[X]], i1 false, <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP57:%.*]] = call <4 x i32> @llvm.vp.cttz.v4i32(<4 x i32> [[X]], i1 false, <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP58:%.*]] = call <4 x i32> @llvm.vp.sadd.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP59:%.*]] = call <4 x i32> @llvm.vp.uadd.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP60:%.*]] = call <4 x i32> @llvm.vp.ssub.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP61:%.*]] = call <4 x i32> @llvm.vp.usub.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP62:%.*]] = call <4 x i32> @llvm.vp.fshl.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i32> [[Z]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP63:%.*]] = call <4 x i32> @llvm.vp.fshr.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i32> [[Z]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP64:%.*]] = call <4 x i1> @llvm.vp.is.fpclass.v4f32(<4 x float> [[FX]], i32 0, <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: ret void
+;
+ call <4 x i32> @llvm.vp.select(<4 x i1> %mask, <4 x i32> %x, <4 x i32> %y, i32 %evl)
+ call <4 x i32> @llvm.vp.add(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.sub(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.mul(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.ashr(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.lshr(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.shl(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.or(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.and(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.xor(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.abs(<4 x i32> %x, i1 false, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.smax(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.smin(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.umax(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.umin(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.copysign(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.minnum(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.maxnum(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.minimum(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.maximum(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.fadd(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.fsub(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.fmul(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.fdiv(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.frem(<4 x float> %fx, <4 x float> %fy, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.fneg(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.fabs(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.sqrt(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.fma(<4 x float> %fx, <4 x float> %fy, <4 x float> %fz, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.fmuladd(<4 x float> %fx, <4 x float> %fy, <4 x float> %fz, <4 x i1> %mask, i32 %evl)
+ call <4 x i16> @llvm.vp.trunc(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x i64> @llvm.vp.zext(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x i64> @llvm.vp.sext(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x half> @llvm.vp.fptrunc(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x double> @llvm.vp.fpext(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.fptoui(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.fptosi(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.uitofp(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.sitofp(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.ptrtoint(<4 x ptr> %px, <4 x i1> %mask, i32 %evl)
+ call <4 x ptr> @llvm.vp.inttoptr(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x i1> @llvm.vp.fcmp(<4 x float> %fx, <4 x float> %fy, metadata !"oeq", <4 x i1> %mask, i32 %evl)
+ call <4 x i1> @llvm.vp.icmp(<4 x i32> %x, <4 x i32> %y, metadata !"eq", <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.ceil(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.floor(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.rint(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.nearbyint(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.round(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.roundeven(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x float> @llvm.vp.roundtozero(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.lrint(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x i64> @llvm.vp.llrint(<4 x float> %fx, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.bitreverse(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.bswap(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.ctpop(<4 x i32> %x, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.ctlz(<4 x i32> %x, i1 false, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.cttz(<4 x i32> %x, i1 false, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.sadd.sat(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.uadd.sat(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.ssub.sat(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.usub.sat(<4 x i32> %x, <4 x i32> %y, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.fshl(<4 x i32> %x, <4 x i32> %y, <4 x i32> %z, <4 x i1> %mask, i32 %evl)
+ call <4 x i32> @llvm.vp.fshr(<4 x i32> %x, <4 x i32> %y, <4 x i32> %z, <4 x i1> %mask, i32 %evl)
+ call <4 x i1> @llvm.vp.is.fpclass(<4 x float> %fx, i32 0, <4 x i1> %mask, i32 %evl)
+ ret void
+}
+
+define <4 x float> @fmfs(<4 x float> %x, <4 x float> %y, <4 x i1> %mask, i32 %evl) {
+; CHECK-LABEL: define <4 x float> @fmfs(
+; CHECK-SAME: <4 x float> [[X:%.*]], <4 x float> [[Y:%.*]], <4 x i1> [[MASK:%.*]], i32 [[EVL:%.*]]) {
+; CHECK-NEXT: [[RES:%.*]] = call fast <4 x float> @llvm.vp.fadd.v4f32(<4 x float> [[X]], <4 x float> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: ret <4 x float> [[RES]]
+;
+ %res = call fast <4 x float> @llvm.vp.fadd(<4 x float> %x, <4 x float> %y, <4 x i1> %mask, i32 %evl)
+ ret <4 x float> %res
+}
>From 126e3d4cf97aab0b0e7291b33e57d1567e6fc5cf Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 28 Jul 2026 18:30:01 +0800
Subject: [PATCH 2/2] [IR] Autoupgrade trivial VP intrinsics to their non-VP
counterparts
As a first step towards removing trivial VP intrinsics, autoupgrade them to their non-VP counterparts for backwards compatibility.
Since trivial VP intrinsics only set lanes to poison, it's safe to replace them with non predicated versions.
RFC: https://discourse.llvm.org/t/rfc-remove-trivial-vp-intrinsics/90972
---
llvm/lib/IR/AutoUpgrade.cpp | 71 +
.../test/Analysis/CostModel/RISCV/arith-fp.ll | 470 -----
llvm/test/Analysis/CostModel/RISCV/cast.ll | 1763 -----------------
llvm/test/Analysis/CostModel/RISCV/cmp.ll | 322 +--
llvm/test/Analysis/CostModel/RISCV/fround.ll | 616 +++---
.../Analysis/CostModel/RISCV/int-bit-manip.ll | 477 +++--
.../Analysis/CostModel/RISCV/rvv-select.ll | 260 +--
.../Analysis/CostModel/RISCV/vp-intrinsics.ll | 786 ++++----
llvm/test/Assembler/auto_upgrade_vp.ll | 130 +-
llvm/test/CodeGen/VE/Packed/vp_add.ll | 26 +-
llvm/test/CodeGen/VE/Packed/vp_and.ll | 26 +-
llvm/test/CodeGen/VE/Packed/vp_fadd.ll | 26 +-
llvm/test/CodeGen/VE/Packed/vp_fdiv.ll | 57 +-
llvm/test/CodeGen/VE/Packed/vp_fmul.ll | 26 +-
llvm/test/CodeGen/VE/Packed/vp_fsub.ll | 30 +-
llvm/test/CodeGen/VE/Packed/vp_mul.ll | 34 +-
llvm/test/CodeGen/VE/Packed/vp_or.ll | 26 +-
llvm/test/CodeGen/VE/Packed/vp_shl.ll | 30 +-
llvm/test/CodeGen/VE/Packed/vp_sra.ll | 30 +-
llvm/test/CodeGen/VE/Packed/vp_srl.ll | 30 +-
llvm/test/CodeGen/VE/Packed/vp_sub.ll | 30 +-
llvm/test/CodeGen/VE/Packed/vp_xor.ll | 26 +-
llvm/test/CodeGen/VE/Vector/vp_add.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_and.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_ashr.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_fadd.ll | 24 +-
llvm/test/CodeGen/VE/Vector/vp_fdiv.ll | 24 +-
llvm/test/CodeGen/VE/Vector/vp_fma.ll | 32 +-
llvm/test/CodeGen/VE/Vector/vp_fmul.ll | 24 +-
llvm/test/CodeGen/VE/Vector/vp_fsub.ll | 32 +-
llvm/test/CodeGen/VE/Vector/vp_lshr.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_mul.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_or.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_select.ll | 32 +-
llvm/test/CodeGen/VE/Vector/vp_shl.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_sra.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_srl.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_sub.ll | 8 +-
llvm/test/CodeGen/VE/Vector/vp_xor.ll | 8 +-
.../DeadStoreElimination/dead-vp.store.ll | 4 +-
llvm/test/Transforms/GVN/vp_gather_scatter.ll | 2 +-
llvm/test/Transforms/InstCombine/fabs.ll | 3 +-
llvm/test/Transforms/InstSimplify/add_vp.ll | 24 +-
.../test/Transforms/LICM/vector-intrinsics.ll | 2 +-
.../PreISelIntrinsicLowering/expand-vp.ll | 132 +-
...ntrin-scalarization-shufflevector-splat.ll | 4 +-
.../RISCV/vpintrin-scalarization.ll | 795 +++-----
47 files changed, 1922 insertions(+), 4592 deletions(-)
diff --git a/llvm/lib/IR/AutoUpgrade.cpp b/llvm/lib/IR/AutoUpgrade.cpp
index 97ba01997b9b9..d826dd95401c1 100644
--- a/llvm/lib/IR/AutoUpgrade.cpp
+++ b/llvm/lib/IR/AutoUpgrade.cpp
@@ -1288,6 +1288,45 @@ static bool consumeNVVMPtrAddrSpace(StringRef &Name) {
Name.consume_front("param");
}
+static bool shouldUpgradeVPIntrinsic(StringRef Name) {
+ // Avoid cttz.elts clashing with cttz.
+ if (Name.starts_with("vp.cttz.elts"))
+ return false;
+ return Name.starts_with("vp.select") || Name.starts_with("vp.add") ||
+ Name.starts_with("vp.sub") || Name.starts_with("vp.mul") ||
+ Name.starts_with("vp.ashr") || Name.starts_with("vp.lshr") ||
+ Name.starts_with("vp.shl") || Name.starts_with("vp.or") ||
+ Name.starts_with("vp.and") || Name.starts_with("vp.xor") ||
+ Name.starts_with("vp.abs") || Name.starts_with("vp.smax") ||
+ Name.starts_with("vp.smin") || Name.starts_with("vp.umax") ||
+ Name.starts_with("vp.umin") || Name.starts_with("vp.copysign") ||
+ Name.starts_with("vp.minnum") || Name.starts_with("vp.maxnum") ||
+ Name.starts_with("vp.minimum") || Name.starts_with("vp.maximum") ||
+ Name.starts_with("vp.fadd") || Name.starts_with("vp.fsub") ||
+ Name.starts_with("vp.fmul") || Name.starts_with("vp.fdiv") ||
+ Name.starts_with("vp.frem") || Name.starts_with("vp.fneg") ||
+ Name.starts_with("vp.fabs") || Name.starts_with("vp.sqrt") ||
+ Name.starts_with("vp.fma") || Name.starts_with("vp.fmuladd") ||
+ Name.starts_with("vp.trunc") || Name.starts_with("vp.zext") ||
+ Name.starts_with("vp.sext") || Name.starts_with("vp.fptrunc") ||
+ Name.starts_with("vp.fpext") || Name.starts_with("vp.fptoui") ||
+ Name.starts_with("vp.fptosi") || Name.starts_with("vp.uitofp") ||
+ Name.starts_with("vp.sitofp") || Name.starts_with("vp.ptrtoint") ||
+ Name.starts_with("vp.inttoptr") || Name.starts_with("vp.fcmp") ||
+ Name.starts_with("vp.icmp") || Name.starts_with("vp.ceil") ||
+ Name.starts_with("vp.floor") || Name.starts_with("vp.rint") ||
+ Name.starts_with("vp.nearbyint") || Name.starts_with("vp.round") ||
+ Name.starts_with("vp.roundeven") ||
+ Name.starts_with("vp.roundtozero") || Name.starts_with("vp.lrint") ||
+ Name.starts_with("vp.llrint") || Name.starts_with("vp.bitreverse") ||
+ Name.starts_with("vp.bswap") || Name.starts_with("vp.ctpop") ||
+ Name.starts_with("vp.ctlz") || Name.starts_with("vp.cttz") ||
+ Name.starts_with("vp.sadd.sat") || Name.starts_with("vp.uadd.sat") ||
+ Name.starts_with("vp.ssub.sat") || Name.starts_with("vp.usub.sat") ||
+ Name.starts_with("vp.fshl") || Name.starts_with("vp.fshr") ||
+ Name.starts_with("vp.is.fpclass");
+}
+
static bool convertIntrinsicValidType(StringRef Name,
const FunctionType *FuncTy) {
Type *HalfTy = Type::getHalfTy(FuncTy->getContext());
@@ -1918,6 +1957,8 @@ static bool upgradeIntrinsicFunction1(Function *F, Function *&NewFn,
break;
return true;
}
+ if (shouldUpgradeVPIntrinsic(Name))
+ return true;
break;
}
@@ -5125,6 +5166,34 @@ static Value *upgradeConvertIntrinsicCall(StringRef Name, CallBase *CI,
return nullptr;
}
+static Value *upgradeVPIntrinsicCall(CallBase *CI, IRBuilder<> &Builder) {
+ Value *Rep;
+ auto Opcode = cast<VPIntrinsic>(CI)->getFunctionalOpcode();
+ if (Opcode && Instruction::isUnaryOp(*Opcode))
+ Rep = Builder.CreateUnOp((Instruction::UnaryOps)*Opcode,
+ CI->getArgOperand(0));
+ else if (Opcode && Instruction::isBinaryOp(*Opcode))
+ Rep = Builder.CreateBinOp((Instruction::BinaryOps)*Opcode,
+ CI->getArgOperand(0), CI->getArgOperand(1));
+ else if (Opcode && Instruction::isCast(*Opcode))
+ Rep = Builder.CreateCast((Instruction::CastOps)*Opcode,
+ CI->getArgOperand(0), CI->getType());
+ else if (Opcode == Instruction::ICmp || Opcode == Instruction::FCmp)
+ Rep = Builder.CreateCmp(cast<VPCmpIntrinsic>(CI)->getPredicate(),
+ CI->getArgOperand(0), CI->getArgOperand(1));
+ else if (Opcode == Instruction::Select)
+ Rep = Builder.CreateSelect(CI->getArgOperand(0), CI->getArgOperand(1),
+ CI->getArgOperand(2));
+ else if (auto IntrinsicID =
+ cast<VPIntrinsic>(CI)->getFunctionalIntrinsicID()) {
+ SmallVector<Value *, 2> Args(drop_end(CI->args(), 2));
+ Rep = Builder.CreateIntrinsic(CI->getType(), *IntrinsicID, Args, {});
+ } else
+ llvm_unreachable("Unexpected vp intrinsic");
+ Rep->takeName(CI);
+ return Rep;
+}
+
static bool upgradeIntrinsicCallWithDefaultArgs(CallBase *CI, Function *NewFn,
IRBuilder<> &Builder) {
Intrinsic::ID IID = NewFn->getIntrinsicID();
@@ -5233,6 +5302,8 @@ void llvm::UpgradeIntrinsicCall(CallBase *CI, Function *NewFn) {
} else if (Name == "lifetime.start.i64" || Name == "lifetime.end.i64") {
// Delete calls to invalid @llvm.lifetime.{start,end}.i64 intrinsics.
Rep = nullptr;
+ } else if (shouldUpgradeVPIntrinsic(Name)) {
+ Rep = upgradeVPIntrinsicCall(CI, Builder);
} else {
llvm_unreachable("Unknown function for CallBase upgrade.");
}
diff --git a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
index 03bdd439ba2fc..1c2fb2c7d61d6 100644
--- a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
@@ -27,24 +27,6 @@ define void @fadd() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64 = fadd <vscale x 2 x double> poison, poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64 = fadd <vscale x 4 x double> poison, poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fadd <vscale x 8 x double> poison, poison
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32_VP = call <1 x float> @llvm.vp.fadd.v1f32(<1 x float> poison, <1 x float> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32_VP = call <2 x float> @llvm.vp.fadd.v2f32(<2 x float> poison, <2 x float> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32_VP = call <4 x float> @llvm.vp.fadd.v4f32(<4 x float> poison, <4 x float> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32_VP = call <8 x float> @llvm.vp.fadd.v8f32(<8 x float> poison, <8 x float> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32_VP = call <16 x float> @llvm.vp.fadd.v16f32(<16 x float> poison, <16 x float> poison, <16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64_VP = call <1 x double> @llvm.vp.fadd.v1f64(<1 x double> poison, <1 x double> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64_VP = call <2 x double> @llvm.vp.fadd.v2f64(<2 x double> poison, <2 x double> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64_VP = call <4 x double> @llvm.vp.fadd.v4f64(<4 x double> poison, <4 x double> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64_VP = call <8 x double> @llvm.vp.fadd.v8f64(<8 x double> poison, <8 x double> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F32_VP = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> poison, <vscale x 1 x float> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F32_VP = call <vscale x 2 x float> @llvm.vp.fadd.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F32_VP = call <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F32_VP = call <vscale x 8 x float> @llvm.vp.fadd.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison, <vscale x 8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F32_VP = call <vscale x 16 x float> @llvm.vp.fadd.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison, <vscale x 16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F64_VP = call <vscale x 1 x double> @llvm.vp.fadd.nxv1f64(<vscale x 1 x double> poison, <vscale x 1 x double> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64_VP = call <vscale x 2 x double> @llvm.vp.fadd.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64_VP = call <vscale x 4 x double> @llvm.vp.fadd.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64_VP = call <vscale x 8 x double> @llvm.vp.fadd.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison, <vscale x 8 x i1> poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F32 = fadd float poison, poison
@@ -110,16 +92,6 @@ define void @fadd_bf16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4BF16 = fadd <vscale x 4 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fadd <vscale x 8 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fadd <vscale x 16 x bfloat> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fadd.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fadd.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fadd.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fadd.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fadd.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fadd.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fadd.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fadd.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fadd.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fadd.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fadd_bf16'
@@ -134,16 +106,6 @@ define void @fadd_bf16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4BF16 = fadd <vscale x 4 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fadd <vscale x 8 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fadd <vscale x 16 x bfloat> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fadd.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fadd.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fadd.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fadd.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fadd.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fadd.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fadd.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fadd.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fadd.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fadd.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fadd_bf16'
@@ -158,16 +120,6 @@ define void @fadd_bf16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16 = fadd <vscale x 4 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = fadd <vscale x 8 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = fadd <vscale x 16 x bfloat> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fadd.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fadd.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fadd.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fadd.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fadd.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fadd.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fadd.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fadd.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fadd.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fadd.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%BF16 = fadd bfloat poison, poison
@@ -214,16 +166,6 @@ define void @fadd_f16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fadd <vscale x 8 x half> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fadd <vscale x 16 x half> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fadd <vscale x 32 x half> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fadd.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fadd.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fadd.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fadd.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fadd.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fadd.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fadd.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fadd.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fadd.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fadd.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fadd_f16'
@@ -240,16 +182,6 @@ define void @fadd_f16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8F16 = fadd <vscale x 8 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16F16 = fadd <vscale x 16 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fadd <vscale x 32 x half> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fadd.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fadd.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fadd.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fadd.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fadd.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fadd.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fadd.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fadd.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fadd.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fadd.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fadd_f16'
@@ -266,16 +198,6 @@ define void @fadd_f16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16 = fadd <vscale x 8 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16 = fadd <vscale x 16 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32F16 = fadd <vscale x 32 x half> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fadd.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fadd.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fadd.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fadd.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fadd.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fadd.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fadd.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fadd.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fadd.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fadd.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fadd half poison, poison
@@ -331,24 +253,6 @@ define void @fsub() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64 = fsub <vscale x 2 x double> poison, poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64 = fsub <vscale x 4 x double> poison, poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fsub <vscale x 8 x double> poison, poison
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32_VP = call <1 x float> @llvm.vp.fsub.v1f32(<1 x float> poison, <1 x float> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32_VP = call <2 x float> @llvm.vp.fsub.v2f32(<2 x float> poison, <2 x float> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32_VP = call <4 x float> @llvm.vp.fsub.v4f32(<4 x float> poison, <4 x float> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32_VP = call <8 x float> @llvm.vp.fsub.v8f32(<8 x float> poison, <8 x float> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32_VP = call <16 x float> @llvm.vp.fsub.v16f32(<16 x float> poison, <16 x float> poison, <16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64_VP = call <1 x double> @llvm.vp.fsub.v1f64(<1 x double> poison, <1 x double> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64_VP = call <2 x double> @llvm.vp.fsub.v2f64(<2 x double> poison, <2 x double> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64_VP = call <4 x double> @llvm.vp.fsub.v4f64(<4 x double> poison, <4 x double> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64_VP = call <8 x double> @llvm.vp.fsub.v8f64(<8 x double> poison, <8 x double> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F32_VP = call <vscale x 1 x float> @llvm.vp.fsub.nxv1f32(<vscale x 1 x float> poison, <vscale x 1 x float> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F32_VP = call <vscale x 2 x float> @llvm.vp.fsub.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F32_VP = call <vscale x 4 x float> @llvm.vp.fsub.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F32_VP = call <vscale x 8 x float> @llvm.vp.fsub.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison, <vscale x 8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F32_VP = call <vscale x 16 x float> @llvm.vp.fsub.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison, <vscale x 16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F64_VP = call <vscale x 1 x double> @llvm.vp.fsub.nxv1f64(<vscale x 1 x double> poison, <vscale x 1 x double> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64_VP = call <vscale x 2 x double> @llvm.vp.fsub.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64_VP = call <vscale x 4 x double> @llvm.vp.fsub.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64_VP = call <vscale x 8 x double> @llvm.vp.fsub.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison, <vscale x 8 x i1> poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F32 = fsub float poison, poison
@@ -416,16 +320,6 @@ define void @fsub_bf16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fsub <vscale x 8 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fsub <vscale x 16 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32BF16 = fsub <vscale x 32 x bfloat> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fsub.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fsub.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fsub.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fsub.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fsub.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fsub.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fsub.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fsub.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fsub.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fsub.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fsub_bf16'
@@ -442,16 +336,6 @@ define void @fsub_bf16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fsub <vscale x 8 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fsub <vscale x 16 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32BF16 = fsub <vscale x 32 x bfloat> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fsub.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fsub.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fsub.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fsub.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fsub.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fsub.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fsub.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fsub.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fsub.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fsub.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fsub_bf16'
@@ -468,16 +352,6 @@ define void @fsub_bf16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = fsub <vscale x 8 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = fsub <vscale x 16 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32BF16 = fsub <vscale x 32 x bfloat> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fsub.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fsub.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fsub.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fsub.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fsub.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fsub.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fsub.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fsub.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fsub.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fsub.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%BF16 = fsub bfloat poison, poison
@@ -526,16 +400,6 @@ define void @fsub_f16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fsub <vscale x 8 x half> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fsub <vscale x 16 x half> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fsub <vscale x 32 x half> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fsub.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fsub.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fsub.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fsub.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fsub.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fsub.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fsub.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fsub.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fsub.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fsub.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fsub_f16'
@@ -552,16 +416,6 @@ define void @fsub_f16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8F16 = fsub <vscale x 8 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16F16 = fsub <vscale x 16 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fsub <vscale x 32 x half> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fsub.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fsub.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fsub.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fsub.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fsub.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fsub.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fsub.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fsub.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fsub.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fsub.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fsub_f16'
@@ -578,16 +432,6 @@ define void @fsub_f16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16 = fsub <vscale x 8 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16 = fsub <vscale x 16 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32F16 = fsub <vscale x 32 x half> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fsub.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fsub.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fsub.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fsub.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fsub.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fsub.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fsub.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fsub.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fsub.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fsub.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fsub half poison, poison
@@ -643,24 +487,6 @@ define void @fmul() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64 = fmul <vscale x 2 x double> poison, poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64 = fmul <vscale x 4 x double> poison, poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fmul <vscale x 8 x double> poison, poison
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32_VP = call <1 x float> @llvm.vp.fmul.v1f32(<1 x float> poison, <1 x float> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32_VP = call <2 x float> @llvm.vp.fmul.v2f32(<2 x float> poison, <2 x float> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32_VP = call <4 x float> @llvm.vp.fmul.v4f32(<4 x float> poison, <4 x float> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32_VP = call <8 x float> @llvm.vp.fmul.v8f32(<8 x float> poison, <8 x float> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32_VP = call <16 x float> @llvm.vp.fmul.v16f32(<16 x float> poison, <16 x float> poison, <16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64_VP = call <1 x double> @llvm.vp.fmul.v1f64(<1 x double> poison, <1 x double> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64_VP = call <2 x double> @llvm.vp.fmul.v2f64(<2 x double> poison, <2 x double> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64_VP = call <4 x double> @llvm.vp.fmul.v4f64(<4 x double> poison, <4 x double> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64_VP = call <8 x double> @llvm.vp.fmul.v8f64(<8 x double> poison, <8 x double> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F32_VP = call <vscale x 1 x float> @llvm.vp.fmul.nxv1f32(<vscale x 1 x float> poison, <vscale x 1 x float> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F32_VP = call <vscale x 2 x float> @llvm.vp.fmul.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F32_VP = call <vscale x 4 x float> @llvm.vp.fmul.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F32_VP = call <vscale x 8 x float> @llvm.vp.fmul.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison, <vscale x 8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F32_VP = call <vscale x 16 x float> @llvm.vp.fmul.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison, <vscale x 16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F64_VP = call <vscale x 1 x double> @llvm.vp.fmul.nxv1f64(<vscale x 1 x double> poison, <vscale x 1 x double> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64_VP = call <vscale x 2 x double> @llvm.vp.fmul.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64_VP = call <vscale x 4 x double> @llvm.vp.fmul.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64_VP = call <vscale x 8 x double> @llvm.vp.fmul.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison, <vscale x 8 x i1> poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F32 = fmul float poison, poison
@@ -728,16 +554,6 @@ define void @fmul_bf16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fmul <vscale x 8 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fmul <vscale x 16 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32BF16 = fmul <vscale x 32 x bfloat> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fmul.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fmul.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fmul.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fmul.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fmul.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fmul.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fmul.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fmul.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fmul.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fmul.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fmul_bf16'
@@ -754,16 +570,6 @@ define void @fmul_bf16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fmul <vscale x 8 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fmul <vscale x 16 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32BF16 = fmul <vscale x 32 x bfloat> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fmul.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fmul.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fmul.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fmul.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fmul.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fmul.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fmul.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fmul.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fmul.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fmul.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fmul_bf16'
@@ -780,16 +586,6 @@ define void @fmul_bf16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = fmul <vscale x 8 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = fmul <vscale x 16 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32BF16 = fmul <vscale x 32 x bfloat> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fmul.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fmul.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fmul.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fmul.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fmul.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fmul.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fmul.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fmul.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fmul.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fmul.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%BF16 = fmul bfloat poison, poison
@@ -838,16 +634,6 @@ define void @fmul_f16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fmul <vscale x 8 x half> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fmul <vscale x 16 x half> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fmul <vscale x 32 x half> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fmul.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fmul.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fmul.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fmul.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fmul.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fmul.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fmul.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fmul.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fmul.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fmul.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fmul_f16'
@@ -864,16 +650,6 @@ define void @fmul_f16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8F16 = fmul <vscale x 8 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16F16 = fmul <vscale x 16 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fmul <vscale x 32 x half> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fmul.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fmul.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fmul.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fmul.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fmul.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fmul.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fmul.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fmul.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fmul.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fmul.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fmul_f16'
@@ -890,16 +666,6 @@ define void @fmul_f16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16 = fmul <vscale x 8 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16 = fmul <vscale x 16 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32F16 = fmul <vscale x 32 x half> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fmul.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fmul.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fmul.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fmul.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fmul.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fmul.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fmul.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fmul.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fmul.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fmul.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fmul half poison, poison
@@ -955,24 +721,6 @@ define void @fdiv() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64 = fdiv <vscale x 2 x double> poison, poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64 = fdiv <vscale x 4 x double> poison, poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fdiv <vscale x 8 x double> poison, poison
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32_VP = call <1 x float> @llvm.vp.fdiv.v1f32(<1 x float> poison, <1 x float> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32_VP = call <2 x float> @llvm.vp.fdiv.v2f32(<2 x float> poison, <2 x float> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32_VP = call <4 x float> @llvm.vp.fdiv.v4f32(<4 x float> poison, <4 x float> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32_VP = call <8 x float> @llvm.vp.fdiv.v8f32(<8 x float> poison, <8 x float> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32_VP = call <16 x float> @llvm.vp.fdiv.v16f32(<16 x float> poison, <16 x float> poison, <16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64_VP = call <1 x double> @llvm.vp.fdiv.v1f64(<1 x double> poison, <1 x double> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64_VP = call <2 x double> @llvm.vp.fdiv.v2f64(<2 x double> poison, <2 x double> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64_VP = call <4 x double> @llvm.vp.fdiv.v4f64(<4 x double> poison, <4 x double> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64_VP = call <8 x double> @llvm.vp.fdiv.v8f64(<8 x double> poison, <8 x double> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F32_VP = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> poison, <vscale x 1 x float> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F32_VP = call <vscale x 2 x float> @llvm.vp.fdiv.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F32_VP = call <vscale x 4 x float> @llvm.vp.fdiv.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F32_VP = call <vscale x 8 x float> @llvm.vp.fdiv.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison, <vscale x 8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F32_VP = call <vscale x 16 x float> @llvm.vp.fdiv.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison, <vscale x 16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F64_VP = call <vscale x 1 x double> @llvm.vp.fdiv.nxv1f64(<vscale x 1 x double> poison, <vscale x 1 x double> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64_VP = call <vscale x 2 x double> @llvm.vp.fdiv.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64_VP = call <vscale x 4 x double> @llvm.vp.fdiv.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64_VP = call <vscale x 8 x double> @llvm.vp.fdiv.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison, <vscale x 8 x i1> poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F32 = fdiv float poison, poison
@@ -1041,16 +789,6 @@ define void @fdiv_bf16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fdiv <vscale x 8 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fdiv <vscale x 16 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32BF16 = fdiv <vscale x 32 x bfloat> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fdiv.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fdiv.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fdiv.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fdiv.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fdiv.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fdiv.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fdiv.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fdiv.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fdiv.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fdiv.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fdiv_bf16'
@@ -1067,16 +805,6 @@ define void @fdiv_bf16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fdiv <vscale x 8 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fdiv <vscale x 16 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32BF16 = fdiv <vscale x 32 x bfloat> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fdiv.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fdiv.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fdiv.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fdiv.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fdiv.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fdiv.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fdiv.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fdiv.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fdiv.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fdiv.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fdiv_bf16'
@@ -1093,16 +821,6 @@ define void @fdiv_bf16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = fdiv <vscale x 8 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = fdiv <vscale x 16 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32BF16 = fdiv <vscale x 32 x bfloat> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fdiv.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fdiv.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fdiv.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fdiv.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fdiv.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fdiv.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fdiv.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fdiv.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fdiv.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fdiv.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%BF16 = fdiv bfloat poison, poison
@@ -1151,16 +869,6 @@ define void @fdiv_f16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fdiv <vscale x 8 x half> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> poison, poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fdiv <vscale x 32 x half> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fdiv.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fdiv.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fdiv.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fdiv.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fdiv.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fdiv.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fdiv.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fdiv.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fdiv.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fdiv.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fdiv_f16'
@@ -1177,16 +885,6 @@ define void @fdiv_f16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8F16 = fdiv <vscale x 8 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fdiv <vscale x 32 x half> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fdiv.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fdiv.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fdiv.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fdiv.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fdiv.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fdiv.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fdiv.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fdiv.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fdiv.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fdiv.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fdiv_f16'
@@ -1203,16 +901,6 @@ define void @fdiv_f16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16 = fdiv <vscale x 8 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16 = fdiv <vscale x 16 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32F16 = fdiv <vscale x 32 x half> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fdiv.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fdiv.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fdiv.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fdiv.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fdiv.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fdiv.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fdiv.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fdiv.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fdiv.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fdiv.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fdiv half poison, poison
@@ -1268,24 +956,6 @@ define void @frem() {
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV2F64 = frem <vscale x 2 x double> poison, poison
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV4F64 = frem <vscale x 4 x double> poison, poison
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV8F64 = frem <vscale x 8 x double> poison, poison
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V1F32_VP = call <1 x float> @llvm.vp.frem.v1f32(<1 x float> poison, <1 x float> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V2F32_VP = call <2 x float> @llvm.vp.frem.v2f32(<2 x float> poison, <2 x float> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4F32_VP = call <4 x float> @llvm.vp.frem.v4f32(<4 x float> poison, <4 x float> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V8F32_VP = call <8 x float> @llvm.vp.frem.v8f32(<8 x float> poison, <8 x float> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V16F32_VP = call <16 x float> @llvm.vp.frem.v16f32(<16 x float> poison, <16 x float> poison, <16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V1F64_VP = call <1 x double> @llvm.vp.frem.v1f64(<1 x double> poison, <1 x double> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V2F64_VP = call <2 x double> @llvm.vp.frem.v2f64(<2 x double> poison, <2 x double> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V4F64_VP = call <4 x double> @llvm.vp.frem.v4f64(<4 x double> poison, <4 x double> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V8F64_VP = call <8 x double> @llvm.vp.frem.v8f64(<8 x double> poison, <8 x double> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV1F32_VP = call <vscale x 1 x float> @llvm.vp.frem.nxv1f32(<vscale x 1 x float> poison, <vscale x 1 x float> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV2F32_VP = call <vscale x 2 x float> @llvm.vp.frem.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV4F32_VP = call <vscale x 4 x float> @llvm.vp.frem.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV8F32_VP = call <vscale x 8 x float> @llvm.vp.frem.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison, <vscale x 8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV16F32_VP = call <vscale x 16 x float> @llvm.vp.frem.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison, <vscale x 16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV1F64_VP = call <vscale x 1 x double> @llvm.vp.frem.nxv1f64(<vscale x 1 x double> poison, <vscale x 1 x double> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV2F64_VP = call <vscale x 2 x double> @llvm.vp.frem.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV4F64_VP = call <vscale x 4 x double> @llvm.vp.frem.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV8F64_VP = call <vscale x 8 x double> @llvm.vp.frem.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison, <vscale x 8 x i1> poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F32 = frem float poison, poison
@@ -1353,16 +1023,6 @@ define void @frem_bf16() {
; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = frem <vscale x 8 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = frem <vscale x 16 x bfloat> poison, poison
; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV32BF16 = frem <vscale x 32 x bfloat> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.frem.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.frem.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.frem.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.frem.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.frem.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.frem.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.frem.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.frem.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.frem.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.frem.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'frem_bf16'
@@ -1379,16 +1039,6 @@ define void @frem_bf16() {
; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = frem <vscale x 8 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = frem <vscale x 16 x bfloat> poison, poison
; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32BF16 = frem <vscale x 32 x bfloat> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.frem.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.frem.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.frem.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.frem.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.frem.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.frem.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.frem.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.frem.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.frem.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.frem.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'frem_bf16'
@@ -1405,16 +1055,6 @@ define void @frem_bf16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = frem <vscale x 8 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = frem <vscale x 16 x bfloat> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32BF16 = frem <vscale x 32 x bfloat> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.frem.v1bf16(<1 x bfloat> poison, <1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.frem.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.frem.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.frem.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.frem.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.frem.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.frem.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.frem.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.frem.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.frem.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%BF16 = frem bfloat poison, poison
@@ -1463,16 +1103,6 @@ define void @frem_f16() {
; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16 = frem <vscale x 8 x half> poison, poison
; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16 = frem <vscale x 16 x half> poison, poison
; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV32F16 = frem <vscale x 32 x half> poison, poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.frem.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.frem.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.frem.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.frem.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.frem.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.frem.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.frem.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.frem.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.frem.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.frem.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'frem_f16'
@@ -1489,16 +1119,6 @@ define void @frem_f16() {
; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16 = frem <vscale x 8 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16 = frem <vscale x 16 x half> poison, poison
; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32F16 = frem <vscale x 32 x half> poison, poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.frem.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.frem.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.frem.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.frem.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.frem.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.frem.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.frem.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.frem.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.frem.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.frem.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'frem_f16'
@@ -1515,16 +1135,6 @@ define void @frem_f16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16 = frem <vscale x 8 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16 = frem <vscale x 16 x half> poison, poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32F16 = frem <vscale x 32 x half> poison, poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.frem.v1f16(<1 x half> poison, <1 x half> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.frem.v2f16(<2 x half> poison, <2 x half> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.frem.v4f16(<4 x half> poison, <4 x half> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.frem.v8f16(<8 x half> poison, <8 x half> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.frem.v16f16(<16 x half> poison, <16 x half> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.frem.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.frem.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.frem.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.frem.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.frem.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = frem half poison, poison
@@ -1580,26 +1190,6 @@ define void @fneg() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64 = fneg <vscale x 2 x double> poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64 = fneg <vscale x 4 x double> poison
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fneg <vscale x 8 x double> poison
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32_VP = call <1 x float> @llvm.vp.fneg.v1f32(<1 x float> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32_VP = call <2 x float> @llvm.vp.fneg.v2f32(<2 x float> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32_VP = call <4 x float> @llvm.vp.fneg.v4f32(<4 x float> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32_VP = call <8 x float> @llvm.vp.fneg.v8f32(<8 x float> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32_VP = call <16 x float> @llvm.vp.fneg.v16f32(<16 x float> poison, <16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64_VP = call <1 x double> @llvm.vp.fneg.v1f64(<1 x double> poison, <1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64_VP = call <2 x double> @llvm.vp.fneg.v2f64(<2 x double> poison, <2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64_VP = call <4 x double> @llvm.vp.fneg.v4f64(<4 x double> poison, <4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64_VP = call <8 x double> @llvm.vp.fneg.v8f64(<8 x double> poison, <8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F64_VP = call <16 x double> @llvm.vp.fneg.v16f64(<16 x double> poison, <16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F32_VP = call <vscale x 1 x float> @llvm.vp.fneg.nxv1f32(<vscale x 1 x float> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F32_VP = call <vscale x 2 x float> @llvm.vp.fneg.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F32_VP = call <vscale x 4 x float> @llvm.vp.fneg.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F32_VP = call <vscale x 8 x float> @llvm.vp.fneg.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F32_VP = call <vscale x 16 x float> @llvm.vp.fneg.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F64_VP = call <vscale x 1 x double> @llvm.vp.fneg.nxv1f64(<vscale x 1 x double> poison, <vscale x 1 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV2F64_VP = call <vscale x 2 x double> @llvm.vp.fneg.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV4F64_VP = call <vscale x 4 x double> @llvm.vp.fneg.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64_VP = call <vscale x 8 x double> @llvm.vp.fneg.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x i1> poison, i32 poison)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %NXV16F64_VP = call <vscale x 16 x double> @llvm.vp.fneg.nxv16f64(<vscale x 16 x double> poison, <vscale x 16 x i1> poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F32 = fneg float poison
@@ -1669,16 +1259,6 @@ define void @fneg_bf16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fneg <vscale x 8 x bfloat> poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fneg <vscale x 16 x bfloat> poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32BF16 = fneg <vscale x 32 x bfloat> poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fneg.v1bf16(<1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fneg.v2bf16(<2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fneg.v4bf16(<4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fneg.v8bf16(<8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fneg.v16bf16(<16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fneg.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fneg.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fneg.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fneg.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fneg.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fneg_bf16'
@@ -1695,16 +1275,6 @@ define void @fneg_bf16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fneg <vscale x 8 x bfloat> poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fneg <vscale x 16 x bfloat> poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32BF16 = fneg <vscale x 32 x bfloat> poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fneg.v1bf16(<1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fneg.v2bf16(<2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fneg.v4bf16(<4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fneg.v8bf16(<8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fneg.v16bf16(<16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fneg.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fneg.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fneg.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fneg.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fneg.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fneg_bf16'
@@ -1721,16 +1291,6 @@ define void @fneg_bf16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = fneg <vscale x 8 x bfloat> poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = fneg <vscale x 16 x bfloat> poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32BF16 = fneg <vscale x 32 x bfloat> poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16_VP = call <1 x bfloat> @llvm.vp.fneg.v1bf16(<1 x bfloat> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2BF16_VP = call <2 x bfloat> @llvm.vp.fneg.v2bf16(<2 x bfloat> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4BF16_VP = call <4 x bfloat> @llvm.vp.fneg.v4bf16(<4 x bfloat> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8BF16_VP = call <8 x bfloat> @llvm.vp.fneg.v8bf16(<8 x bfloat> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16BF16_VP = call <16 x bfloat> @llvm.vp.fneg.v16bf16(<16 x bfloat> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16_VP = call <vscale x 1 x bfloat> @llvm.vp.fneg.nxv1bf16(<vscale x 1 x bfloat> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16_VP = call <vscale x 2 x bfloat> @llvm.vp.fneg.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16_VP = call <vscale x 4 x bfloat> @llvm.vp.fneg.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16_VP = call <vscale x 8 x bfloat> @llvm.vp.fneg.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16_VP = call <vscale x 16 x bfloat> @llvm.vp.fneg.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%BF16 = fneg bfloat poison
@@ -1779,16 +1339,6 @@ define void @fneg_f16() {
; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fneg <vscale x 8 x half> poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fneg <vscale x 16 x half> poison
; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fneg <vscale x 32 x half> poison
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fneg.v1f16(<1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fneg.v2f16(<2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fneg.v4f16(<4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fneg.v8f16(<8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fneg.v16f16(<16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fneg.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fneg.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fneg.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fneg.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fneg.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fneg_f16'
@@ -1805,16 +1355,6 @@ define void @fneg_f16() {
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fneg <vscale x 8 x half> poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fneg <vscale x 16 x half> poison
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fneg <vscale x 32 x half> poison
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fneg.v1f16(<1 x half> poison, <1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fneg.v2f16(<2 x half> poison, <2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fneg.v4f16(<4 x half> poison, <4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fneg.v8f16(<8 x half> poison, <8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fneg.v16f16(<16 x half> poison, <16 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fneg.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fneg.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fneg.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fneg.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fneg.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; NO-ZFHMIN-LABEL: 'fneg_f16'
@@ -1831,16 +1371,6 @@ define void @fneg_f16() {
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16 = fneg <vscale x 8 x half> poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16 = fneg <vscale x 16 x half> poison
; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV32F16 = fneg <vscale x 32 x half> poison
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16_VP = call <1 x half> @llvm.vp.fneg.v1f16(<1 x half> poison, <1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F16_VP = call <2 x half> @llvm.vp.fneg.v2f16(<2 x half> poison, <2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F16_VP = call <4 x half> @llvm.vp.fneg.v4f16(<4 x half> poison, <4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F16_VP = call <8 x half> @llvm.vp.fneg.v8f16(<8 x half> poison, <8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F16_VP = call <16 x half> @llvm.vp.fneg.v16f16(<16 x half> poison, <16 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV1F16_VP = call <vscale x 1 x half> @llvm.vp.fneg.nxv1f16(<vscale x 1 x half> poison, <vscale x 1 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV2F16_VP = call <vscale x 2 x half> @llvm.vp.fneg.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV4F16_VP = call <vscale x 4 x half> @llvm.vp.fneg.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV8F16_VP = call <vscale x 8 x half> @llvm.vp.fneg.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x i1> poison, i32 poison)
-; NO-ZFHMIN-NEXT: Cost Model: Invalid cost for instruction: %NXV16F16_VP = call <vscale x 16 x half> @llvm.vp.fneg.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x i1> poison, i32 poison)
; NO-ZFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fneg half poison
diff --git a/llvm/test/Analysis/CostModel/RISCV/cast.ll b/llvm/test/Analysis/CostModel/RISCV/cast.ll
index 6dacd59f07fde..431e08a65f7f5 100644
--- a/llvm/test/Analysis/CostModel/RISCV/cast.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/cast.ll
@@ -15,16 +15,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_v2i16 = sext <2 x i1> undef to <2 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_v2i32 = sext <2 x i1> undef to <2 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_v2i64 = sext <2 x i1> undef to <2 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i8_v2i16 = call <2 x i16> @llvm.vp.sext.v2i16.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i8_v2i32 = call <2 x i32> @llvm.vp.sext.v2i32.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i8_v2i64 = call <2 x i64> @llvm.vp.sext.v2i64.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i16_v2i32 = call <2 x i32> @llvm.vp.sext.v2i32.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i16_v2i64 = call <2 x i64> @llvm.vp.sext.v2i64.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i32_v2i64 = call <2 x i64> @llvm.vp.sext.v2i64.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i1_v2i8 = call <2 x i8> @llvm.vp.sext.v2i8.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i1_v2i16 = call <2 x i16> @llvm.vp.sext.v2i16.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i1_v2i32 = call <2 x i32> @llvm.vp.sext.v2i32.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i1_v2i64 = call <2 x i64> @llvm.vp.sext.v2i64.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_v4i16 = sext <4 x i8> undef to <4 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_v4i32 = sext <4 x i8> undef to <4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i8_v4i64 = sext <4 x i8> undef to <4 x i64>
@@ -35,16 +25,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i1_v4i16 = sext <4 x i1> undef to <4 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i1_v4i32 = sext <4 x i1> undef to <4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4i1_v4i64 = sext <4 x i1> undef to <4 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i8_v4i16 = call <4 x i16> @llvm.vp.sext.v4i16.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i8_v4i32 = call <4 x i32> @llvm.vp.sext.v4i32.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i8_v4i64 = call <4 x i64> @llvm.vp.sext.v4i64.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i16_v4i32 = call <4 x i32> @llvm.vp.sext.v4i32.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i16_v4i64 = call <4 x i64> @llvm.vp.sext.v4i64.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i32_v4i64 = call <4 x i64> @llvm.vp.sext.v4i64.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i1_v4i8 = call <4 x i8> @llvm.vp.sext.v4i8.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i1_v4i16 = call <4 x i16> @llvm.vp.sext.v4i16.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i1_v4i32 = call <4 x i32> @llvm.vp.sext.v4i32.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4i1_v4i64 = call <4 x i64> @llvm.vp.sext.v4i64.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_v8i16 = sext <8 x i8> undef to <8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i8_v8i32 = sext <8 x i8> undef to <8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i8_v8i64 = sext <8 x i8> undef to <8 x i64>
@@ -55,16 +35,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i1_v8i16 = sext <8 x i1> undef to <8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i1_v8i32 = sext <8 x i1> undef to <8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i1_v8i64 = sext <8 x i1> undef to <8 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v8i8_v8i16 = call <8 x i16> @llvm.vp.sext.v8i16.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i8_v8i32 = call <8 x i32> @llvm.vp.sext.v8i32.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i8_v8i64 = call <8 x i64> @llvm.vp.sext.v8i64.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i16_v8i32 = call <8 x i32> @llvm.vp.sext.v8i32.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i16_v8i64 = call <8 x i64> @llvm.vp.sext.v8i64.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i32_v8i64 = call <8 x i64> @llvm.vp.sext.v8i64.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i1_v8i8 = call <8 x i8> @llvm.vp.sext.v8i8.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i1_v8i16 = call <8 x i16> @llvm.vp.sext.v8i16.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i1_v8i32 = call <8 x i32> @llvm.vp.sext.v8i32.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8i1_v8i64 = call <8 x i64> @llvm.vp.sext.v8i64.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i8_v16i16 = sext <16 x i8> undef to <16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i8_v16i32 = sext <16 x i8> undef to <16 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16i8_v16i64 = sext <16 x i8> undef to <16 x i64>
@@ -75,16 +45,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i1_v16i16 = sext <16 x i1> undef to <16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16i1_v16i32 = sext <16 x i1> undef to <16 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16i1_v16i64 = sext <16 x i1> undef to <16 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16i8_v16i16 = call <16 x i16> @llvm.vp.sext.v16i16.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16i8_v16i32 = call <16 x i32> @llvm.vp.sext.v16i32.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i8_v16i64 = call <16 x i64> @llvm.vp.sext.v16i64.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16i16_v16i32 = call <16 x i32> @llvm.vp.sext.v16i32.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i16_v16i64 = call <16 x i64> @llvm.vp.sext.v16i64.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i32_v16i64 = call <16 x i64> @llvm.vp.sext.v16i64.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16i1_v16i8 = call <16 x i8> @llvm.vp.sext.v16i8.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16i1_v16i16 = call <16 x i16> @llvm.vp.sext.v16i16.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i1_v16i32 = call <16 x i32> @llvm.vp.sext.v16i32.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16i1_v16i64 = call <16 x i64> @llvm.vp.sext.v16i64.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i8_v32i16 = sext <32 x i8> undef to <32 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v32i8_v32i32 = sext <32 x i8> undef to <32 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v32i8_v32i64 = sext <32 x i8> undef to <32 x i64>
@@ -95,16 +55,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v32i1_v32i16 = sext <32 x i1> undef to <32 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v32i1_v32i32 = sext <32 x i1> undef to <32 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v32i1_v32i64 = sext <32 x i1> undef to <32 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32i8_v32i16 = call <32 x i16> @llvm.vp.sext.v32i16.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32i8_v32i32 = call <32 x i32> @llvm.vp.sext.v32i32.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32i8_v32i64 = call <32 x i64> @llvm.vp.sext.v32i64.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32i16_v32i32 = call <32 x i32> @llvm.vp.sext.v32i32.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32i16_v32i64 = call <32 x i64> @llvm.vp.sext.v32i64.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32i32_v32i64 = call <32 x i64> @llvm.vp.sext.v32i64.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32i1_v32i8 = call <32 x i8> @llvm.vp.sext.v32i8.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32i1_v32i16 = call <32 x i16> @llvm.vp.sext.v32i16.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v32i1_v32i32 = call <32 x i32> @llvm.vp.sext.v32i32.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32i1_v32i64 = call <32 x i64> @llvm.vp.sext.v32i64.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v64i8_v64i16 = sext <64 x i8> undef to <64 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v64i8_v64i32 = sext <64 x i8> undef to <64 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %v64i8_v64i64 = sext <64 x i8> undef to <64 x i64>
@@ -115,16 +65,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v64i1_v64i16 = sext <64 x i1> undef to <64 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v64i1_v64i32 = sext <64 x i1> undef to <64 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %v64i1_v64i64 = sext <64 x i1> undef to <64 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v64i8_v64i16 = call <64 x i16> @llvm.vp.sext.v64i16.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v64i8_v64i32 = call <64 x i32> @llvm.vp.sext.v64i32.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_v64i8_v64i64 = call <64 x i64> @llvm.vp.sext.v64i64.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v64i16_v64i32 = call <64 x i32> @llvm.vp.sext.v64i32.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_v64i16_v64i64 = call <64 x i64> @llvm.vp.sext.v64i64.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v64i32_v64i64 = call <64 x i64> @llvm.vp.sext.v64i64.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v64i1_v64i8 = call <64 x i8> @llvm.vp.sext.v64i8.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v64i1_v64i16 = call <64 x i16> @llvm.vp.sext.v64i16.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v64i1_v64i32 = call <64 x i32> @llvm.vp.sext.v64i32.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_v64i1_v64i64 = call <64 x i64> @llvm.vp.sext.v64i64.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v128i8_v128i16 = sext <128 x i8> undef to <128 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %v128i8_v128i32 = sext <128 x i8> undef to <128 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %v128i8_v128i64 = sext <128 x i8> undef to <128 x i64>
@@ -135,16 +75,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v128i1_v128i16 = sext <128 x i1> undef to <128 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %v128i1_v128i32 = sext <128 x i1> undef to <128 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %v128i1_v128i64 = sext <128 x i1> undef to <128 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v128i8_v128i16 = call <128 x i16> @llvm.vp.sext.v128i16.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_v128i8_v128i32 = call <128 x i32> @llvm.vp.sext.v128i32.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %vp_v128i8_v128i64 = call <128 x i64> @llvm.vp.sext.v128i64.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v128i16_v128i32 = call <128 x i32> @llvm.vp.sext.v128i32.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %vp_v128i16_v128i64 = call <128 x i64> @llvm.vp.sext.v128i64.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v128i32_v128i64 = call <128 x i64> @llvm.vp.sext.v128i64.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v128i1_v128i8 = call <128 x i8> @llvm.vp.sext.v128i8.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v128i1_v128i16 = call <128 x i16> @llvm.vp.sext.v128i16.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_v128i1_v128i32 = call <128 x i32> @llvm.vp.sext.v128i32.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_v128i1_v128i64 = call <128 x i64> @llvm.vp.sext.v128i64.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v256i8_v256i16 = sext <256 x i8> undef to <256 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %v256i8_v256i32 = sext <256 x i8> undef to <256 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 142 for instruction: %v256i8_v256i64 = sext <256 x i8> undef to <256 x i64>
@@ -155,16 +85,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %v256i1_v256i16 = sext <256 x i1> undef to <256 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %v256i1_v256i32 = sext <256 x i1> undef to <256 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 151 for instruction: %v256i1_v256i64 = sext <256 x i1> undef to <256 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v256i8_v256i16 = call <256 x i16> @llvm.vp.sext.v256i16.v256i8(<256 x i8> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %vp_v256i8_v256i32 = call <256 x i32> @llvm.vp.sext.v256i32.v256i8(<256 x i8> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 142 for instruction: %vp_v256i8_v256i64 = call <256 x i64> @llvm.vp.sext.v256i64.v256i8(<256 x i8> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v256i16_v256i32 = call <256 x i32> @llvm.vp.sext.v256i32.v256i16(<256 x i16> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %vp_v256i16_v256i64 = call <256 x i64> @llvm.vp.sext.v256i64.v256i16(<256 x i16> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %vp_v256i32_v256i64 = call <256 x i64> @llvm.vp.sext.v256i64.v256i32(<256 x i32> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v256i1_v256i8 = call <256 x i8> @llvm.vp.sext.v256i8.v256i1(<256 x i1> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_v256i1_v256i16 = call <256 x i16> @llvm.vp.sext.v256i16.v256i1(<256 x i1> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_v256i1_v256i32 = call <256 x i32> @llvm.vp.sext.v256i32.v256i1(<256 x i1> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 151 for instruction: %vp_v256i1_v256i64 = call <256 x i64> @llvm.vp.sext.v256i64.v256i1(<256 x i1> undef, <256 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8_nxv1i16 = sext <vscale x 1 x i8> undef to <vscale x 1 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8_nxv1i32 = sext <vscale x 1 x i8> undef to <vscale x 1 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8_nxv1i64 = sext <vscale x 1 x i8> undef to <vscale x 1 x i64>
@@ -175,16 +95,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i1_nxv1i16 = sext <vscale x 1 x i1> undef to <vscale x 1 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i1_nxv1i32 = sext <vscale x 1 x i1> undef to <vscale x 1 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i1_nxv1i64 = sext <vscale x 1 x i1> undef to <vscale x 1 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i8_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.sext.nxv1i16.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i8_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.sext.nxv1i32.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i8_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.sext.nxv1i64.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i16_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.sext.nxv1i32.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i16_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.sext.nxv1i64.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i32_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.sext.nxv1i64.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i1_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.sext.nxv1i8.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i1_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.sext.nxv1i16.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i1_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.sext.nxv1i32.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i1_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.sext.nxv1i64.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8_nxv2i16 = sext <vscale x 2 x i8> undef to <vscale x 2 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8_nxv2i32 = sext <vscale x 2 x i8> undef to <vscale x 2 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i8_nxv2i64 = sext <vscale x 2 x i8> undef to <vscale x 2 x i64>
@@ -195,16 +105,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i1_nxv2i16 = sext <vscale x 2 x i1> undef to <vscale x 2 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i1_nxv2i32 = sext <vscale x 2 x i1> undef to <vscale x 2 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv2i1_nxv2i64 = sext <vscale x 2 x i1> undef to <vscale x 2 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i8_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.sext.nxv2i16.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i8_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.sext.nxv2i32.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i8_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.sext.nxv2i64.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i16_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.sext.nxv2i32.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i16_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.sext.nxv2i64.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i32_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.sext.nxv2i64.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i1_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.sext.nxv2i8.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i1_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.sext.nxv2i16.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i1_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.sext.nxv2i32.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv2i1_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.sext.nxv2i64.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8_nxv4i16 = sext <vscale x 4 x i8> undef to <vscale x 4 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i8_nxv4i32 = sext <vscale x 4 x i8> undef to <vscale x 4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i8_nxv4i64 = sext <vscale x 4 x i8> undef to <vscale x 4 x i64>
@@ -215,16 +115,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i1_nxv4i16 = sext <vscale x 4 x i1> undef to <vscale x 4 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i1_nxv4i32 = sext <vscale x 4 x i1> undef to <vscale x 4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv4i1_nxv4i64 = sext <vscale x 4 x i1> undef to <vscale x 4 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv4i8_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.sext.nxv4i16.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i8_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.sext.nxv4i32.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i8_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.sext.nxv4i64.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i16_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.sext.nxv4i32.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i16_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.sext.nxv4i64.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i32_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.sext.nxv4i64.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i1_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.sext.nxv4i8.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i1_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.sext.nxv4i16.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i1_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.sext.nxv4i32.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv4i1_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.sext.nxv4i64.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i8_nxv8i16 = sext <vscale x 8 x i8> undef to <vscale x 8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i8_nxv8i32 = sext <vscale x 8 x i8> undef to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i8_nxv8i64 = sext <vscale x 8 x i8> undef to <vscale x 8 x i64>
@@ -235,16 +125,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i1_nxv8i16 = sext <vscale x 8 x i1> undef to <vscale x 8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i1_nxv8i32 = sext <vscale x 8 x i1> undef to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv8i1_nxv8i64 = sext <vscale x 8 x i1> undef to <vscale x 8 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8i8_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.sext.nxv8i16.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8i8_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.sext.nxv8i32.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i8_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.sext.nxv8i64.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8i16_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.sext.nxv8i32.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i16_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.sext.nxv8i64.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i32_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.sext.nxv8i64.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8i1_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.sext.nxv8i8.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8i1_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.sext.nxv8i16.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i1_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.sext.nxv8i32.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv8i1_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.sext.nxv8i64.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i8_nxv16i16 = sext <vscale x 16 x i8> undef to <vscale x 16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i8_nxv16i32 = sext <vscale x 16 x i8> undef to <vscale x 16 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv16i8_nxv16i64 = sext <vscale x 16 x i8> undef to <vscale x 16 x i64>
@@ -255,16 +135,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i1_nxv16i16 = sext <vscale x 16 x i1> undef to <vscale x 16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv16i1_nxv16i32 = sext <vscale x 16 x i1> undef to <vscale x 16 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv16i1_nxv16i64 = sext <vscale x 16 x i1> undef to <vscale x 16 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16i8_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.sext.nxv16i16.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16i8_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.sext.nxv16i32.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16i8_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.sext.nxv16i64.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16i16_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.sext.nxv16i32.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16i16_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.sext.nxv16i64.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16i32_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.sext.nxv16i64.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16i1_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.sext.nxv16i8.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16i1_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.sext.nxv16i16.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv16i1_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.sext.nxv16i32.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16i1_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.sext.nxv16i64.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv32i8_nxv32i16 = sext <vscale x 32 x i8> undef to <vscale x 32 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv32i8_nxv32i32 = sext <vscale x 32 x i8> undef to <vscale x 32 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %nxv32i8_nxv32i64 = sext <vscale x 32 x i8> undef to <vscale x 32 x i64>
@@ -275,16 +145,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv32i1_nxv32i16 = sext <vscale x 32 x i1> undef to <vscale x 32 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv32i1_nxv32i32 = sext <vscale x 32 x i1> undef to <vscale x 32 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %nxv32i1_nxv32i64 = sext <vscale x 32 x i1> undef to <vscale x 32 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv32i8_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.sext.nxv32i16.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv32i8_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.sext.nxv32i32.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_nxv32i8_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.sext.nxv32i64.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv32i16_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.sext.nxv32i32.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_nxv32i16_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.sext.nxv32i64.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv32i32_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.sext.nxv32i64.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv32i1_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.sext.nxv32i8.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv32i1_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.sext.nxv32i16.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv32i1_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.sext.nxv32i32.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_nxv32i1_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.sext.nxv32i64.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv64i8_nxv64i16 = sext <vscale x 64 x i8> undef to <vscale x 64 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %nxv64i8_nxv64i32 = sext <vscale x 64 x i8> undef to <vscale x 64 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %nxv64i8_nxv64i64 = sext <vscale x 64 x i8> undef to <vscale x 64 x i64>
@@ -295,16 +155,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv64i1_nxv64i16 = sext <vscale x 64 x i1> undef to <vscale x 64 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %nxv64i1_nxv64i32 = sext <vscale x 64 x i1> undef to <vscale x 64 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %nxv64i1_nxv64i64 = sext <vscale x 64 x i1> undef to <vscale x 64 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv64i8_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.sext.nxv64i16.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_nxv64i8_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.sext.nxv64i32.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %vp_nxv64i8_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.sext.nxv64i64.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv64i16_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.sext.nxv64i32.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %vp_nxv64i16_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.sext.nxv64i64.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv64i32_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.sext.nxv64i64.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv64i1_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.sext.nxv64i8.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv64i1_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.sext.nxv64i16.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_nxv64i1_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.sext.nxv64i32.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_nxv64i1_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.sext.nxv64i64.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %nxv128i8_nxv128i16 = sext <vscale x 128 x i8> undef to <vscale x 128 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %nxv128i8_nxv128i32 = sext <vscale x 128 x i8> undef to <vscale x 128 x i32>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nxv128i8_nxv128i128 = sext <vscale x 128 x i8> undef to <vscale x 128 x i128>
@@ -315,16 +165,6 @@ define void @sext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %nxv128i1_nxv128i16 = sext <vscale x 128 x i1> undef to <vscale x 128 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %nxv128i1_nxv128i32 = sext <vscale x 128 x i1> undef to <vscale x 128 x i32>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nxv128i1_nxv128i128 = sext <vscale x 128 x i1> undef to <vscale x 128 x i128>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv128i8_nxv128i16 = call <vscale x 128 x i16> @llvm.vp.sext.nxv128i16.nxv128i8(<vscale x 128 x i8> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %vp_nxv128i8_nxv128i32 = call <vscale x 128 x i32> @llvm.vp.sext.nxv128i32.nxv128i8(<vscale x 128 x i8> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv128i8_nxv128i128 = call <vscale x 128 x i128> @llvm.vp.sext.nxv128i128.nxv128i8(<vscale x 128 x i8> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv128i16_nxv128i32 = call <vscale x 128 x i32> @llvm.vp.sext.nxv128i32.nxv128i16(<vscale x 128 x i16> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv128i16_nxv128i128 = call <vscale x 128 x i128> @llvm.vp.sext.nxv128i128.nxv128i16(<vscale x 128 x i16> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv128i32_nxv128i128 = call <vscale x 128 x i128> @llvm.vp.sext.nxv128i128.nxv128i32(<vscale x 128 x i32> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv128i1_nxv128i8 = call <vscale x 128 x i8> @llvm.vp.sext.nxv128i8.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_nxv128i1_nxv128i16 = call <vscale x 128 x i16> @llvm.vp.sext.nxv128i16.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_nxv128i1_nxv128i32 = call <vscale x 128 x i32> @llvm.vp.sext.nxv128i32.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv128i1_nxv128i128 = call <vscale x 128 x i128> @llvm.vp.sext.nxv128i128.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8_v2i16 = sext <2 x i8> undef to <2 x i16>
@@ -694,16 +534,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_v2i16 = zext <2 x i1> undef to <2 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_v2i32 = zext <2 x i1> undef to <2 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_v2i64 = zext <2 x i1> undef to <2 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i8_v2i16 = call <2 x i16> @llvm.vp.zext.v2i16.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i8_v2i32 = call <2 x i32> @llvm.vp.zext.v2i32.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i8_v2i64 = call <2 x i64> @llvm.vp.zext.v2i64.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i16_v2i32 = call <2 x i32> @llvm.vp.zext.v2i32.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i16_v2i64 = call <2 x i64> @llvm.vp.zext.v2i64.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i32_v2i64 = call <2 x i64> @llvm.vp.zext.v2i64.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i1_v2i8 = call <2 x i8> @llvm.vp.zext.v2i8.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i1_v2i16 = call <2 x i16> @llvm.vp.zext.v2i16.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i1_v2i32 = call <2 x i32> @llvm.vp.zext.v2i32.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i1_v2i64 = call <2 x i64> @llvm.vp.zext.v2i64.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_v4i16 = zext <4 x i8> undef to <4 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_v4i32 = zext <4 x i8> undef to <4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i8_v4i64 = zext <4 x i8> undef to <4 x i64>
@@ -714,16 +544,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i1_v4i16 = zext <4 x i1> undef to <4 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i1_v4i32 = zext <4 x i1> undef to <4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4i1_v4i64 = zext <4 x i1> undef to <4 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i8_v4i16 = call <4 x i16> @llvm.vp.zext.v4i16.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i8_v4i32 = call <4 x i32> @llvm.vp.zext.v4i32.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i8_v4i64 = call <4 x i64> @llvm.vp.zext.v4i64.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i16_v4i32 = call <4 x i32> @llvm.vp.zext.v4i32.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i16_v4i64 = call <4 x i64> @llvm.vp.zext.v4i64.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i32_v4i64 = call <4 x i64> @llvm.vp.zext.v4i64.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i1_v4i8 = call <4 x i8> @llvm.vp.zext.v4i8.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i1_v4i16 = call <4 x i16> @llvm.vp.zext.v4i16.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i1_v4i32 = call <4 x i32> @llvm.vp.zext.v4i32.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4i1_v4i64 = call <4 x i64> @llvm.vp.zext.v4i64.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_v8i16 = zext <8 x i8> undef to <8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i8_v8i32 = zext <8 x i8> undef to <8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i8_v8i64 = zext <8 x i8> undef to <8 x i64>
@@ -734,16 +554,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i1_v8i16 = zext <8 x i1> undef to <8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i1_v8i32 = zext <8 x i1> undef to <8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i1_v8i64 = zext <8 x i1> undef to <8 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v8i8_v8i16 = call <8 x i16> @llvm.vp.zext.v8i16.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i8_v8i32 = call <8 x i32> @llvm.vp.zext.v8i32.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i8_v8i64 = call <8 x i64> @llvm.vp.zext.v8i64.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i16_v8i32 = call <8 x i32> @llvm.vp.zext.v8i32.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i16_v8i64 = call <8 x i64> @llvm.vp.zext.v8i64.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i32_v8i64 = call <8 x i64> @llvm.vp.zext.v8i64.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i1_v8i8 = call <8 x i8> @llvm.vp.zext.v8i8.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i1_v8i16 = call <8 x i16> @llvm.vp.zext.v8i16.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i1_v8i32 = call <8 x i32> @llvm.vp.zext.v8i32.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8i1_v8i64 = call <8 x i64> @llvm.vp.zext.v8i64.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i8_v16i16 = zext <16 x i8> undef to <16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i8_v16i32 = zext <16 x i8> undef to <16 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16i8_v16i64 = zext <16 x i8> undef to <16 x i64>
@@ -754,16 +564,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i1_v16i16 = zext <16 x i1> undef to <16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16i1_v16i32 = zext <16 x i1> undef to <16 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16i1_v16i64 = zext <16 x i1> undef to <16 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16i8_v16i16 = call <16 x i16> @llvm.vp.zext.v16i16.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16i8_v16i32 = call <16 x i32> @llvm.vp.zext.v16i32.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i8_v16i64 = call <16 x i64> @llvm.vp.zext.v16i64.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16i16_v16i32 = call <16 x i32> @llvm.vp.zext.v16i32.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i16_v16i64 = call <16 x i64> @llvm.vp.zext.v16i64.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i32_v16i64 = call <16 x i64> @llvm.vp.zext.v16i64.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16i1_v16i8 = call <16 x i8> @llvm.vp.zext.v16i8.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16i1_v16i16 = call <16 x i16> @llvm.vp.zext.v16i16.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i1_v16i32 = call <16 x i32> @llvm.vp.zext.v16i32.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16i1_v16i64 = call <16 x i64> @llvm.vp.zext.v16i64.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i8_v32i16 = zext <32 x i8> undef to <32 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v32i8_v32i32 = zext <32 x i8> undef to <32 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v32i8_v32i64 = zext <32 x i8> undef to <32 x i64>
@@ -774,16 +574,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v32i1_v32i16 = zext <32 x i1> undef to <32 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v32i1_v32i32 = zext <32 x i1> undef to <32 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v32i1_v32i64 = zext <32 x i1> undef to <32 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32i8_v32i16 = call <32 x i16> @llvm.vp.zext.v32i16.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32i8_v32i32 = call <32 x i32> @llvm.vp.zext.v32i32.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32i8_v32i64 = call <32 x i64> @llvm.vp.zext.v32i64.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32i16_v32i32 = call <32 x i32> @llvm.vp.zext.v32i32.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32i16_v32i64 = call <32 x i64> @llvm.vp.zext.v32i64.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32i32_v32i64 = call <32 x i64> @llvm.vp.zext.v32i64.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32i1_v32i8 = call <32 x i8> @llvm.vp.zext.v32i8.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32i1_v32i16 = call <32 x i16> @llvm.vp.zext.v32i16.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v32i1_v32i32 = call <32 x i32> @llvm.vp.zext.v32i32.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32i1_v32i64 = call <32 x i64> @llvm.vp.zext.v32i64.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v64i8_v64i16 = zext <64 x i8> undef to <64 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v64i8_v64i32 = zext <64 x i8> undef to <64 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %v64i8_v64i64 = zext <64 x i8> undef to <64 x i64>
@@ -794,16 +584,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v64i1_v64i16 = zext <64 x i1> undef to <64 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v64i1_v64i32 = zext <64 x i1> undef to <64 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %v64i1_v64i64 = zext <64 x i1> undef to <64 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v64i8_v64i16 = call <64 x i16> @llvm.vp.zext.v64i16.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v64i8_v64i32 = call <64 x i32> @llvm.vp.zext.v64i32.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_v64i8_v64i64 = call <64 x i64> @llvm.vp.zext.v64i64.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v64i16_v64i32 = call <64 x i32> @llvm.vp.zext.v64i32.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_v64i16_v64i64 = call <64 x i64> @llvm.vp.zext.v64i64.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v64i32_v64i64 = call <64 x i64> @llvm.vp.zext.v64i64.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v64i1_v64i8 = call <64 x i8> @llvm.vp.zext.v64i8.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v64i1_v64i16 = call <64 x i16> @llvm.vp.zext.v64i16.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v64i1_v64i32 = call <64 x i32> @llvm.vp.zext.v64i32.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_v64i1_v64i64 = call <64 x i64> @llvm.vp.zext.v64i64.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v128i8_v128i16 = zext <128 x i8> undef to <128 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %v128i8_v128i32 = zext <128 x i8> undef to <128 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %v128i8_v128i64 = zext <128 x i8> undef to <128 x i64>
@@ -814,16 +594,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v128i1_v128i16 = zext <128 x i1> undef to <128 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %v128i1_v128i32 = zext <128 x i1> undef to <128 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %v128i1_v128i64 = zext <128 x i1> undef to <128 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v128i8_v128i16 = call <128 x i16> @llvm.vp.zext.v128i16.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_v128i8_v128i32 = call <128 x i32> @llvm.vp.zext.v128i32.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %vp_v128i8_v128i64 = call <128 x i64> @llvm.vp.zext.v128i64.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v128i16_v128i32 = call <128 x i32> @llvm.vp.zext.v128i32.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %vp_v128i16_v128i64 = call <128 x i64> @llvm.vp.zext.v128i64.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v128i32_v128i64 = call <128 x i64> @llvm.vp.zext.v128i64.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v128i1_v128i8 = call <128 x i8> @llvm.vp.zext.v128i8.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v128i1_v128i16 = call <128 x i16> @llvm.vp.zext.v128i16.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_v128i1_v128i32 = call <128 x i32> @llvm.vp.zext.v128i32.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_v128i1_v128i64 = call <128 x i64> @llvm.vp.zext.v128i64.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v256i8_v256i16 = zext <256 x i8> undef to <256 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %v256i8_v256i32 = zext <256 x i8> undef to <256 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 142 for instruction: %v256i8_v256i64 = zext <256 x i8> undef to <256 x i64>
@@ -834,16 +604,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %v256i1_v256i16 = zext <256 x i1> undef to <256 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %v256i1_v256i32 = zext <256 x i1> undef to <256 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 151 for instruction: %v256i1_v256i64 = zext <256 x i1> undef to <256 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v256i8_v256i16 = call <256 x i16> @llvm.vp.zext.v256i16.v256i8(<256 x i8> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %vp_v256i8_v256i32 = call <256 x i32> @llvm.vp.zext.v256i32.v256i8(<256 x i8> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 142 for instruction: %vp_v256i8_v256i64 = call <256 x i64> @llvm.vp.zext.v256i64.v256i8(<256 x i8> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v256i16_v256i32 = call <256 x i32> @llvm.vp.zext.v256i32.v256i16(<256 x i16> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %vp_v256i16_v256i64 = call <256 x i64> @llvm.vp.zext.v256i64.v256i16(<256 x i16> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %vp_v256i32_v256i64 = call <256 x i64> @llvm.vp.zext.v256i64.v256i32(<256 x i32> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v256i1_v256i8 = call <256 x i8> @llvm.vp.zext.v256i8.v256i1(<256 x i1> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_v256i1_v256i16 = call <256 x i16> @llvm.vp.zext.v256i16.v256i1(<256 x i1> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_v256i1_v256i32 = call <256 x i32> @llvm.vp.zext.v256i32.v256i1(<256 x i1> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 151 for instruction: %vp_v256i1_v256i64 = call <256 x i64> @llvm.vp.zext.v256i64.v256i1(<256 x i1> undef, <256 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8_nxv1i16 = zext <vscale x 1 x i8> undef to <vscale x 1 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8_nxv1i32 = zext <vscale x 1 x i8> undef to <vscale x 1 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8_nxv1i64 = zext <vscale x 1 x i8> undef to <vscale x 1 x i64>
@@ -854,16 +614,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i1_nxv1i16 = zext <vscale x 1 x i1> undef to <vscale x 1 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i1_nxv1i32 = zext <vscale x 1 x i1> undef to <vscale x 1 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i1_nxv1i64 = zext <vscale x 1 x i1> undef to <vscale x 1 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i8_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.zext.nxv1i16.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i8_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.zext.nxv1i32.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i8_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.zext.nxv1i64.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i16_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.zext.nxv1i32.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i16_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.zext.nxv1i64.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i32_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.zext.nxv1i64.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i1_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.zext.nxv1i8.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i1_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.zext.nxv1i16.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i1_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.zext.nxv1i32.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i1_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.zext.nxv1i64.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8_nxv2i16 = zext <vscale x 2 x i8> undef to <vscale x 2 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8_nxv2i32 = zext <vscale x 2 x i8> undef to <vscale x 2 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i8_nxv2i64 = zext <vscale x 2 x i8> undef to <vscale x 2 x i64>
@@ -874,16 +624,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i1_nxv2i16 = zext <vscale x 2 x i1> undef to <vscale x 2 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i1_nxv2i32 = zext <vscale x 2 x i1> undef to <vscale x 2 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv2i1_nxv2i64 = zext <vscale x 2 x i1> undef to <vscale x 2 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i8_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.zext.nxv2i16.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i8_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.zext.nxv2i32.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i8_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.zext.nxv2i64.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i16_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.zext.nxv2i32.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i16_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.zext.nxv2i64.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i32_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.zext.nxv2i64.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i1_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.zext.nxv2i8.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i1_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.zext.nxv2i16.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i1_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.zext.nxv2i32.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv2i1_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.zext.nxv2i64.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8_nxv4i16 = zext <vscale x 4 x i8> undef to <vscale x 4 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i8_nxv4i32 = zext <vscale x 4 x i8> undef to <vscale x 4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i8_nxv4i64 = zext <vscale x 4 x i8> undef to <vscale x 4 x i64>
@@ -894,16 +634,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i1_nxv4i16 = zext <vscale x 4 x i1> undef to <vscale x 4 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i1_nxv4i32 = zext <vscale x 4 x i1> undef to <vscale x 4 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv4i1_nxv4i64 = zext <vscale x 4 x i1> undef to <vscale x 4 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv4i8_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.zext.nxv4i16.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i8_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.zext.nxv4i32.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i8_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.zext.nxv4i64.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i16_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.zext.nxv4i32.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i16_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.zext.nxv4i64.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i32_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.zext.nxv4i64.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i1_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.zext.nxv4i8.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i1_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.zext.nxv4i16.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i1_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.zext.nxv4i32.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv4i1_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.zext.nxv4i64.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i8_nxv8i16 = zext <vscale x 8 x i8> undef to <vscale x 8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i8_nxv8i32 = zext <vscale x 8 x i8> undef to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i8_nxv8i64 = zext <vscale x 8 x i8> undef to <vscale x 8 x i64>
@@ -914,16 +644,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i1_nxv8i16 = zext <vscale x 8 x i1> undef to <vscale x 8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i1_nxv8i32 = zext <vscale x 8 x i1> undef to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv8i1_nxv8i64 = zext <vscale x 8 x i1> undef to <vscale x 8 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8i8_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.zext.nxv8i16.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8i8_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.zext.nxv8i32.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i8_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.zext.nxv8i64.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8i16_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.zext.nxv8i32.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i16_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.zext.nxv8i64.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i32_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.zext.nxv8i64.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8i1_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.zext.nxv8i8.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8i1_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.zext.nxv8i16.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i1_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.zext.nxv8i32.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv8i1_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.zext.nxv8i64.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i8_nxv16i16 = zext <vscale x 16 x i8> undef to <vscale x 16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i8_nxv16i32 = zext <vscale x 16 x i8> undef to <vscale x 16 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv16i8_nxv16i64 = zext <vscale x 16 x i8> undef to <vscale x 16 x i64>
@@ -934,16 +654,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i1_nxv16i16 = zext <vscale x 16 x i1> undef to <vscale x 16 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv16i1_nxv16i32 = zext <vscale x 16 x i1> undef to <vscale x 16 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv16i1_nxv16i64 = zext <vscale x 16 x i1> undef to <vscale x 16 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16i8_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.zext.nxv16i16.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16i8_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.zext.nxv16i32.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16i8_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.zext.nxv16i64.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16i16_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.zext.nxv16i32.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16i16_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.zext.nxv16i64.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16i32_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.zext.nxv16i64.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16i1_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.zext.nxv16i8.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16i1_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.zext.nxv16i16.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv16i1_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.zext.nxv16i32.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16i1_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.zext.nxv16i64.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv32i8_nxv32i16 = zext <vscale x 32 x i8> undef to <vscale x 32 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv32i8_nxv32i32 = zext <vscale x 32 x i8> undef to <vscale x 32 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %nxv32i8_nxv32i64 = zext <vscale x 32 x i8> undef to <vscale x 32 x i64>
@@ -954,16 +664,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv32i1_nxv32i16 = zext <vscale x 32 x i1> undef to <vscale x 32 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv32i1_nxv32i32 = zext <vscale x 32 x i1> undef to <vscale x 32 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %nxv32i1_nxv32i64 = zext <vscale x 32 x i1> undef to <vscale x 32 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv32i8_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.zext.nxv32i16.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv32i8_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.zext.nxv32i32.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_nxv32i8_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.zext.nxv32i64.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv32i16_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.zext.nxv32i32.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_nxv32i16_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.zext.nxv32i64.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv32i32_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.zext.nxv32i64.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv32i1_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.zext.nxv32i8.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv32i1_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.zext.nxv32i16.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv32i1_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.zext.nxv32i32.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_nxv32i1_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.zext.nxv32i64.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv64i8_nxv64i16 = zext <vscale x 64 x i8> undef to <vscale x 64 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %nxv64i8_nxv64i32 = zext <vscale x 64 x i8> undef to <vscale x 64 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %nxv64i8_nxv64i64 = zext <vscale x 64 x i8> undef to <vscale x 64 x i64>
@@ -974,16 +674,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv64i1_nxv64i16 = zext <vscale x 64 x i1> undef to <vscale x 64 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %nxv64i1_nxv64i32 = zext <vscale x 64 x i1> undef to <vscale x 64 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %nxv64i1_nxv64i64 = zext <vscale x 64 x i1> undef to <vscale x 64 x i64>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv64i8_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.zext.nxv64i16.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %vp_nxv64i8_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.zext.nxv64i32.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %vp_nxv64i8_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.zext.nxv64i64.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv64i16_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.zext.nxv64i32.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %vp_nxv64i16_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.zext.nxv64i64.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv64i32_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.zext.nxv64i64.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv64i1_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.zext.nxv64i8.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv64i1_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.zext.nxv64i16.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_nxv64i1_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.zext.nxv64i32.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_nxv64i1_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.zext.nxv64i64.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %nxv128i8_nxv128i16 = zext <vscale x 128 x i8> undef to <vscale x 128 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %nxv128i8_nxv128i32 = zext <vscale x 128 x i8> undef to <vscale x 128 x i32>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nxv128i8_nxv128i128 = zext <vscale x 128 x i8> undef to <vscale x 128 x i128>
@@ -994,16 +684,6 @@ define void @zext() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %nxv128i1_nxv128i16 = zext <vscale x 128 x i1> undef to <vscale x 128 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %nxv128i1_nxv128i32 = zext <vscale x 128 x i1> undef to <vscale x 128 x i32>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nxv128i1_nxv128i128 = zext <vscale x 128 x i1> undef to <vscale x 128 x i128>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv128i8_nxv128i16 = call <vscale x 128 x i16> @llvm.vp.zext.nxv128i16.nxv128i8(<vscale x 128 x i8> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %vp_nxv128i8_nxv128i32 = call <vscale x 128 x i32> @llvm.vp.zext.nxv128i32.nxv128i8(<vscale x 128 x i8> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv128i8_nxv128i128 = call <vscale x 128 x i128> @llvm.vp.zext.nxv128i128.nxv128i8(<vscale x 128 x i8> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv128i16_nxv128i32 = call <vscale x 128 x i32> @llvm.vp.zext.nxv128i32.nxv128i16(<vscale x 128 x i16> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv128i16_nxv128i128 = call <vscale x 128 x i128> @llvm.vp.zext.nxv128i128.nxv128i16(<vscale x 128 x i16> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv128i32_nxv128i128 = call <vscale x 128 x i128> @llvm.vp.zext.nxv128i128.nxv128i32(<vscale x 128 x i32> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv128i1_nxv128i8 = call <vscale x 128 x i8> @llvm.vp.zext.nxv128i8.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %vp_nxv128i1_nxv128i16 = call <vscale x 128 x i16> @llvm.vp.zext.nxv128i16.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_nxv128i1_nxv128i32 = call <vscale x 128 x i32> @llvm.vp.zext.nxv128i32.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv128i1_nxv128i128 = call <vscale x 128 x i128> @llvm.vp.zext.nxv128i128.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8_v2i16 = zext <2 x i8> undef to <2 x i16>
@@ -1368,11 +1048,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_v2i6 = trunc <2 x i16> undef to <2 x i6>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2i4_v2i2 = trunc <2 x i4> undef to <2 x i2>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2i6_v2i4 = trunc <2 x i6> undef to <2 x i4>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i16_v2i2 = call <2 x i2> @llvm.vp.trunc.v2i2.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i16_v2i4 = call <2 x i4> @llvm.vp.trunc.v2i4.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i16_v2i6 = call <2 x i6> @llvm.vp.trunc.v2i6.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %vp_v2i4_v2i2 = call <2 x i2> @llvm.vp.trunc.v2i2.v2i4(<2 x i4> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %vp_v2i6_v2i4 = call <2 x i4> @llvm.vp.trunc.v2i4.v2i6(<2 x i6> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_v2i8 = trunc <2 x i16> undef to <2 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i32_v2i8 = trunc <2 x i32> undef to <2 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i64_v2i8 = trunc <2 x i64> undef to <2 x i8>
@@ -1383,16 +1058,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i16_v2i1 = trunc <2 x i16> undef to <2 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i32_v2i1 = trunc <2 x i32> undef to <2 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i64_v2i1 = trunc <2 x i64> undef to <2 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i16_v2i8 = call <2 x i8> @llvm.vp.trunc.v2i8.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i32_v2i8 = call <2 x i8> @llvm.vp.trunc.v2i8.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2i64_v2i8 = call <2 x i8> @llvm.vp.trunc.v2i8.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i32_v2i16 = call <2 x i16> @llvm.vp.trunc.v2i16.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i64_v2i16 = call <2 x i16> @llvm.vp.trunc.v2i16.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2i64_v2i32 = call <2 x i32> @llvm.vp.trunc.v2i32.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i8_v2i1 = call <2 x i1> @llvm.vp.trunc.v2i1.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i16_v2i1 = call <2 x i1> @llvm.vp.trunc.v2i1.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i32_v2i1 = call <2 x i1> @llvm.vp.trunc.v2i1.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2i64_v2i1 = call <2 x i1> @llvm.vp.trunc.v2i1.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_v4i8 = trunc <4 x i16> undef to <4 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i32_v4i8 = trunc <4 x i32> undef to <4 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i64_v4i8 = trunc <4 x i64> undef to <4 x i8>
@@ -1403,16 +1068,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i16_v4i1 = trunc <4 x i16> undef to <4 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i32_v4i1 = trunc <4 x i32> undef to <4 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4i64_v4i1 = trunc <4 x i64> undef to <4 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i16_v4i8 = call <4 x i8> @llvm.vp.trunc.v4i8.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i32_v4i8 = call <4 x i8> @llvm.vp.trunc.v4i8.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4i64_v4i8 = call <4 x i8> @llvm.vp.trunc.v4i8.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i32_v4i16 = call <4 x i16> @llvm.vp.trunc.v4i16.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i64_v4i16 = call <4 x i16> @llvm.vp.trunc.v4i16.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4i64_v4i32 = call <4 x i32> @llvm.vp.trunc.v4i32.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i8_v4i1 = call <4 x i1> @llvm.vp.trunc.v4i1.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i16_v4i1 = call <4 x i1> @llvm.vp.trunc.v4i1.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4i32_v4i1 = call <4 x i1> @llvm.vp.trunc.v4i1.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4i64_v4i1 = call <4 x i1> @llvm.vp.trunc.v4i1.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_v8i8 = trunc <8 x i16> undef to <8 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32_v8i8 = trunc <8 x i32> undef to <8 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64_v8i8 = trunc <8 x i64> undef to <8 x i8>
@@ -1423,16 +1078,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i16_v8i1 = trunc <8 x i16> undef to <8 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i32_v8i1 = trunc <8 x i32> undef to <8 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i64_v8i1 = trunc <8 x i64> undef to <8 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v8i16_v8i8 = call <8 x i8> @llvm.vp.trunc.v8i8.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i32_v8i8 = call <8 x i8> @llvm.vp.trunc.v8i8.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i64_v8i8 = call <8 x i8> @llvm.vp.trunc.v8i8.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v8i32_v8i16 = call <8 x i16> @llvm.vp.trunc.v8i16.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v8i64_v8i16 = call <8 x i16> @llvm.vp.trunc.v8i16.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i64_v8i32 = call <8 x i32> @llvm.vp.trunc.v8i32.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i8_v8i1 = call <8 x i1> @llvm.vp.trunc.v8i1.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8i16_v8i1 = call <8 x i1> @llvm.vp.trunc.v8i1.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8i32_v8i1 = call <8 x i1> @llvm.vp.trunc.v8i1.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8i64_v8i1 = call <8 x i1> @llvm.vp.trunc.v8i1.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_v16i8 = trunc <2 x i16> undef to <2 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i32_v16i8 = trunc <2 x i32> undef to <2 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i64_v16i8 = trunc <2 x i64> undef to <2 x i8>
@@ -1443,16 +1088,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16_v16i1 = trunc <2 x i16> undef to <2 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i32_v16i1 = trunc <2 x i32> undef to <2 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i64_v16i1 = trunc <2 x i64> undef to <2 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v16i16_v16i8 = call <16 x i8> @llvm.vp.trunc.v16i8.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v16i32_v16i8 = call <16 x i8> @llvm.vp.trunc.v16i8.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v16i64_v16i8 = call <16 x i8> @llvm.vp.trunc.v16i8.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16i32_v16i16 = call <16 x i16> @llvm.vp.trunc.v16i16.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v16i64_v16i16 = call <16 x i16> @llvm.vp.trunc.v16i16.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16i64_v16i32 = call <16 x i32> @llvm.vp.trunc.v16i32.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16i8_v16i1 = call <16 x i1> @llvm.vp.trunc.v16i1.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16i16_v16i1 = call <16 x i1> @llvm.vp.trunc.v16i1.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16i32_v16i1 = call <16 x i1> @llvm.vp.trunc.v16i1.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16i64_v16i1 = call <16 x i1> @llvm.vp.trunc.v16i1.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_v32i8 = trunc <16 x i16> undef to <16 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i32_v32i8 = trunc <16 x i32> undef to <16 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v32i64_v32i8 = trunc <16 x i64> undef to <16 x i8>
@@ -1463,16 +1098,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i16_v32i1 = trunc <16 x i16> undef to <16 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v32i32_v32i1 = trunc <16 x i32> undef to <16 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v32i64_v32i1 = trunc <16 x i64> undef to <16 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v32i16_v32i8 = call <32 x i8> @llvm.vp.trunc.v32i8.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v32i32_v32i8 = call <32 x i8> @llvm.vp.trunc.v32i8.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v32i64_v32i8 = call <32 x i8> @llvm.vp.trunc.v32i8.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32i32_v32i16 = call <32 x i16> @llvm.vp.trunc.v32i16.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_v32i64_v32i16 = call <32 x i16> @llvm.vp.trunc.v32i16.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v32i64_v32i32 = call <32 x i32> @llvm.vp.trunc.v32i32.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32i8_v32i1 = call <32 x i1> @llvm.vp.trunc.v32i1.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32i16_v32i1 = call <32 x i1> @llvm.vp.trunc.v32i1.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v32i32_v32i1 = call <32 x i1> @llvm.vp.trunc.v32i1.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_v32i64_v32i1 = call <32 x i1> @llvm.vp.trunc.v32i1.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i16_v64i8 = trunc <64 x i16> undef to <64 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %v64i32_v64i8 = trunc <64 x i32> undef to <64 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v64i64_v64i8 = trunc <64 x i64> undef to <64 x i8>
@@ -1483,16 +1108,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v64i16_v64i1 = trunc <64 x i16> undef to <64 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v64i32_v64i1 = trunc <64 x i32> undef to <64 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %v64i64_v64i1 = trunc <64 x i64> undef to <64 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v64i16_v64i8 = call <64 x i8> @llvm.vp.trunc.v64i8.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_v64i32_v64i8 = call <64 x i8> @llvm.vp.trunc.v64i8.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v64i64_v64i8 = call <64 x i8> @llvm.vp.trunc.v64i8.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v64i32_v64i16 = call <64 x i16> @llvm.vp.trunc.v64i16.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_v64i64_v64i16 = call <64 x i16> @llvm.vp.trunc.v64i16.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v64i64_v64i32 = call <64 x i32> @llvm.vp.trunc.v64i32.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v64i8_v64i1 = call <64 x i1> @llvm.vp.trunc.v64i1.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v64i16_v64i1 = call <64 x i1> @llvm.vp.trunc.v64i1.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_v64i32_v64i1 = call <64 x i1> @llvm.vp.trunc.v64i1.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_v64i64_v64i1 = call <64 x i1> @llvm.vp.trunc.v64i1.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v128i16_v128i8 = trunc <128 x i16> undef to <128 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %v128i32_v128i8 = trunc <128 x i32> undef to <128 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v128i64_v128i8 = trunc <128 x i64> undef to <128 x i8>
@@ -1503,16 +1118,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v128i16_v128i1 = trunc <128 x i16> undef to <128 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %v128i32_v128i1 = trunc <128 x i32> undef to <128 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %v128i64_v128i1 = trunc <128 x i64> undef to <128 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v128i16_v128i8 = call <128 x i8> @llvm.vp.trunc.v128i8.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_v128i32_v128i8 = call <128 x i8> @llvm.vp.trunc.v128i8.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v128i64_v128i8 = call <128 x i8> @llvm.vp.trunc.v128i8.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v128i32_v128i16 = call <128 x i16> @llvm.vp.trunc.v128i16.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_v128i64_v128i16 = call <128 x i16> @llvm.vp.trunc.v128i16.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_v128i64_v128i32 = call <128 x i32> @llvm.vp.trunc.v128i32.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v128i8_v128i1 = call <128 x i1> @llvm.vp.trunc.v128i1.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_v128i16_v128i1 = call <128 x i1> @llvm.vp.trunc.v128i1.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_v128i32_v128i1 = call <128 x i1> @llvm.vp.trunc.v128i1.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %vp_v128i64_v128i1 = call <128 x i1> @llvm.vp.trunc.v128i1.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %v256i16_v256i8 = trunc <256 x i16> undef to <256 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %v256i32_v256i8 = trunc <256 x i32> undef to <256 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %v256i64_v256i8 = trunc <256 x i64> undef to <256 x i8>
@@ -1523,16 +1128,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %v256i16_v256i1 = trunc <256 x i16> undef to <256 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %v256i32_v256i1 = trunc <256 x i32> undef to <256 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 271 for instruction: %v256i64_v256i1 = trunc <256 x i64> undef to <256 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v256i16_v256i8 = call <256 x i8> @llvm.vp.trunc.v256i8.v256i16(<256 x i16> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_v256i32_v256i8 = call <256 x i8> @llvm.vp.trunc.v256i8.v256i32(<256 x i32> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %vp_v256i64_v256i8 = call <256 x i8> @llvm.vp.trunc.v256i8.v256i64(<256 x i64> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_v256i32_v256i16 = call <256 x i16> @llvm.vp.trunc.v256i16.v256i32(<256 x i32> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %vp_v256i64_v256i16 = call <256 x i16> @llvm.vp.trunc.v256i16.v256i64(<256 x i64> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %vp_v256i64_v256i32 = call <256 x i32> @llvm.vp.trunc.v256i32.v256i64(<256 x i64> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_v256i8_v256i1 = call <256 x i1> @llvm.vp.trunc.v256i1.v256i8(<256 x i8> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_v256i16_v256i1 = call <256 x i1> @llvm.vp.trunc.v256i1.v256i16(<256 x i16> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %vp_v256i32_v256i1 = call <256 x i1> @llvm.vp.trunc.v256i1.v256i32(<256 x i32> undef, <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 271 for instruction: %vp_v256i64_v256i1 = call <256 x i1> @llvm.vp.trunc.v256i1.v256i64(<256 x i64> undef, <256 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16_nxv1i8 = trunc <vscale x 1 x i16> undef to <vscale x 1 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i32_nxv1i8 = trunc <vscale x 1 x i32> undef to <vscale x 1 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1i64_nxv1i8 = trunc <vscale x 1 x i64> undef to <vscale x 1 x i8>
@@ -1543,16 +1138,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i16_nxv1i1 = trunc <vscale x 1 x i16> undef to <vscale x 1 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i32_nxv1i1 = trunc <vscale x 1 x i32> undef to <vscale x 1 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i64_nxv1i1 = trunc <vscale x 1 x i64> undef to <vscale x 1 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i16_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.trunc.nxv1i8.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i32_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.trunc.nxv1i8.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1i64_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.trunc.nxv1i8.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i32_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.trunc.nxv1i16.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i64_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.trunc.nxv1i16.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1i64_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.trunc.nxv1i32.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i8_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.trunc.nxv1i1.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i16_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.trunc.nxv1i1.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i32_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.trunc.nxv1i1.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1i64_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.trunc.nxv1i1.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16_nxv2i8 = trunc <vscale x 2 x i16> undef to <vscale x 2 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i32_nxv2i8 = trunc <vscale x 2 x i32> undef to <vscale x 2 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2i64_nxv2i8 = trunc <vscale x 2 x i64> undef to <vscale x 2 x i8>
@@ -1563,16 +1148,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i16_nxv2i1 = trunc <vscale x 2 x i16> undef to <vscale x 2 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i32_nxv2i1 = trunc <vscale x 2 x i32> undef to <vscale x 2 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv2i64_nxv2i1 = trunc <vscale x 2 x i64> undef to <vscale x 2 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i16_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.trunc.nxv2i8.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i32_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.trunc.nxv2i8.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2i64_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.trunc.nxv2i8.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i32_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.trunc.nxv2i16.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i64_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.trunc.nxv2i16.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2i64_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.trunc.nxv2i32.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i8_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.trunc.nxv2i1.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i16_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.trunc.nxv2i1.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2i32_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.trunc.nxv2i1.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv2i64_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.trunc.nxv2i1.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16_nxv4i8 = trunc <vscale x 4 x i16> undef to <vscale x 4 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32_nxv4i8 = trunc <vscale x 4 x i32> undef to <vscale x 4 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64_nxv4i8 = trunc <vscale x 4 x i64> undef to <vscale x 4 x i8>
@@ -1583,16 +1158,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i16_nxv4i1 = trunc <vscale x 4 x i16> undef to <vscale x 4 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i32_nxv4i1 = trunc <vscale x 4 x i32> undef to <vscale x 4 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv4i64_nxv4i1 = trunc <vscale x 4 x i64> undef to <vscale x 4 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv4i16_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.trunc.nxv4i8.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i32_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.trunc.nxv4i8.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i64_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.trunc.nxv4i8.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv4i32_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.trunc.nxv4i16.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv4i64_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.trunc.nxv4i16.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i64_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.trunc.nxv4i32.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i8_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.trunc.nxv4i1.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4i16_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.trunc.nxv4i1.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4i32_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.trunc.nxv4i1.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv4i64_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.trunc.nxv4i1.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16_nxv8i8 = trunc <vscale x 8 x i16> undef to <vscale x 8 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv8i32_nxv8i8 = trunc <vscale x 8 x i32> undef to <vscale x 8 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %nxv8i64_nxv8i8 = trunc <vscale x 8 x i64> undef to <vscale x 8 x i8>
@@ -1603,16 +1168,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i16_nxv8i1 = trunc <vscale x 8 x i16> undef to <vscale x 8 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i32_nxv8i1 = trunc <vscale x 8 x i32> undef to <vscale x 8 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv8i64_nxv8i1 = trunc <vscale x 8 x i64> undef to <vscale x 8 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv8i16_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.trunc.nxv8i8.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv8i32_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.trunc.nxv8i8.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_nxv8i64_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.trunc.nxv8i8.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8i32_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.trunc.nxv8i16.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv8i64_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.trunc.nxv8i16.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8i64_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.trunc.nxv8i32.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8i8_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.trunc.nxv8i1.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8i16_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.trunc.nxv8i1.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8i32_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.trunc.nxv8i1.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv8i64_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.trunc.nxv8i1.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i16_nxv16i8 = trunc <vscale x 16 x i16> undef to <vscale x 16 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv16i32_nxv16i8 = trunc <vscale x 16 x i32> undef to <vscale x 16 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %nxv16i64_nxv16i8 = trunc <vscale x 16 x i64> undef to <vscale x 16 x i8>
@@ -1623,16 +1178,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i16_nxv16i1 = trunc <vscale x 16 x i16> undef to <vscale x 16 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv16i32_nxv16i1 = trunc <vscale x 16 x i32> undef to <vscale x 16 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %nxv16i64_nxv16i1 = trunc <vscale x 16 x i64> undef to <vscale x 16 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv16i16_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.trunc.nxv16i8.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv16i32_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.trunc.nxv16i8.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_nxv16i64_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.trunc.nxv16i8.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16i32_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.trunc.nxv16i16.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_nxv16i64_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.trunc.nxv16i16.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv16i64_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.trunc.nxv16i32.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16i8_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.trunc.nxv16i1.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16i16_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.trunc.nxv16i1.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv16i32_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.trunc.nxv16i1.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_nxv16i64_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.trunc.nxv16i1.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i16_nxv32i8 = trunc <vscale x 32 x i16> undef to <vscale x 32 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %nxv32i32_nxv32i8 = trunc <vscale x 32 x i32> undef to <vscale x 32 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %nxv32i64_nxv32i8 = trunc <vscale x 32 x i64> undef to <vscale x 32 x i8>
@@ -1643,16 +1188,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv32i16_nxv32i1 = trunc <vscale x 32 x i16> undef to <vscale x 32 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %nxv32i32_nxv32i1 = trunc <vscale x 32 x i32> undef to <vscale x 32 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %nxv32i64_nxv32i1 = trunc <vscale x 32 x i64> undef to <vscale x 32 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv32i16_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.trunc.nxv32i8.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_nxv32i32_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.trunc.nxv32i8.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_nxv32i64_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.trunc.nxv32i8.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv32i32_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.trunc.nxv32i16.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_nxv32i64_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.trunc.nxv32i16.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv32i64_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.trunc.nxv32i32.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv32i8_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.trunc.nxv32i1.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv32i16_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.trunc.nxv32i1.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_nxv32i32_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.trunc.nxv32i1.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_nxv32i64_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.trunc.nxv32i1.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %nxv64i16_nxv64i8 = trunc <vscale x 64 x i16> undef to <vscale x 64 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %nxv64i32_nxv64i8 = trunc <vscale x 64 x i32> undef to <vscale x 64 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %nxv64i64_nxv64i8 = trunc <vscale x 64 x i64> undef to <vscale x 64 x i8>
@@ -1663,16 +1198,6 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %nxv64i16_nxv64i1 = trunc <vscale x 64 x i16> undef to <vscale x 64 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %nxv64i32_nxv64i1 = trunc <vscale x 64 x i32> undef to <vscale x 64 x i1>
; CHECK-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %nxv64i64_nxv64i1 = trunc <vscale x 64 x i64> undef to <vscale x 64 x i1>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv64i16_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.trunc.nxv64i8.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_nxv64i32_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.trunc.nxv64i8.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_nxv64i64_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.trunc.nxv64i8.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv64i32_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.trunc.nxv64i16.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_nxv64i64_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.trunc.nxv64i16.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_nxv64i64_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.trunc.nxv64i32.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv64i8_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.trunc.nxv64i1.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_nxv64i16_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.trunc.nxv64i1.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_nxv64i32_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.trunc.nxv64i1.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %vp_nxv64i64_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.trunc.nxv64i1.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -2026,174 +1551,90 @@ define void @fpext() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16_v2f32 = fpext <2 x half> undef to <2 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f16_v2f64 = fpext <2 x half> undef to <2 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_v2f64 = fpext <2 x float> undef to <2 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f16_v2f32 = call <2 x float> @llvm.vp.fpext.v2f32.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f16_v2f64 = call <2 x double> @llvm.vp.fpext.v2f64.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f32_v2f64 = call <2 x double> @llvm.vp.fpext.v2f64.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f16_v4f32 = fpext <4 x half> undef to <4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f16_v4f64 = fpext <4 x half> undef to <4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4f64 = fpext <4 x float> undef to <4 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f16_v4f32 = call <4 x float> @llvm.vp.fpext.v4f32.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4f16_v4f64 = call <4 x double> @llvm.vp.fpext.v4f64.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f32_v4f64 = call <4 x double> @llvm.vp.fpext.v4f64.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f16_v8f32 = fpext <8 x half> undef to <8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v8f16_v8f64 = fpext <8 x half> undef to <8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f32_v8f64 = fpext <8 x float> undef to <8 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8f16_v8f32 = call <8 x float> @llvm.vp.fpext.v8f32.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v8f16_v8f64 = call <8 x double> @llvm.vp.fpext.v8f64.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8f32_v8f64 = call <8 x double> @llvm.vp.fpext.v8f64.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16f16_v16f32 = fpext <16 x half> undef to <16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v16f16_v16f64 = fpext <16 x half> undef to <16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16f32_v16f64 = fpext <16 x float> undef to <16 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16f16_v16f32 = call <16 x float> @llvm.vp.fpext.v16f32.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v16f16_v16f64 = call <16 x double> @llvm.vp.fpext.v16f64.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16f32_v16f64 = call <16 x double> @llvm.vp.fpext.v16f64.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v32f16_v32f32 = fpext <32 x half> undef to <32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v32f16_v32f64 = fpext <32 x half> undef to <32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v32f32_v32f64 = fpext <32 x float> undef to <32 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32f16_v32f32 = call <32 x float> @llvm.vp.fpext.v32f32.v32f16(<32 x half> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32f16_v32f64 = call <32 x double> @llvm.vp.fpext.v32f64.v32f16(<32 x half> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32f32_v32f64 = call <32 x double> @llvm.vp.fpext.v32f64.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v64f16_v64f32 = fpext <64 x half> undef to <64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v64f16_v64f64 = fpext <64 x half> undef to <64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v64f32_v64f64 = fpext <64 x float> undef to <64 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v64f16_v64f32 = call <64 x float> @llvm.vp.fpext.v64f32.v64f16(<64 x half> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v64f16_v64f64 = call <64 x double> @llvm.vp.fpext.v64f64.v64f16(<64 x half> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v64f32_v64f64 = call <64 x double> @llvm.vp.fpext.v64f64.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v128f16_v128f32 = fpext <128 x half> undef to <128 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %v128f16_v128f64 = fpext <128 x half> undef to <128 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %v128f32_v128f64 = fpext <128 x float> undef to <128 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v128f16_v128f32 = call <128 x float> @llvm.vp.fpext.v128f32.v128f16(<128 x half> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %vp_v128f16_v128f64 = call <128 x double> @llvm.vp.fpext.v128f64.v128f16(<128 x half> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v128f32_v128f64 = call <128 x double> @llvm.vp.fpext.v128f64.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f16_nxv1f32 = fpext <vscale x 1 x half> undef to <vscale x 1 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1f16_nxv1f64 = fpext <vscale x 1 x half> undef to <vscale x 1 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32_nxv1f64 = fpext <vscale x 1 x float> undef to <vscale x 1 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f16_nxv1f32 = call <vscale x 1 x float> @llvm.vp.fpext.nxv1f32.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1f16_nxv1f64 = call <vscale x 1 x double> @llvm.vp.fpext.nxv1f64.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f32_nxv1f64 = call <vscale x 1 x double> @llvm.vp.fpext.nxv1f64.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f16_nxv2f32 = fpext <vscale x 2 x half> undef to <vscale x 2 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2f16_nxv2f64 = fpext <vscale x 2 x half> undef to <vscale x 2 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f32_nxv2f64 = fpext <vscale x 2 x float> undef to <vscale x 2 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f16_nxv2f32 = call <vscale x 2 x float> @llvm.vp.fpext.nxv2f32.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2f16_nxv2f64 = call <vscale x 2 x double> @llvm.vp.fpext.nxv2f64.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f32_nxv2f64 = call <vscale x 2 x double> @llvm.vp.fpext.nxv2f64.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f16_nxv4f32 = fpext <vscale x 4 x half> undef to <vscale x 4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv4f16_nxv4f64 = fpext <vscale x 4 x half> undef to <vscale x 4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f32_nxv4f64 = fpext <vscale x 4 x float> undef to <vscale x 4 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4f16_nxv4f32 = call <vscale x 4 x float> @llvm.vp.fpext.nxv4f32.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv4f16_nxv4f64 = call <vscale x 4 x double> @llvm.vp.fpext.nxv4f64.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4f32_nxv4f64 = call <vscale x 4 x double> @llvm.vp.fpext.nxv4f64.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8f16_nxv8f32 = fpext <vscale x 8 x half> undef to <vscale x 8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv8f16_nxv8f64 = fpext <vscale x 8 x half> undef to <vscale x 8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f32_nxv8f64 = fpext <vscale x 8 x float> undef to <vscale x 8 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8f16_nxv8f32 = call <vscale x 8 x float> @llvm.vp.fpext.nxv8f32.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv8f16_nxv8f64 = call <vscale x 8 x double> @llvm.vp.fpext.nxv8f64.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8f32_nxv8f64 = call <vscale x 8 x double> @llvm.vp.fpext.nxv8f64.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16f16_nxv16f32 = fpext <vscale x 16 x half> undef to <vscale x 16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv16f16_nxv16f64 = fpext <vscale x 16 x half> undef to <vscale x 16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv16f32_nxv16f64 = fpext <vscale x 16 x float> undef to <vscale x 16 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16f16_nxv16f32 = call <vscale x 16 x float> @llvm.vp.fpext.nxv16f32.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16f16_nxv16f64 = call <vscale x 16 x double> @llvm.vp.fpext.nxv16f64.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16f32_nxv16f64 = call <vscale x 16 x double> @llvm.vp.fpext.nxv16f64.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv32f16_nxv32f32 = fpext <vscale x 32 x half> undef to <vscale x 32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv32f16_nxv32f64 = fpext <vscale x 32 x half> undef to <vscale x 32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %nxv32f32_nxv32f64 = fpext <vscale x 32 x float> undef to <vscale x 32 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv32f16_nxv32f32 = call <vscale x 32 x float> @llvm.vp.fpext.nxv32f32.nxv32f16(<vscale x 32 x half> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv32f16_nxv32f64 = call <vscale x 32 x double> @llvm.vp.fpext.nxv32f64.nxv32f16(<vscale x 32 x half> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv32f32_nxv32f64 = call <vscale x 32 x double> @llvm.vp.fpext.nxv32f64.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %nxv64f16_nxv64f32 = fpext <vscale x 64 x half> undef to <vscale x 64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %nxv64f16_nxv64f64 = fpext <vscale x 64 x half> undef to <vscale x 64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %nxv64f32_nxv64f64 = fpext <vscale x 64 x float> undef to <vscale x 64 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv64f16_nxv64f32 = call <vscale x 64 x float> @llvm.vp.fpext.nxv64f32.nxv64f16(<vscale x 64 x half> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %vp_nxv64f16_nxv64f64 = call <vscale x 64 x double> @llvm.vp.fpext.nxv64f64.nxv64f16(<vscale x 64 x half> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv64f32_nxv64f64 = call <vscale x 64 x double> @llvm.vp.fpext.nxv64f64.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVE64X-LABEL: 'fpext'
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f16_v2f32 = fpext <2 x half> undef to <2 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f16_v2f64 = fpext <2 x half> undef to <2 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2f64 = fpext <2 x float> undef to <2 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f16_v2f32 = call <2 x float> @llvm.vp.fpext.v2f32.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f16_v2f64 = call <2 x double> @llvm.vp.fpext.v2f64.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f32_v2f64 = call <2 x double> @llvm.vp.fpext.v2f64.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f16_v4f32 = fpext <4 x half> undef to <4 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f16_v4f64 = fpext <4 x half> undef to <4 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f32_v4f64 = fpext <4 x float> undef to <4 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4f16_v4f32 = call <4 x float> @llvm.vp.fpext.v4f32.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4f16_v4f64 = call <4 x double> @llvm.vp.fpext.v4f64.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4f32_v4f64 = call <4 x double> @llvm.vp.fpext.v4f64.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f16_v8f32 = fpext <8 x half> undef to <8 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f16_v8f64 = fpext <8 x half> undef to <8 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f32_v8f64 = fpext <8 x float> undef to <8 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8f16_v8f32 = call <8 x float> @llvm.vp.fpext.v8f32.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8f16_v8f64 = call <8 x double> @llvm.vp.fpext.v8f64.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8f32_v8f64 = call <8 x double> @llvm.vp.fpext.v8f64.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f16_v16f32 = fpext <16 x half> undef to <16 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f16_v16f64 = fpext <16 x half> undef to <16 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f32_v16f64 = fpext <16 x float> undef to <16 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16f16_v16f32 = call <16 x float> @llvm.vp.fpext.v16f32.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16f16_v16f64 = call <16 x double> @llvm.vp.fpext.v16f64.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16f32_v16f64 = call <16 x double> @llvm.vp.fpext.v16f64.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v32f16_v32f32 = fpext <32 x half> undef to <32 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v32f16_v32f64 = fpext <32 x half> undef to <32 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v32f32_v32f64 = fpext <32 x float> undef to <32 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v32f16_v32f32 = call <32 x float> @llvm.vp.fpext.v32f32.v32f16(<32 x half> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v32f16_v32f64 = call <32 x double> @llvm.vp.fpext.v32f64.v32f16(<32 x half> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v32f32_v32f64 = call <32 x double> @llvm.vp.fpext.v32f64.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v64f16_v64f32 = fpext <64 x half> undef to <64 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v64f16_v64f64 = fpext <64 x half> undef to <64 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v64f32_v64f64 = fpext <64 x float> undef to <64 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %vp_v64f16_v64f32 = call <64 x float> @llvm.vp.fpext.v64f32.v64f16(<64 x half> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %vp_v64f16_v64f64 = call <64 x double> @llvm.vp.fpext.v64f64.v64f16(<64 x half> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %vp_v64f32_v64f64 = call <64 x double> @llvm.vp.fpext.v64f64.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %v128f16_v128f32 = fpext <128 x half> undef to <128 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %v128f16_v128f64 = fpext <128 x half> undef to <128 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %v128f32_v128f64 = fpext <128 x float> undef to <128 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %vp_v128f16_v128f32 = call <128 x float> @llvm.vp.fpext.v128f32.v128f16(<128 x half> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %vp_v128f16_v128f64 = call <128 x double> @llvm.vp.fpext.v128f64.v128f16(<128 x half> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %vp_v128f32_v128f64 = call <128 x double> @llvm.vp.fpext.v128f64.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f16_nxv1f32 = fpext <vscale x 1 x half> undef to <vscale x 1 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f16_nxv1f64 = fpext <vscale x 1 x half> undef to <vscale x 1 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f32_nxv1f64 = fpext <vscale x 1 x float> undef to <vscale x 1 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f16_nxv1f32 = call <vscale x 1 x float> @llvm.vp.fpext.nxv1f32.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f16_nxv1f64 = call <vscale x 1 x double> @llvm.vp.fpext.nxv1f64.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1f64 = call <vscale x 1 x double> @llvm.vp.fpext.nxv1f64.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f16_nxv2f32 = fpext <vscale x 2 x half> undef to <vscale x 2 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f16_nxv2f64 = fpext <vscale x 2 x half> undef to <vscale x 2 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f32_nxv2f64 = fpext <vscale x 2 x float> undef to <vscale x 2 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f16_nxv2f32 = call <vscale x 2 x float> @llvm.vp.fpext.nxv2f32.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f16_nxv2f64 = call <vscale x 2 x double> @llvm.vp.fpext.nxv2f64.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2f64 = call <vscale x 2 x double> @llvm.vp.fpext.nxv2f64.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f16_nxv4f32 = fpext <vscale x 4 x half> undef to <vscale x 4 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f16_nxv4f64 = fpext <vscale x 4 x half> undef to <vscale x 4 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f32_nxv4f64 = fpext <vscale x 4 x float> undef to <vscale x 4 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f16_nxv4f32 = call <vscale x 4 x float> @llvm.vp.fpext.nxv4f32.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f16_nxv4f64 = call <vscale x 4 x double> @llvm.vp.fpext.nxv4f64.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4f64 = call <vscale x 4 x double> @llvm.vp.fpext.nxv4f64.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f16_nxv8f32 = fpext <vscale x 8 x half> undef to <vscale x 8 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f16_nxv8f64 = fpext <vscale x 8 x half> undef to <vscale x 8 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f32_nxv8f64 = fpext <vscale x 8 x float> undef to <vscale x 8 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f16_nxv8f32 = call <vscale x 8 x float> @llvm.vp.fpext.nxv8f32.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f16_nxv8f64 = call <vscale x 8 x double> @llvm.vp.fpext.nxv8f64.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8f64 = call <vscale x 8 x double> @llvm.vp.fpext.nxv8f64.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f16_nxv16f32 = fpext <vscale x 16 x half> undef to <vscale x 16 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f16_nxv16f64 = fpext <vscale x 16 x half> undef to <vscale x 16 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f32_nxv16f64 = fpext <vscale x 16 x float> undef to <vscale x 16 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f16_nxv16f32 = call <vscale x 16 x float> @llvm.vp.fpext.nxv16f32.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f16_nxv16f64 = call <vscale x 16 x double> @llvm.vp.fpext.nxv16f64.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16f64 = call <vscale x 16 x double> @llvm.vp.fpext.nxv16f64.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f16_nxv32f32 = fpext <vscale x 32 x half> undef to <vscale x 32 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f16_nxv32f64 = fpext <vscale x 32 x half> undef to <vscale x 32 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f32_nxv32f64 = fpext <vscale x 32 x float> undef to <vscale x 32 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f16_nxv32f32 = call <vscale x 32 x float> @llvm.vp.fpext.nxv32f32.nxv32f16(<vscale x 32 x half> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f16_nxv32f64 = call <vscale x 32 x double> @llvm.vp.fpext.nxv32f64.nxv32f16(<vscale x 32 x half> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32f64 = call <vscale x 32 x double> @llvm.vp.fpext.nxv32f64.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f16_nxv64f32 = fpext <vscale x 64 x half> undef to <vscale x 64 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f16_nxv64f64 = fpext <vscale x 64 x half> undef to <vscale x 64 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f32_nxv64f64 = fpext <vscale x 64 x float> undef to <vscale x 64 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f16_nxv64f32 = call <vscale x 64 x float> @llvm.vp.fpext.nxv64f32.nxv64f16(<vscale x 64 x half> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f16_nxv64f64 = call <vscale x 64 x double> @llvm.vp.fpext.nxv64f64.nxv64f16(<vscale x 64 x half> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64f64 = call <vscale x 64 x double> @llvm.vp.fpext.nxv64f64.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f16_v2f32 = fpext <2 x half> undef to <2 x float>
@@ -2316,174 +1757,90 @@ define void @fptrunc() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_v2f16 = fptrunc <2 x float> undef to <2 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2f16 = fptrunc <2 x double> undef to <2 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_v2f32 = fptrunc <2 x double> undef to <2 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f32_v2f16 = call <2 x half> @llvm.vp.fptrunc.v2f16.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f64_v2f16 = call <2 x half> @llvm.vp.fptrunc.v2f16.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f64_v2f32 = call <2 x float> @llvm.vp.fptrunc.v2f32.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_v4f16 = fptrunc <4 x float> undef to <4 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64_v4f16 = fptrunc <4 x double> undef to <4 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64_v4f32 = fptrunc <4 x double> undef to <4 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f32_v4f16 = call <4 x half> @llvm.vp.fptrunc.v4f16.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f64_v4f16 = call <4 x half> @llvm.vp.fptrunc.v4f16.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f64_v4f32 = call <4 x float> @llvm.vp.fptrunc.v4f32.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_v8f16 = fptrunc <8 x float> undef to <8 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f64_v8f16 = fptrunc <8 x double> undef to <8 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f64_v8f32 = fptrunc <8 x double> undef to <8 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v8f32_v8f16 = call <8 x half> @llvm.vp.fptrunc.v8f16.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v8f64_v8f16 = call <8 x half> @llvm.vp.fptrunc.v8f16.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8f64_v8f32 = call <8 x float> @llvm.vp.fptrunc.v8f32.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_v16f16 = fptrunc <16 x float> undef to <16 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v16f64_v16f16 = fptrunc <16 x double> undef to <16 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16f64_v16f32 = fptrunc <16 x double> undef to <16 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16f32_v16f16 = call <16 x half> @llvm.vp.fptrunc.v16f16.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v16f64_v16f16 = call <16 x half> @llvm.vp.fptrunc.v16f16.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16f64_v16f32 = call <16 x float> @llvm.vp.fptrunc.v16f32.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32f32_v32f16 = fptrunc <32 x float> undef to <32 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %v32f64_v32f16 = fptrunc <32 x double> undef to <32 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v32f64_v32f32 = fptrunc <32 x double> undef to <32 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32f32_v32f16 = call <32 x half> @llvm.vp.fptrunc.v32f16.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_v32f64_v32f16 = call <32 x half> @llvm.vp.fptrunc.v32f16.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v32f64_v32f32 = call <32 x float> @llvm.vp.fptrunc.v32f32.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v64f32_v64f16 = fptrunc <64 x float> undef to <64 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %v64f64_v64f16 = fptrunc <64 x double> undef to <64 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %v64f64_v64f32 = fptrunc <64 x double> undef to <64 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v64f32_v64f16 = call <64 x half> @llvm.vp.fptrunc.v64f16.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_v64f64_v64f16 = call <64 x half> @llvm.vp.fptrunc.v64f16.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v64f64_v64f32 = call <64 x float> @llvm.vp.fptrunc.v64f32.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %v128f32_v128f16 = fptrunc <128 x float> undef to <128 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %v128f64_v128f16 = fptrunc <128 x double> undef to <128 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %v128f64_v128f32 = fptrunc <128 x double> undef to <128 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v128f32_v128f16 = call <128 x half> @llvm.vp.fptrunc.v128f16.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_v128f64_v128f16 = call <128 x half> @llvm.vp.fptrunc.v128f16.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_v128f64_v128f32 = call <128 x float> @llvm.vp.fptrunc.v128f32.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32_nxv1f16 = fptrunc <vscale x 1 x float> undef to <vscale x 1 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1f64_nxv1f16 = fptrunc <vscale x 1 x double> undef to <vscale x 1 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64_nxv1f32 = fptrunc <vscale x 1 x double> undef to <vscale x 1 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f32_nxv1f16 = call <vscale x 1 x half> @llvm.vp.fptrunc.nxv1f16.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1f64_nxv1f16 = call <vscale x 1 x half> @llvm.vp.fptrunc.nxv1f16.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f64_nxv1f32 = call <vscale x 1 x float> @llvm.vp.fptrunc.nxv1f32.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32_nxv1f16 = fptrunc <vscale x 2 x float> undef to <vscale x 2 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64_nxv1f16 = fptrunc <vscale x 2 x double> undef to <vscale x 2 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64_nxv1f32 = fptrunc <vscale x 2 x double> undef to <vscale x 2 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f32_nxv2f16 = call <vscale x 2 x half> @llvm.vp.fptrunc.nxv2f16.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f64_nxv2f16 = call <vscale x 2 x half> @llvm.vp.fptrunc.nxv2f16.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f64_nxv2f32 = call <vscale x 2 x float> @llvm.vp.fptrunc.nxv2f32.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32_nxv4f16 = fptrunc <vscale x 4 x float> undef to <vscale x 4 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv4f64_nxv4f16 = fptrunc <vscale x 4 x double> undef to <vscale x 4 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f64_nxv4f32 = fptrunc <vscale x 4 x double> undef to <vscale x 4 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv4f32_nxv4f16 = call <vscale x 4 x half> @llvm.vp.fptrunc.nxv4f16.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv4f64_nxv4f16 = call <vscale x 4 x half> @llvm.vp.fptrunc.nxv4f16.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4f64_nxv4f32 = call <vscale x 4 x float> @llvm.vp.fptrunc.nxv4f32.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f32_nxv8f16 = fptrunc <vscale x 8 x float> undef to <vscale x 8 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv8f64_nxv8f16 = fptrunc <vscale x 8 x double> undef to <vscale x 8 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8f64_nxv8f32 = fptrunc <vscale x 8 x double> undef to <vscale x 8 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8f32_nxv8f16 = call <vscale x 8 x half> @llvm.vp.fptrunc.nxv8f16.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv8f64_nxv8f16 = call <vscale x 8 x half> @llvm.vp.fptrunc.nxv8f16.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8f64_nxv8f32 = call <vscale x 8 x float> @llvm.vp.fptrunc.nxv8f32.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f32_nxv16f16 = fptrunc <vscale x 16 x float> undef to <vscale x 16 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %nxv16f64_nxv16f16 = fptrunc <vscale x 16 x double> undef to <vscale x 16 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %nxv16f64_nxv16f32 = fptrunc <vscale x 16 x double> undef to <vscale x 16 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16f32_nxv16f16 = call <vscale x 16 x half> @llvm.vp.fptrunc.nxv16f16.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_nxv16f64_nxv16f16 = call <vscale x 16 x half> @llvm.vp.fptrunc.nxv16f16.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv16f64_nxv16f32 = call <vscale x 16 x float> @llvm.vp.fptrunc.nxv16f32.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %nxv32f32_nxv32f16 = fptrunc <vscale x 32 x float> undef to <vscale x 32 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %nxv32f64_nxv32f16 = fptrunc <vscale x 32 x double> undef to <vscale x 32 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %nxv32f64_nxv32f32 = fptrunc <vscale x 32 x double> undef to <vscale x 32 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv32f32_nxv32f16 = call <vscale x 32 x half> @llvm.vp.fptrunc.nxv32f16.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_nxv32f64_nxv32f16 = call <vscale x 32 x half> @llvm.vp.fptrunc.nxv32f16.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv32f64_nxv32f32 = call <vscale x 32 x float> @llvm.vp.fptrunc.nxv32f32.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %nxv64f32_nxv64f16 = fptrunc <vscale x 64 x float> undef to <vscale x 64 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %nxv64f64_nxv64f16 = fptrunc <vscale x 64 x double> undef to <vscale x 64 x half>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %nxv64f64_nxv64f32 = fptrunc <vscale x 64 x double> undef to <vscale x 64 x float>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv64f32_nxv64f16 = call <vscale x 64 x half> @llvm.vp.fptrunc.nxv64f16.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_nxv64f64_nxv64f16 = call <vscale x 64 x half> @llvm.vp.fptrunc.nxv64f16.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_nxv64f64_nxv64f32 = call <vscale x 64 x float> @llvm.vp.fptrunc.nxv64f32.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVE64X-LABEL: 'fptrunc'
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2f16 = fptrunc <2 x float> undef to <2 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2f16 = fptrunc <2 x double> undef to <2 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2f32 = fptrunc <2 x double> undef to <2 x float>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f32_v2f16 = call <2 x half> @llvm.vp.fptrunc.v2f16.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f64_v2f16 = call <2 x half> @llvm.vp.fptrunc.v2f16.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f64_v2f32 = call <2 x float> @llvm.vp.fptrunc.v2f32.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f32_v4f16 = fptrunc <4 x float> undef to <4 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f64_v4f16 = fptrunc <4 x double> undef to <4 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4f64_v4f32 = fptrunc <4 x double> undef to <4 x float>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4f32_v4f16 = call <4 x half> @llvm.vp.fptrunc.v4f16.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4f64_v4f16 = call <4 x half> @llvm.vp.fptrunc.v4f16.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4f64_v4f32 = call <4 x float> @llvm.vp.fptrunc.v4f32.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f32_v8f16 = fptrunc <8 x float> undef to <8 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f64_v8f16 = fptrunc <8 x double> undef to <8 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8f64_v8f32 = fptrunc <8 x double> undef to <8 x float>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8f32_v8f16 = call <8 x half> @llvm.vp.fptrunc.v8f16.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8f64_v8f16 = call <8 x half> @llvm.vp.fptrunc.v8f16.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8f64_v8f32 = call <8 x float> @llvm.vp.fptrunc.v8f32.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f32_v16f16 = fptrunc <16 x float> undef to <16 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f64_v16f16 = fptrunc <16 x double> undef to <16 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16f64_v16f32 = fptrunc <16 x double> undef to <16 x float>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16f32_v16f16 = call <16 x half> @llvm.vp.fptrunc.v16f16.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16f64_v16f16 = call <16 x half> @llvm.vp.fptrunc.v16f16.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16f64_v16f32 = call <16 x float> @llvm.vp.fptrunc.v16f32.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v32f32_v32f16 = fptrunc <32 x float> undef to <32 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v32f64_v32f16 = fptrunc <32 x double> undef to <32 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v32f64_v32f32 = fptrunc <32 x double> undef to <32 x float>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v32f32_v32f16 = call <32 x half> @llvm.vp.fptrunc.v32f16.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v32f64_v32f16 = call <32 x half> @llvm.vp.fptrunc.v32f16.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v32f64_v32f32 = call <32 x float> @llvm.vp.fptrunc.v32f32.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v64f32_v64f16 = fptrunc <64 x float> undef to <64 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v64f64_v64f16 = fptrunc <64 x double> undef to <64 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v64f64_v64f32 = fptrunc <64 x double> undef to <64 x float>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %vp_v64f32_v64f16 = call <64 x half> @llvm.vp.fptrunc.v64f16.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %vp_v64f64_v64f16 = call <64 x half> @llvm.vp.fptrunc.v64f16.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %vp_v64f64_v64f32 = call <64 x float> @llvm.vp.fptrunc.v64f32.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %v128f32_v128f16 = fptrunc <128 x float> undef to <128 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %v128f64_v128f16 = fptrunc <128 x double> undef to <128 x half>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %v128f64_v128f32 = fptrunc <128 x double> undef to <128 x float>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %vp_v128f32_v128f16 = call <128 x half> @llvm.vp.fptrunc.v128f16.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %vp_v128f64_v128f16 = call <128 x half> @llvm.vp.fptrunc.v128f16.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %vp_v128f64_v128f32 = call <128 x float> @llvm.vp.fptrunc.v128f32.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f32_nxv1f16 = fptrunc <vscale x 1 x float> undef to <vscale x 1 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f64_nxv1f16 = fptrunc <vscale x 1 x double> undef to <vscale x 1 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f64_nxv1f32 = fptrunc <vscale x 1 x double> undef to <vscale x 1 x float>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1f16 = call <vscale x 1 x half> @llvm.vp.fptrunc.nxv1f16.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1f16 = call <vscale x 1 x half> @llvm.vp.fptrunc.nxv1f16.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1f32 = call <vscale x 1 x float> @llvm.vp.fptrunc.nxv1f32.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f32_nxv1f16 = fptrunc <vscale x 2 x float> undef to <vscale x 2 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f64_nxv1f16 = fptrunc <vscale x 2 x double> undef to <vscale x 2 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f64_nxv1f32 = fptrunc <vscale x 2 x double> undef to <vscale x 2 x float>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2f16 = call <vscale x 2 x half> @llvm.vp.fptrunc.nxv2f16.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2f16 = call <vscale x 2 x half> @llvm.vp.fptrunc.nxv2f16.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2f32 = call <vscale x 2 x float> @llvm.vp.fptrunc.nxv2f32.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f32_nxv4f16 = fptrunc <vscale x 4 x float> undef to <vscale x 4 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f64_nxv4f16 = fptrunc <vscale x 4 x double> undef to <vscale x 4 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f64_nxv4f32 = fptrunc <vscale x 4 x double> undef to <vscale x 4 x float>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4f16 = call <vscale x 4 x half> @llvm.vp.fptrunc.nxv4f16.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4f16 = call <vscale x 4 x half> @llvm.vp.fptrunc.nxv4f16.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4f32 = call <vscale x 4 x float> @llvm.vp.fptrunc.nxv4f32.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f32_nxv8f16 = fptrunc <vscale x 8 x float> undef to <vscale x 8 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f64_nxv8f16 = fptrunc <vscale x 8 x double> undef to <vscale x 8 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f64_nxv8f32 = fptrunc <vscale x 8 x double> undef to <vscale x 8 x float>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8f16 = call <vscale x 8 x half> @llvm.vp.fptrunc.nxv8f16.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8f16 = call <vscale x 8 x half> @llvm.vp.fptrunc.nxv8f16.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8f32 = call <vscale x 8 x float> @llvm.vp.fptrunc.nxv8f32.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f32_nxv16f16 = fptrunc <vscale x 16 x float> undef to <vscale x 16 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f64_nxv16f16 = fptrunc <vscale x 16 x double> undef to <vscale x 16 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f64_nxv16f32 = fptrunc <vscale x 16 x double> undef to <vscale x 16 x float>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16f16 = call <vscale x 16 x half> @llvm.vp.fptrunc.nxv16f16.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16f16 = call <vscale x 16 x half> @llvm.vp.fptrunc.nxv16f16.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16f32 = call <vscale x 16 x float> @llvm.vp.fptrunc.nxv16f32.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f32_nxv32f16 = fptrunc <vscale x 32 x float> undef to <vscale x 32 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f64_nxv32f16 = fptrunc <vscale x 32 x double> undef to <vscale x 32 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f64_nxv32f32 = fptrunc <vscale x 32 x double> undef to <vscale x 32 x float>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32f16 = call <vscale x 32 x half> @llvm.vp.fptrunc.nxv32f16.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32f16 = call <vscale x 32 x half> @llvm.vp.fptrunc.nxv32f16.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32f32 = call <vscale x 32 x float> @llvm.vp.fptrunc.nxv32f32.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f32_nxv64f16 = fptrunc <vscale x 64 x float> undef to <vscale x 64 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f64_nxv64f16 = fptrunc <vscale x 64 x double> undef to <vscale x 64 x half>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f64_nxv64f32 = fptrunc <vscale x 64 x double> undef to <vscale x 64 x float>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64f16 = call <vscale x 64 x half> @llvm.vp.fptrunc.nxv64f16.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64f16 = call <vscale x 64 x half> @llvm.vp.fptrunc.nxv64f16.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64f32 = call <vscale x 64 x float> @llvm.vp.fptrunc.nxv64f32.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f32_v2f16 = fptrunc <2 x float> undef to <2 x half>
@@ -2613,16 +1970,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_v2i64 = fptosi <2 x double> undef to <2 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f32_v2i1 = fptosi <2 x float> undef to <2 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f64_v2i1 = fptosi <2 x double> undef to <2 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f32_v2i8 = call <2 x i8> @llvm.vp.fptosi.v2i8.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f64_v2i8 = call <2 x i8> @llvm.vp.fptosi.v2i8.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f32_v2i16 = call <2 x i16> @llvm.vp.fptosi.v2i16.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f64_v2i16 = call <2 x i16> @llvm.vp.fptosi.v2i16.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f32_v2i32 = call <2 x i32> @llvm.vp.fptosi.v2i32.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f64_v2i32 = call <2 x i32> @llvm.vp.fptosi.v2i32.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f32_v2i64 = call <2 x i64> @llvm.vp.fptosi.v2i64.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f64_v2i64 = call <2 x i64> @llvm.vp.fptosi.v2i64.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f32_v2i1 = call <2 x i1> @llvm.vp.fptosi.v2i1.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f64_v2i1 = call <2 x i1> @llvm.vp.fptosi.v2i1.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4i8 = fptosi <4 x float> undef to <4 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f64_v4i8 = fptosi <4 x double> undef to <4 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_v4i16 = fptosi <4 x float> undef to <4 x i16>
@@ -2633,16 +1980,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64_v4i64 = fptosi <4 x double> undef to <4 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f32_v4i1 = fptosi <4 x float> undef to <4 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f64_v4i1 = fptosi <4 x double> undef to <4 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f32_v4i8 = call <4 x i8> @llvm.vp.fptosi.v4i8.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4f64_v4i8 = call <4 x i8> @llvm.vp.fptosi.v4i8.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f32_v4i16 = call <4 x i16> @llvm.vp.fptosi.v4i16.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f64_v4i16 = call <4 x i16> @llvm.vp.fptosi.v4i16.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f32_v4i32 = call <4 x i32> @llvm.vp.fptosi.v4i32.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f64_v4i32 = call <4 x i32> @llvm.vp.fptosi.v4i32.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f32_v4i64 = call <4 x i64> @llvm.vp.fptosi.v4i64.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f64_v4i64 = call <4 x i64> @llvm.vp.fptosi.v4i64.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4f32_v4i1 = call <4 x i1> @llvm.vp.fptosi.v4i1.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4f64_v4i1 = call <4 x i1> @llvm.vp.fptosi.v4i1.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_v8i8 = fptosi <8 x float> undef to <8 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64_v8i8 = fptosi <8 x double> undef to <8 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_v8i16 = fptosi <8 x float> undef to <8 x i16>
@@ -2653,16 +1990,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64_v8i64 = fptosi <8 x double> undef to <8 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f32_v8i1 = fptosi <8 x float> undef to <8 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v8f64_v8i1 = fptosi <8 x double> undef to <8 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8f32_v8i8 = call <8 x i8> @llvm.vp.fptosi.v8i8.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8f64_v8i8 = call <8 x i8> @llvm.vp.fptosi.v8i8.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v8f32_v8i16 = call <8 x i16> @llvm.vp.fptosi.v8i16.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v8f64_v8i16 = call <8 x i16> @llvm.vp.fptosi.v8i16.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8f32_v8i32 = call <8 x i32> @llvm.vp.fptosi.v8i32.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8f64_v8i32 = call <8 x i32> @llvm.vp.fptosi.v8i32.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8f32_v8i64 = call <8 x i64> @llvm.vp.fptosi.v8i64.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8f64_v8i64 = call <8 x i64> @llvm.vp.fptosi.v8i64.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v8f32_v8i1 = call <8 x i1> @llvm.vp.fptosi.v8i1.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v8f64_v8i1 = call <8 x i1> @llvm.vp.fptosi.v8i1.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16f32_v16i8 = fptosi <16 x float> undef to <16 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v16f64_v16i8 = fptosi <16 x double> undef to <16 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_v16i16 = fptosi <16 x float> undef to <16 x i16>
@@ -2673,16 +2000,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16f64_v16i64 = fptosi <16 x double> undef to <16 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v16f32_v16i1 = fptosi <16 x float> undef to <16 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v16f64_v16i1 = fptosi <16 x double> undef to <16 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v16f32_v16i8 = call <16 x i8> @llvm.vp.fptosi.v16i8.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v16f64_v16i8 = call <16 x i8> @llvm.vp.fptosi.v16i8.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16f32_v16i16 = call <16 x i16> @llvm.vp.fptosi.v16i16.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v16f64_v16i16 = call <16 x i16> @llvm.vp.fptosi.v16i16.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16f32_v16i32 = call <16 x i32> @llvm.vp.fptosi.v16i32.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16f64_v16i32 = call <16 x i32> @llvm.vp.fptosi.v16i32.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16f32_v16i64 = call <16 x i64> @llvm.vp.fptosi.v16i64.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16f64_v16i64 = call <16 x i64> @llvm.vp.fptosi.v16i64.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v16f32_v16i1 = call <16 x i1> @llvm.vp.fptosi.v16i1.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v16f64_v16i1 = call <16 x i1> @llvm.vp.fptosi.v16i1.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v32f32_v32i8 = fptosi <32 x float> undef to <32 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v32f64_v32i8 = fptosi <32 x double> undef to <32 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32f32_v32i16 = fptosi <32 x float> undef to <32 x i16>
@@ -2693,16 +2010,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32f64_v32i64 = fptosi <32 x double> undef to <32 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v32f32_v32i1 = fptosi <32 x float> undef to <32 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v32f64_v32i1 = fptosi <32 x double> undef to <32 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v32f32_v32i8 = call <32 x i8> @llvm.vp.fptosi.v32i8.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v32f64_v32i8 = call <32 x i8> @llvm.vp.fptosi.v32i8.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32f32_v32i16 = call <32 x i16> @llvm.vp.fptosi.v32i16.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_v32f64_v32i16 = call <32 x i16> @llvm.vp.fptosi.v32i16.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32f32_v32i32 = call <32 x i32> @llvm.vp.fptosi.v32i32.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v32f64_v32i32 = call <32 x i32> @llvm.vp.fptosi.v32i32.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32f32_v32i64 = call <32 x i64> @llvm.vp.fptosi.v32i64.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v32f64_v32i64 = call <32 x i64> @llvm.vp.fptosi.v32i64.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v32f32_v32i1 = call <32 x i1> @llvm.vp.fptosi.v32i1.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32f64_v32i1 = call <32 x i1> @llvm.vp.fptosi.v32i1.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %v64f32_v64i8 = fptosi <64 x float> undef to <64 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v64f64_v64i8 = fptosi <64 x double> undef to <64 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v64f32_v64i16 = fptosi <64 x float> undef to <64 x i16>
@@ -2713,16 +2020,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64f64_v64i64 = fptosi <64 x double> undef to <64 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v64f32_v64i1 = fptosi <64 x float> undef to <64 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v64f64_v64i1 = fptosi <64 x double> undef to <64 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_v64f32_v64i8 = call <64 x i8> @llvm.vp.fptosi.v64i8.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v64f64_v64i8 = call <64 x i8> @llvm.vp.fptosi.v64i8.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v64f32_v64i16 = call <64 x i16> @llvm.vp.fptosi.v64i16.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_v64f64_v64i16 = call <64 x i16> @llvm.vp.fptosi.v64i16.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v64f32_v64i32 = call <64 x i32> @llvm.vp.fptosi.v64i32.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v64f64_v64i32 = call <64 x i32> @llvm.vp.fptosi.v64i32.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v64f32_v64i64 = call <64 x i64> @llvm.vp.fptosi.v64i64.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v64f64_v64i64 = call <64 x i64> @llvm.vp.fptosi.v64i64.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v64f32_v64i1 = call <64 x i1> @llvm.vp.fptosi.v64i1.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v64f64_v64i1 = call <64 x i1> @llvm.vp.fptosi.v64i1.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %v128f32_v128i8 = fptosi <128 x float> undef to <128 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v128f64_v128i8 = fptosi <128 x double> undef to <128 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %v128f32_v128i16 = fptosi <128 x float> undef to <128 x i16>
@@ -2733,16 +2030,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v128f64_v128i64 = fptosi <128 x double> undef to <128 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v128f32_v128i1 = fptosi <128 x float> undef to <128 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %v128f64_v128i1 = fptosi <128 x double> undef to <128 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_v128f32_v128i8 = call <128 x i8> @llvm.vp.fptosi.v128i8.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v128f64_v128i8 = call <128 x i8> @llvm.vp.fptosi.v128i8.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v128f32_v128i16 = call <128 x i16> @llvm.vp.fptosi.v128i16.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_v128f64_v128i16 = call <128 x i16> @llvm.vp.fptosi.v128i16.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v128f32_v128i32 = call <128 x i32> @llvm.vp.fptosi.v128i32.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_v128f64_v128i32 = call <128 x i32> @llvm.vp.fptosi.v128i32.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v128f32_v128i64 = call <128 x i64> @llvm.vp.fptosi.v128i64.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v128f64_v128i64 = call <128 x i64> @llvm.vp.fptosi.v128i64.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v128f32_v128i1 = call <128 x i1> @llvm.vp.fptosi.v128i1.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %vp_v128f64_v128i1 = call <128 x i1> @llvm.vp.fptosi.v128i1.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1f32_nxv1i8 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1f64_nxv1i8 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32_nxv1i16 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i16>
@@ -2753,16 +2040,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64_nxv1i64 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1f32_nxv1i1 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1f64_nxv1i1 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1f32_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.fptosi.nxv1i8.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1f64_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.fptosi.nxv1i8.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f32_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.fptosi.nxv1i16.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1f64_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.fptosi.nxv1i16.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f32_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.fptosi.nxv1i32.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f64_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.fptosi.nxv1i32.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f32_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.fptosi.nxv1i64.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f64_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.fptosi.nxv1i64.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1f32_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.fptosi.nxv1i1.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1f64_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.fptosi.nxv1i1.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f32_nxv2i8 = fptosi <vscale x 2 x float> undef to <vscale x 2 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2f64_nxv2i8 = fptosi <vscale x 2 x double> undef to <vscale x 2 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32_nxv2i16 = fptosi <vscale x 2 x float> undef to <vscale x 2 x i16>
@@ -2773,16 +2050,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64_nxv2i64 = fptosi <vscale x 2 x double> undef to <vscale x 2 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2f32_nxv2i1 = fptosi <vscale x 2 x float> undef to <vscale x 2 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2f64_nxv2i1 = fptosi <vscale x 2 x double> undef to <vscale x 2 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f32_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.fptosi.nxv2i8.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2f64_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.fptosi.nxv2i8.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f32_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.fptosi.nxv2i16.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f64_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.fptosi.nxv2i16.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f32_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.fptosi.nxv2i32.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f64_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.fptosi.nxv2i32.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f32_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.fptosi.nxv2i64.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f64_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.fptosi.nxv2i64.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2f32_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.fptosi.nxv2i1.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2f64_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.fptosi.nxv2i1.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32_nxv4i8 = fptosi <vscale x 4 x float> undef to <vscale x 4 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64_nxv4i8 = fptosi <vscale x 4 x double> undef to <vscale x 4 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32_nxv4i16 = fptosi <vscale x 4 x float> undef to <vscale x 4 x i16>
@@ -2793,16 +2060,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64_nxv4i64 = fptosi <vscale x 4 x double> undef to <vscale x 4 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv4f32_nxv4i1 = fptosi <vscale x 4 x float> undef to <vscale x 4 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv4f64_nxv4i1 = fptosi <vscale x 4 x double> undef to <vscale x 4 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4f32_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.fptosi.nxv4i8.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4f64_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.fptosi.nxv4i8.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv4f32_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.fptosi.nxv4i16.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv4f64_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.fptosi.nxv4i16.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4f32_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.fptosi.nxv4i32.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4f64_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.fptosi.nxv4i32.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4f32_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.fptosi.nxv4i64.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4f64_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.fptosi.nxv4i64.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv4f32_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.fptosi.nxv4i1.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv4f64_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.fptosi.nxv4i1.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv8f32_nxv8i8 = fptosi <vscale x 8 x float> undef to <vscale x 8 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %nxv8f64_nxv8i8 = fptosi <vscale x 8 x double> undef to <vscale x 8 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f32_nxv8i16 = fptosi <vscale x 8 x float> undef to <vscale x 8 x i16>
@@ -2813,16 +2070,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f64_nxv8i64 = fptosi <vscale x 8 x double> undef to <vscale x 8 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv8f32_nxv8i1 = fptosi <vscale x 8 x float> undef to <vscale x 8 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv8f64_nxv8i1 = fptosi <vscale x 8 x double> undef to <vscale x 8 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv8f32_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.fptosi.nxv8i8.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_nxv8f64_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.fptosi.nxv8i8.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8f32_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.fptosi.nxv8i16.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv8f64_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.fptosi.nxv8i16.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8f32_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.fptosi.nxv8i32.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8f64_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.fptosi.nxv8i32.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8f32_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.fptosi.nxv8i64.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8f64_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.fptosi.nxv8i64.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv8f32_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.fptosi.nxv8i1.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv8f64_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.fptosi.nxv8i1.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv16f32_nxv16i8 = fptosi <vscale x 16 x float> undef to <vscale x 16 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %nxv16f64_nxv16i8 = fptosi <vscale x 16 x double> undef to <vscale x 16 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f32_nxv16i16 = fptosi <vscale x 16 x float> undef to <vscale x 16 x i16>
@@ -2833,16 +2080,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16f64_nxv16i64 = fptosi <vscale x 16 x double> undef to <vscale x 16 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv16f32_nxv16i1 = fptosi <vscale x 16 x float> undef to <vscale x 16 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv16f64_nxv16i1 = fptosi <vscale x 16 x double> undef to <vscale x 16 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv16f32_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.fptosi.nxv16i8.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_nxv16f64_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.fptosi.nxv16i8.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16f32_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.fptosi.nxv16i16.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_nxv16f64_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.fptosi.nxv16i16.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16f32_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.fptosi.nxv16i32.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv16f64_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.fptosi.nxv16i32.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16f32_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.fptosi.nxv16i64.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv16f64_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.fptosi.nxv16i64.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv16f32_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.fptosi.nxv16i1.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16f64_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.fptosi.nxv16i1.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %nxv32f32_nxv32i8 = fptosi <vscale x 32 x float> undef to <vscale x 32 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %nxv32f64_nxv32i8 = fptosi <vscale x 32 x double> undef to <vscale x 32 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %nxv32f32_nxv32i16 = fptosi <vscale x 32 x float> undef to <vscale x 32 x i16>
@@ -2853,16 +2090,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32f64_nxv32i64 = fptosi <vscale x 32 x double> undef to <vscale x 32 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv32f32_nxv32i1 = fptosi <vscale x 32 x float> undef to <vscale x 32 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv32f64_nxv32i1 = fptosi <vscale x 32 x double> undef to <vscale x 32 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_nxv32f32_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.fptosi.nxv32i8.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_nxv32f64_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.fptosi.nxv32i8.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv32f32_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.fptosi.nxv32i16.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_nxv32f64_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.fptosi.nxv32i16.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv32f32_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.fptosi.nxv32i32.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv32f64_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.fptosi.nxv32i32.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv32f32_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.fptosi.nxv32i64.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv32f64_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.fptosi.nxv32i64.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv32f32_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.fptosi.nxv32i1.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv32f64_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.fptosi.nxv32i1.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %nxv64f32_nxv64i8 = fptosi <vscale x 64 x float> undef to <vscale x 64 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %nxv64f64_nxv64i8 = fptosi <vscale x 64 x double> undef to <vscale x 64 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %nxv64f32_nxv64i16 = fptosi <vscale x 64 x float> undef to <vscale x 64 x i16>
@@ -2873,16 +2100,6 @@ define void @fptosi() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv64f64_nxv64i64 = fptosi <vscale x 64 x double> undef to <vscale x 64 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv64f32_nxv64i1 = fptosi <vscale x 64 x float> undef to <vscale x 64 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %nxv64f64_nxv64i1 = fptosi <vscale x 64 x double> undef to <vscale x 64 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_nxv64f32_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.fptosi.nxv64i8.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_nxv64f64_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.fptosi.nxv64i8.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv64f32_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.fptosi.nxv64i16.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_nxv64f64_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.fptosi.nxv64i16.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv64f32_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.fptosi.nxv64i32.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_nxv64f64_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.fptosi.nxv64i32.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv64f32_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.fptosi.nxv64i64.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv64f64_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.fptosi.nxv64i64.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv64f32_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.fptosi.nxv64i1.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %vp_nxv64f64_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.fptosi.nxv64i1.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVE64X-LABEL: 'fptosi'
@@ -2896,16 +2113,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f64_v2i64 = fptosi <2 x double> undef to <2 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %v2f32_v2i1 = fptosi <2 x float> undef to <2 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %v2f64_v2i1 = fptosi <2 x double> undef to <2 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f32_v2i8 = call <2 x i8> @llvm.vp.fptosi.v2i8.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f64_v2i8 = call <2 x i8> @llvm.vp.fptosi.v2i8.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f32_v2i16 = call <2 x i16> @llvm.vp.fptosi.v2i16.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f64_v2i16 = call <2 x i16> @llvm.vp.fptosi.v2i16.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f32_v2i32 = call <2 x i32> @llvm.vp.fptosi.v2i32.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f64_v2i32 = call <2 x i32> @llvm.vp.fptosi.v2i32.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f32_v2i64 = call <2 x i64> @llvm.vp.fptosi.v2i64.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f64_v2i64 = call <2 x i64> @llvm.vp.fptosi.v2i64.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %vp_v2f32_v2i1 = call <2 x i1> @llvm.vp.fptosi.v2i1.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %vp_v2f64_v2i1 = call <2 x i1> @llvm.vp.fptosi.v2i1.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v4f32_v4i8 = fptosi <4 x float> undef to <4 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v4f64_v4i8 = fptosi <4 x double> undef to <4 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v4f32_v4i16 = fptosi <4 x float> undef to <4 x i16>
@@ -2916,16 +2123,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4f64_v4i64 = fptosi <4 x double> undef to <4 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %v4f32_v4i1 = fptosi <4 x float> undef to <4 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %v4f64_v4i1 = fptosi <4 x double> undef to <4 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f32_v4i8 = call <4 x i8> @llvm.vp.fptosi.v4i8.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f64_v4i8 = call <4 x i8> @llvm.vp.fptosi.v4i8.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f32_v4i16 = call <4 x i16> @llvm.vp.fptosi.v4i16.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f64_v4i16 = call <4 x i16> @llvm.vp.fptosi.v4i16.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f32_v4i32 = call <4 x i32> @llvm.vp.fptosi.v4i32.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f64_v4i32 = call <4 x i32> @llvm.vp.fptosi.v4i32.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4f32_v4i64 = call <4 x i64> @llvm.vp.fptosi.v4i64.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4f64_v4i64 = call <4 x i64> @llvm.vp.fptosi.v4i64.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %vp_v4f32_v4i1 = call <4 x i1> @llvm.vp.fptosi.v4i1.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %vp_v4f64_v4i1 = call <4 x i1> @llvm.vp.fptosi.v4i1.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v8f32_v8i8 = fptosi <8 x float> undef to <8 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v8f64_v8i8 = fptosi <8 x double> undef to <8 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v8f32_v8i16 = fptosi <8 x float> undef to <8 x i16>
@@ -2936,16 +2133,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8f64_v8i64 = fptosi <8 x double> undef to <8 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %v8f32_v8i1 = fptosi <8 x float> undef to <8 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %v8f64_v8i1 = fptosi <8 x double> undef to <8 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f32_v8i8 = call <8 x i8> @llvm.vp.fptosi.v8i8.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f64_v8i8 = call <8 x i8> @llvm.vp.fptosi.v8i8.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f32_v8i16 = call <8 x i16> @llvm.vp.fptosi.v8i16.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f64_v8i16 = call <8 x i16> @llvm.vp.fptosi.v8i16.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f32_v8i32 = call <8 x i32> @llvm.vp.fptosi.v8i32.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f64_v8i32 = call <8 x i32> @llvm.vp.fptosi.v8i32.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8f32_v8i64 = call <8 x i64> @llvm.vp.fptosi.v8i64.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8f64_v8i64 = call <8 x i64> @llvm.vp.fptosi.v8i64.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_v8f32_v8i1 = call <8 x i1> @llvm.vp.fptosi.v8i1.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_v8f64_v8i1 = call <8 x i1> @llvm.vp.fptosi.v8i1.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v16f32_v16i8 = fptosi <16 x float> undef to <16 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v16f64_v16i8 = fptosi <16 x double> undef to <16 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v16f32_v16i16 = fptosi <16 x float> undef to <16 x i16>
@@ -2956,16 +2143,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16f64_v16i64 = fptosi <16 x double> undef to <16 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 159 for instruction: %v16f32_v16i1 = fptosi <16 x float> undef to <16 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 159 for instruction: %v16f64_v16i1 = fptosi <16 x double> undef to <16 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f32_v16i8 = call <16 x i8> @llvm.vp.fptosi.v16i8.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f64_v16i8 = call <16 x i8> @llvm.vp.fptosi.v16i8.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f32_v16i16 = call <16 x i16> @llvm.vp.fptosi.v16i16.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f64_v16i16 = call <16 x i16> @llvm.vp.fptosi.v16i16.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f32_v16i32 = call <16 x i32> @llvm.vp.fptosi.v16i32.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f64_v16i32 = call <16 x i32> @llvm.vp.fptosi.v16i32.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16f32_v16i64 = call <16 x i64> @llvm.vp.fptosi.v16i64.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16f64_v16i64 = call <16 x i64> @llvm.vp.fptosi.v16i64.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 159 for instruction: %vp_v16f32_v16i1 = call <16 x i1> @llvm.vp.fptosi.v16i1.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 159 for instruction: %vp_v16f64_v16i1 = call <16 x i1> @llvm.vp.fptosi.v16i1.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v32f32_v32i8 = fptosi <32 x float> undef to <32 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v32f64_v32i8 = fptosi <32 x double> undef to <32 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v32f32_v32i16 = fptosi <32 x float> undef to <32 x i16>
@@ -2976,16 +2153,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %v32f64_v32i64 = fptosi <32 x double> undef to <32 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 319 for instruction: %v32f32_v32i1 = fptosi <32 x float> undef to <32 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 319 for instruction: %v32f64_v32i1 = fptosi <32 x double> undef to <32 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f32_v32i8 = call <32 x i8> @llvm.vp.fptosi.v32i8.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f64_v32i8 = call <32 x i8> @llvm.vp.fptosi.v32i8.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f32_v32i16 = call <32 x i16> @llvm.vp.fptosi.v32i16.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f64_v32i16 = call <32 x i16> @llvm.vp.fptosi.v32i16.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f32_v32i32 = call <32 x i32> @llvm.vp.fptosi.v32i32.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f64_v32i32 = call <32 x i32> @llvm.vp.fptosi.v32i32.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %vp_v32f32_v32i64 = call <32 x i64> @llvm.vp.fptosi.v32i64.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %vp_v32f64_v32i64 = call <32 x i64> @llvm.vp.fptosi.v32i64.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 319 for instruction: %vp_v32f32_v32i1 = call <32 x i1> @llvm.vp.fptosi.v32i1.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 319 for instruction: %vp_v32f64_v32i1 = call <32 x i1> @llvm.vp.fptosi.v32i1.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v64f32_v64i8 = fptosi <64 x float> undef to <64 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v64f64_v64i8 = fptosi <64 x double> undef to <64 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v64f32_v64i16 = fptosi <64 x float> undef to <64 x i16>
@@ -2996,16 +2163,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %v64f64_v64i64 = fptosi <64 x double> undef to <64 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 639 for instruction: %v64f32_v64i1 = fptosi <64 x float> undef to <64 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 639 for instruction: %v64f64_v64i1 = fptosi <64 x double> undef to <64 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v64f32_v64i8 = call <64 x i8> @llvm.vp.fptosi.v64i8.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v64f64_v64i8 = call <64 x i8> @llvm.vp.fptosi.v64i8.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v64f32_v64i16 = call <64 x i16> @llvm.vp.fptosi.v64i16.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v64f64_v64i16 = call <64 x i16> @llvm.vp.fptosi.v64i16.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %vp_v64f32_v64i32 = call <64 x i32> @llvm.vp.fptosi.v64i32.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %vp_v64f64_v64i32 = call <64 x i32> @llvm.vp.fptosi.v64i32.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %vp_v64f32_v64i64 = call <64 x i64> @llvm.vp.fptosi.v64i64.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %vp_v64f64_v64i64 = call <64 x i64> @llvm.vp.fptosi.v64i64.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 639 for instruction: %vp_v64f32_v64i1 = call <64 x i1> @llvm.vp.fptosi.v64i1.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 639 for instruction: %vp_v64f64_v64i1 = call <64 x i1> @llvm.vp.fptosi.v64i1.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 511 for instruction: %v128f32_v128i8 = fptosi <128 x float> undef to <128 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 511 for instruction: %v128f64_v128i8 = fptosi <128 x double> undef to <128 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 510 for instruction: %v128f32_v128i16 = fptosi <128 x float> undef to <128 x i16>
@@ -3016,16 +2173,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %v128f64_v128i64 = fptosi <128 x double> undef to <128 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 1279 for instruction: %v128f32_v128i1 = fptosi <128 x float> undef to <128 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 1279 for instruction: %v128f64_v128i1 = fptosi <128 x double> undef to <128 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 511 for instruction: %vp_v128f32_v128i8 = call <128 x i8> @llvm.vp.fptosi.v128i8.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 511 for instruction: %vp_v128f64_v128i8 = call <128 x i8> @llvm.vp.fptosi.v128i8.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 510 for instruction: %vp_v128f32_v128i16 = call <128 x i16> @llvm.vp.fptosi.v128i16.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 510 for instruction: %vp_v128f64_v128i16 = call <128 x i16> @llvm.vp.fptosi.v128i16.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 508 for instruction: %vp_v128f32_v128i32 = call <128 x i32> @llvm.vp.fptosi.v128i32.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 508 for instruction: %vp_v128f64_v128i32 = call <128 x i32> @llvm.vp.fptosi.v128i32.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %vp_v128f32_v128i64 = call <128 x i64> @llvm.vp.fptosi.v128i64.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %vp_v128f64_v128i64 = call <128 x i64> @llvm.vp.fptosi.v128i64.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 1279 for instruction: %vp_v128f32_v128i1 = call <128 x i1> @llvm.vp.fptosi.v128i1.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 1279 for instruction: %vp_v128f64_v128i1 = call <128 x i1> @llvm.vp.fptosi.v128i1.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f32_nxv1i8 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i8 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f32_nxv1i16 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i16>
@@ -3036,16 +2183,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i64 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f32_nxv1i1 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i1 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.fptosi.nxv1i8.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.fptosi.nxv1i8.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.fptosi.nxv1i16.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.fptosi.nxv1i16.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.fptosi.nxv1i32.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.fptosi.nxv1i32.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.fptosi.nxv1i64.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.fptosi.nxv1i64.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.fptosi.nxv1i1.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.fptosi.nxv1i1.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f32_nxv2i8 = fptosi <vscale x 2 x float> undef to <vscale x 2 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i8 = fptosi <vscale x 2 x double> undef to <vscale x 2 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f32_nxv2i16 = fptosi <vscale x 2 x float> undef to <vscale x 2 x i16>
@@ -3056,16 +2193,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i64 = fptosi <vscale x 2 x double> undef to <vscale x 2 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f32_nxv2i1 = fptosi <vscale x 2 x float> undef to <vscale x 2 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i1 = fptosi <vscale x 2 x double> undef to <vscale x 2 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.fptosi.nxv2i8.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.fptosi.nxv2i8.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.fptosi.nxv2i16.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.fptosi.nxv2i16.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.fptosi.nxv2i32.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.fptosi.nxv2i32.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.fptosi.nxv2i64.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.fptosi.nxv2i64.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.fptosi.nxv2i1.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.fptosi.nxv2i1.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f32_nxv4i8 = fptosi <vscale x 4 x float> undef to <vscale x 4 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i8 = fptosi <vscale x 4 x double> undef to <vscale x 4 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f32_nxv4i16 = fptosi <vscale x 4 x float> undef to <vscale x 4 x i16>
@@ -3076,16 +2203,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i64 = fptosi <vscale x 4 x double> undef to <vscale x 4 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f32_nxv4i1 = fptosi <vscale x 4 x float> undef to <vscale x 4 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i1 = fptosi <vscale x 4 x double> undef to <vscale x 4 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.fptosi.nxv4i8.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.fptosi.nxv4i8.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.fptosi.nxv4i16.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.fptosi.nxv4i16.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.fptosi.nxv4i32.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.fptosi.nxv4i32.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.fptosi.nxv4i64.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.fptosi.nxv4i64.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.fptosi.nxv4i1.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.fptosi.nxv4i1.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f32_nxv8i8 = fptosi <vscale x 8 x float> undef to <vscale x 8 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i8 = fptosi <vscale x 8 x double> undef to <vscale x 8 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f32_nxv8i16 = fptosi <vscale x 8 x float> undef to <vscale x 8 x i16>
@@ -3096,16 +2213,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i64 = fptosi <vscale x 8 x double> undef to <vscale x 8 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f32_nxv8i1 = fptosi <vscale x 8 x float> undef to <vscale x 8 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i1 = fptosi <vscale x 8 x double> undef to <vscale x 8 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.fptosi.nxv8i8.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.fptosi.nxv8i8.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.fptosi.nxv8i16.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.fptosi.nxv8i16.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.fptosi.nxv8i32.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.fptosi.nxv8i32.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.fptosi.nxv8i64.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.fptosi.nxv8i64.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.fptosi.nxv8i1.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.fptosi.nxv8i1.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f32_nxv16i8 = fptosi <vscale x 16 x float> undef to <vscale x 16 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i8 = fptosi <vscale x 16 x double> undef to <vscale x 16 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f32_nxv16i16 = fptosi <vscale x 16 x float> undef to <vscale x 16 x i16>
@@ -3116,16 +2223,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i64 = fptosi <vscale x 16 x double> undef to <vscale x 16 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f32_nxv16i1 = fptosi <vscale x 16 x float> undef to <vscale x 16 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i1 = fptosi <vscale x 16 x double> undef to <vscale x 16 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.fptosi.nxv16i8.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.fptosi.nxv16i8.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.fptosi.nxv16i16.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.fptosi.nxv16i16.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.fptosi.nxv16i32.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.fptosi.nxv16i32.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.fptosi.nxv16i64.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.fptosi.nxv16i64.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.fptosi.nxv16i1.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.fptosi.nxv16i1.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f32_nxv32i8 = fptosi <vscale x 32 x float> undef to <vscale x 32 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f64_nxv32i8 = fptosi <vscale x 32 x double> undef to <vscale x 32 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f32_nxv32i16 = fptosi <vscale x 32 x float> undef to <vscale x 32 x i16>
@@ -3136,16 +2233,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f64_nxv32i64 = fptosi <vscale x 32 x double> undef to <vscale x 32 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f32_nxv32i1 = fptosi <vscale x 32 x float> undef to <vscale x 32 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f64_nxv32i1 = fptosi <vscale x 32 x double> undef to <vscale x 32 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.fptosi.nxv32i8.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.fptosi.nxv32i8.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.fptosi.nxv32i16.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.fptosi.nxv32i16.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.fptosi.nxv32i32.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.fptosi.nxv32i32.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.fptosi.nxv32i64.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.fptosi.nxv32i64.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.fptosi.nxv32i1.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.fptosi.nxv32i1.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f32_nxv64i8 = fptosi <vscale x 64 x float> undef to <vscale x 64 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f64_nxv64i8 = fptosi <vscale x 64 x double> undef to <vscale x 64 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f32_nxv64i16 = fptosi <vscale x 64 x float> undef to <vscale x 64 x i16>
@@ -3156,16 +2243,6 @@ define void @fptosi() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f64_nxv64i64 = fptosi <vscale x 64 x double> undef to <vscale x 64 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f32_nxv64i1 = fptosi <vscale x 64 x float> undef to <vscale x 64 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f64_nxv64i1 = fptosi <vscale x 64 x double> undef to <vscale x 64 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.fptosi.nxv64i8.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.fptosi.nxv64i8.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.fptosi.nxv64i16.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.fptosi.nxv64i16.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.fptosi.nxv64i32.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.fptosi.nxv64i32.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.fptosi.nxv64i64.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.fptosi.nxv64i64.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.fptosi.nxv64i1.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.fptosi.nxv64i1.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f32_v2i8 = fptosi <2 x float> undef to <2 x i8>
@@ -3491,16 +2568,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_v2i64 = fptoui <2 x double> undef to <2 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f32_v2i1 = fptoui <2 x float> undef to <2 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f64_v2i1 = fptoui <2 x double> undef to <2 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f32_v2i8 = call <2 x i8> @llvm.vp.fptoui.v2i8.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f64_v2i8 = call <2 x i8> @llvm.vp.fptoui.v2i8.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f32_v2i16 = call <2 x i16> @llvm.vp.fptoui.v2i16.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2f64_v2i16 = call <2 x i16> @llvm.vp.fptoui.v2i16.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f32_v2i32 = call <2 x i32> @llvm.vp.fptoui.v2i32.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f64_v2i32 = call <2 x i32> @llvm.vp.fptoui.v2i32.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f32_v2i64 = call <2 x i64> @llvm.vp.fptoui.v2i64.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2f64_v2i64 = call <2 x i64> @llvm.vp.fptoui.v2i64.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f32_v2i1 = call <2 x i1> @llvm.vp.fptoui.v2i1.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f64_v2i1 = call <2 x i1> @llvm.vp.fptoui.v2i1.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4i8 = fptoui <4 x float> undef to <4 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f64_v4i8 = fptoui <4 x double> undef to <4 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_v4i16 = fptoui <4 x float> undef to <4 x i16>
@@ -3511,16 +2578,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64_v4i64 = fptoui <4 x double> undef to <4 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f32_v4i1 = fptoui <4 x float> undef to <4 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f64_v4i1 = fptoui <4 x double> undef to <4 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f32_v4i8 = call <4 x i8> @llvm.vp.fptoui.v4i8.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4f64_v4i8 = call <4 x i8> @llvm.vp.fptoui.v4i8.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f32_v4i16 = call <4 x i16> @llvm.vp.fptoui.v4i16.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f64_v4i16 = call <4 x i16> @llvm.vp.fptoui.v4i16.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f32_v4i32 = call <4 x i32> @llvm.vp.fptoui.v4i32.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4f64_v4i32 = call <4 x i32> @llvm.vp.fptoui.v4i32.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f32_v4i64 = call <4 x i64> @llvm.vp.fptoui.v4i64.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4f64_v4i64 = call <4 x i64> @llvm.vp.fptoui.v4i64.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4f32_v4i1 = call <4 x i1> @llvm.vp.fptoui.v4i1.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4f64_v4i1 = call <4 x i1> @llvm.vp.fptoui.v4i1.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_v8i8 = fptoui <8 x float> undef to <8 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64_v8i8 = fptoui <8 x double> undef to <8 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_v8i16 = fptoui <8 x float> undef to <8 x i16>
@@ -3531,16 +2588,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64_v8i64 = fptoui <8 x double> undef to <8 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f32_v8i1 = fptoui <8 x float> undef to <8 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v8f64_v8i1 = fptoui <8 x double> undef to <8 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8f32_v8i8 = call <8 x i8> @llvm.vp.fptoui.v8i8.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8f64_v8i8 = call <8 x i8> @llvm.vp.fptoui.v8i8.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v8f32_v8i16 = call <8 x i16> @llvm.vp.fptoui.v8i16.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v8f64_v8i16 = call <8 x i16> @llvm.vp.fptoui.v8i16.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8f32_v8i32 = call <8 x i32> @llvm.vp.fptoui.v8i32.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8f64_v8i32 = call <8 x i32> @llvm.vp.fptoui.v8i32.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8f32_v8i64 = call <8 x i64> @llvm.vp.fptoui.v8i64.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8f64_v8i64 = call <8 x i64> @llvm.vp.fptoui.v8i64.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v8f32_v8i1 = call <8 x i1> @llvm.vp.fptoui.v8i1.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v8f64_v8i1 = call <8 x i1> @llvm.vp.fptoui.v8i1.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16f32_v16i8 = fptoui <16 x float> undef to <16 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v16f64_v16i8 = fptoui <16 x double> undef to <16 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_v16i16 = fptoui <16 x float> undef to <16 x i16>
@@ -3551,16 +2598,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16f64_v16i64 = fptoui <16 x double> undef to <16 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v16f32_v16i1 = fptoui <16 x float> undef to <16 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v16f64_v16i1 = fptoui <16 x double> undef to <16 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v16f32_v16i8 = call <16 x i8> @llvm.vp.fptoui.v16i8.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v16f64_v16i8 = call <16 x i8> @llvm.vp.fptoui.v16i8.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v16f32_v16i16 = call <16 x i16> @llvm.vp.fptoui.v16i16.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v16f64_v16i16 = call <16 x i16> @llvm.vp.fptoui.v16i16.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16f32_v16i32 = call <16 x i32> @llvm.vp.fptoui.v16i32.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16f64_v16i32 = call <16 x i32> @llvm.vp.fptoui.v16i32.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16f32_v16i64 = call <16 x i64> @llvm.vp.fptoui.v16i64.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16f64_v16i64 = call <16 x i64> @llvm.vp.fptoui.v16i64.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v16f32_v16i1 = call <16 x i1> @llvm.vp.fptoui.v16i1.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v16f64_v16i1 = call <16 x i1> @llvm.vp.fptoui.v16i1.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v32f32_v32i8 = fptoui <32 x float> undef to <32 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v32f64_v32i8 = fptoui <32 x double> undef to <32 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32f32_v32i16 = fptoui <32 x float> undef to <32 x i16>
@@ -3571,16 +2608,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32f64_v32i64 = fptoui <32 x double> undef to <32 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v32f32_v32i1 = fptoui <32 x float> undef to <32 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v32f64_v32i1 = fptoui <32 x double> undef to <32 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v32f32_v32i8 = call <32 x i8> @llvm.vp.fptoui.v32i8.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v32f64_v32i8 = call <32 x i8> @llvm.vp.fptoui.v32i8.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v32f32_v32i16 = call <32 x i16> @llvm.vp.fptoui.v32i16.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_v32f64_v32i16 = call <32 x i16> @llvm.vp.fptoui.v32i16.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32f32_v32i32 = call <32 x i32> @llvm.vp.fptoui.v32i32.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v32f64_v32i32 = call <32 x i32> @llvm.vp.fptoui.v32i32.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32f32_v32i64 = call <32 x i64> @llvm.vp.fptoui.v32i64.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v32f64_v32i64 = call <32 x i64> @llvm.vp.fptoui.v32i64.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v32f32_v32i1 = call <32 x i1> @llvm.vp.fptoui.v32i1.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32f64_v32i1 = call <32 x i1> @llvm.vp.fptoui.v32i1.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %v64f32_v64i8 = fptoui <64 x float> undef to <64 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v64f64_v64i8 = fptoui <64 x double> undef to <64 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %v64f32_v64i16 = fptoui <64 x float> undef to <64 x i16>
@@ -3591,16 +2618,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64f64_v64i64 = fptoui <64 x double> undef to <64 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v64f32_v64i1 = fptoui <64 x float> undef to <64 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v64f64_v64i1 = fptoui <64 x double> undef to <64 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_v64f32_v64i8 = call <64 x i8> @llvm.vp.fptoui.v64i8.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v64f64_v64i8 = call <64 x i8> @llvm.vp.fptoui.v64i8.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v64f32_v64i16 = call <64 x i16> @llvm.vp.fptoui.v64i16.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_v64f64_v64i16 = call <64 x i16> @llvm.vp.fptoui.v64i16.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v64f32_v64i32 = call <64 x i32> @llvm.vp.fptoui.v64i32.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v64f64_v64i32 = call <64 x i32> @llvm.vp.fptoui.v64i32.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v64f32_v64i64 = call <64 x i64> @llvm.vp.fptoui.v64i64.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v64f64_v64i64 = call <64 x i64> @llvm.vp.fptoui.v64i64.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v64f32_v64i1 = call <64 x i1> @llvm.vp.fptoui.v64i1.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v64f64_v64i1 = call <64 x i1> @llvm.vp.fptoui.v64i1.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %v128f32_v128i8 = fptoui <128 x float> undef to <128 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v128f64_v128i8 = fptoui <128 x double> undef to <128 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %v128f32_v128i16 = fptoui <128 x float> undef to <128 x i16>
@@ -3611,16 +2628,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v128f64_v128i64 = fptoui <128 x double> undef to <128 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v128f32_v128i1 = fptoui <128 x float> undef to <128 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %v128f64_v128i1 = fptoui <128 x double> undef to <128 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_v128f32_v128i8 = call <128 x i8> @llvm.vp.fptoui.v128i8.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v128f64_v128i8 = call <128 x i8> @llvm.vp.fptoui.v128i8.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v128f32_v128i16 = call <128 x i16> @llvm.vp.fptoui.v128i16.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_v128f64_v128i16 = call <128 x i16> @llvm.vp.fptoui.v128i16.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v128f32_v128i32 = call <128 x i32> @llvm.vp.fptoui.v128i32.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_v128f64_v128i32 = call <128 x i32> @llvm.vp.fptoui.v128i32.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v128f32_v128i64 = call <128 x i64> @llvm.vp.fptoui.v128i64.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v128f64_v128i64 = call <128 x i64> @llvm.vp.fptoui.v128i64.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v128f32_v128i1 = call <128 x i1> @llvm.vp.fptoui.v128i1.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %vp_v128f64_v128i1 = call <128 x i1> @llvm.vp.fptoui.v128i1.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1f32_nxv1i8 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1f64_nxv1i8 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32_nxv1i16 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i16>
@@ -3631,16 +2638,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64_nxv1i64 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1f32_nxv1i1 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1f64_nxv1i1 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1f32_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.fptoui.nxv1i8.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1f64_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.fptoui.nxv1i8.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f32_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.fptoui.nxv1i16.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1f64_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.fptoui.nxv1i16.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f32_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.fptoui.nxv1i32.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f64_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.fptoui.nxv1i32.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f32_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.fptoui.nxv1i64.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1f64_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.fptoui.nxv1i64.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1f32_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.fptoui.nxv1i1.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1f64_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.fptoui.nxv1i1.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f32_nxv2i8 = fptoui <vscale x 2 x float> undef to <vscale x 2 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2f64_nxv2i8 = fptoui <vscale x 2 x double> undef to <vscale x 2 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32_nxv2i16 = fptoui <vscale x 2 x float> undef to <vscale x 2 x i16>
@@ -3651,16 +2648,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64_nxv2i64 = fptoui <vscale x 2 x double> undef to <vscale x 2 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2f32_nxv2i1 = fptoui <vscale x 2 x float> undef to <vscale x 2 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2f64_nxv2i1 = fptoui <vscale x 2 x double> undef to <vscale x 2 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f32_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.fptoui.nxv2i8.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2f64_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.fptoui.nxv2i8.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f32_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.fptoui.nxv2i16.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f64_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.fptoui.nxv2i16.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f32_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.fptoui.nxv2i32.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2f64_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.fptoui.nxv2i32.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f32_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.fptoui.nxv2i64.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2f64_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.fptoui.nxv2i64.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2f32_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.fptoui.nxv2i1.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2f64_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.fptoui.nxv2i1.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32_nxv4i8 = fptoui <vscale x 4 x float> undef to <vscale x 4 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64_nxv4i8 = fptoui <vscale x 4 x double> undef to <vscale x 4 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32_nxv4i16 = fptoui <vscale x 4 x float> undef to <vscale x 4 x i16>
@@ -3671,16 +2658,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64_nxv4i64 = fptoui <vscale x 4 x double> undef to <vscale x 4 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv4f32_nxv4i1 = fptoui <vscale x 4 x float> undef to <vscale x 4 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv4f64_nxv4i1 = fptoui <vscale x 4 x double> undef to <vscale x 4 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4f32_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.fptoui.nxv4i8.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4f64_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.fptoui.nxv4i8.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv4f32_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.fptoui.nxv4i16.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv4f64_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.fptoui.nxv4i16.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4f32_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.fptoui.nxv4i32.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4f64_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.fptoui.nxv4i32.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4f32_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.fptoui.nxv4i64.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4f64_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.fptoui.nxv4i64.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv4f32_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.fptoui.nxv4i1.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv4f64_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.fptoui.nxv4i1.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv8f32_nxv8i8 = fptoui <vscale x 8 x float> undef to <vscale x 8 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %nxv8f64_nxv8i8 = fptoui <vscale x 8 x double> undef to <vscale x 8 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f32_nxv8i16 = fptoui <vscale x 8 x float> undef to <vscale x 8 x i16>
@@ -3691,16 +2668,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f64_nxv8i64 = fptoui <vscale x 8 x double> undef to <vscale x 8 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv8f32_nxv8i1 = fptoui <vscale x 8 x float> undef to <vscale x 8 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv8f64_nxv8i1 = fptoui <vscale x 8 x double> undef to <vscale x 8 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv8f32_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.fptoui.nxv8i8.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_nxv8f64_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.fptoui.nxv8i8.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8f32_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.fptoui.nxv8i16.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv8f64_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.fptoui.nxv8i16.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8f32_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.fptoui.nxv8i32.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8f64_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.fptoui.nxv8i32.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8f32_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.fptoui.nxv8i64.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8f64_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.fptoui.nxv8i64.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv8f32_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.fptoui.nxv8i1.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv8f64_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.fptoui.nxv8i1.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv16f32_nxv16i8 = fptoui <vscale x 16 x float> undef to <vscale x 16 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %nxv16f64_nxv16i8 = fptoui <vscale x 16 x double> undef to <vscale x 16 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f32_nxv16i16 = fptoui <vscale x 16 x float> undef to <vscale x 16 x i16>
@@ -3711,16 +2678,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16f64_nxv16i64 = fptoui <vscale x 16 x double> undef to <vscale x 16 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv16f32_nxv16i1 = fptoui <vscale x 16 x float> undef to <vscale x 16 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv16f64_nxv16i1 = fptoui <vscale x 16 x double> undef to <vscale x 16 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv16f32_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.fptoui.nxv16i8.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_nxv16f64_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.fptoui.nxv16i8.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv16f32_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.fptoui.nxv16i16.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_nxv16f64_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.fptoui.nxv16i16.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16f32_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.fptoui.nxv16i32.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv16f64_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.fptoui.nxv16i32.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16f32_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.fptoui.nxv16i64.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv16f64_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.fptoui.nxv16i64.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv16f32_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.fptoui.nxv16i1.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16f64_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.fptoui.nxv16i1.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %nxv32f32_nxv32i8 = fptoui <vscale x 32 x float> undef to <vscale x 32 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %nxv32f64_nxv32i8 = fptoui <vscale x 32 x double> undef to <vscale x 32 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %nxv32f32_nxv32i16 = fptoui <vscale x 32 x float> undef to <vscale x 32 x i16>
@@ -3731,16 +2688,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32f64_nxv32i64 = fptoui <vscale x 32 x double> undef to <vscale x 32 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv32f32_nxv32i1 = fptoui <vscale x 32 x float> undef to <vscale x 32 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv32f64_nxv32i1 = fptoui <vscale x 32 x double> undef to <vscale x 32 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %vp_nxv32f32_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.fptoui.nxv32i8.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_nxv32f64_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.fptoui.nxv32i8.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv32f32_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.fptoui.nxv32i16.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_nxv32f64_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.fptoui.nxv32i16.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv32f32_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.fptoui.nxv32i32.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv32f64_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.fptoui.nxv32i32.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv32f32_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.fptoui.nxv32i64.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv32f64_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.fptoui.nxv32i64.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv32f32_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.fptoui.nxv32i1.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv32f64_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.fptoui.nxv32i1.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %nxv64f32_nxv64i8 = fptoui <vscale x 64 x float> undef to <vscale x 64 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %nxv64f64_nxv64i8 = fptoui <vscale x 64 x double> undef to <vscale x 64 x i8>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %nxv64f32_nxv64i16 = fptoui <vscale x 64 x float> undef to <vscale x 64 x i16>
@@ -3751,16 +2698,6 @@ define void @fptoui() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv64f64_nxv64i64 = fptoui <vscale x 64 x double> undef to <vscale x 64 x i64>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv64f32_nxv64i1 = fptoui <vscale x 64 x float> undef to <vscale x 64 x i1>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %nxv64f64_nxv64i1 = fptoui <vscale x 64 x double> undef to <vscale x 64 x i1>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %vp_nxv64f32_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.fptoui.nxv64i8.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_nxv64f64_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.fptoui.nxv64i8.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv64f32_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.fptoui.nxv64i16.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %vp_nxv64f64_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.fptoui.nxv64i16.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv64f32_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.fptoui.nxv64i32.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_nxv64f64_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.fptoui.nxv64i32.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv64f32_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.fptoui.nxv64i64.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv64f64_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.fptoui.nxv64i64.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv64f32_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.fptoui.nxv64i1.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %vp_nxv64f64_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.fptoui.nxv64i1.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVE64X-LABEL: 'fptoui'
@@ -3774,16 +2711,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2f64_v2i64 = fptoui <2 x double> undef to <2 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %v2f32_v2i1 = fptoui <2 x float> undef to <2 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %v2f64_v2i1 = fptoui <2 x double> undef to <2 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f32_v2i8 = call <2 x i8> @llvm.vp.fptoui.v2i8.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f64_v2i8 = call <2 x i8> @llvm.vp.fptoui.v2i8.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f32_v2i16 = call <2 x i16> @llvm.vp.fptoui.v2i16.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f64_v2i16 = call <2 x i16> @llvm.vp.fptoui.v2i16.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f32_v2i32 = call <2 x i32> @llvm.vp.fptoui.v2i32.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v2f64_v2i32 = call <2 x i32> @llvm.vp.fptoui.v2i32.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f32_v2i64 = call <2 x i64> @llvm.vp.fptoui.v2i64.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2f64_v2i64 = call <2 x i64> @llvm.vp.fptoui.v2i64.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %vp_v2f32_v2i1 = call <2 x i1> @llvm.vp.fptoui.v2i1.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %vp_v2f64_v2i1 = call <2 x i1> @llvm.vp.fptoui.v2i1.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v4f32_v4i8 = fptoui <4 x float> undef to <4 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v4f64_v4i8 = fptoui <4 x double> undef to <4 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v4f32_v4i16 = fptoui <4 x float> undef to <4 x i16>
@@ -3794,16 +2721,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4f64_v4i64 = fptoui <4 x double> undef to <4 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %v4f32_v4i1 = fptoui <4 x float> undef to <4 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %v4f64_v4i1 = fptoui <4 x double> undef to <4 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f32_v4i8 = call <4 x i8> @llvm.vp.fptoui.v4i8.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f64_v4i8 = call <4 x i8> @llvm.vp.fptoui.v4i8.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f32_v4i16 = call <4 x i16> @llvm.vp.fptoui.v4i16.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f64_v4i16 = call <4 x i16> @llvm.vp.fptoui.v4i16.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f32_v4i32 = call <4 x i32> @llvm.vp.fptoui.v4i32.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v4f64_v4i32 = call <4 x i32> @llvm.vp.fptoui.v4i32.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4f32_v4i64 = call <4 x i64> @llvm.vp.fptoui.v4i64.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4f64_v4i64 = call <4 x i64> @llvm.vp.fptoui.v4i64.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %vp_v4f32_v4i1 = call <4 x i1> @llvm.vp.fptoui.v4i1.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %vp_v4f64_v4i1 = call <4 x i1> @llvm.vp.fptoui.v4i1.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v8f32_v8i8 = fptoui <8 x float> undef to <8 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v8f64_v8i8 = fptoui <8 x double> undef to <8 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v8f32_v8i16 = fptoui <8 x float> undef to <8 x i16>
@@ -3814,16 +2731,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8f64_v8i64 = fptoui <8 x double> undef to <8 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %v8f32_v8i1 = fptoui <8 x float> undef to <8 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %v8f64_v8i1 = fptoui <8 x double> undef to <8 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f32_v8i8 = call <8 x i8> @llvm.vp.fptoui.v8i8.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f64_v8i8 = call <8 x i8> @llvm.vp.fptoui.v8i8.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f32_v8i16 = call <8 x i16> @llvm.vp.fptoui.v8i16.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f64_v8i16 = call <8 x i16> @llvm.vp.fptoui.v8i16.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f32_v8i32 = call <8 x i32> @llvm.vp.fptoui.v8i32.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v8f64_v8i32 = call <8 x i32> @llvm.vp.fptoui.v8i32.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8f32_v8i64 = call <8 x i64> @llvm.vp.fptoui.v8i64.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8f64_v8i64 = call <8 x i64> @llvm.vp.fptoui.v8i64.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_v8f32_v8i1 = call <8 x i1> @llvm.vp.fptoui.v8i1.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %vp_v8f64_v8i1 = call <8 x i1> @llvm.vp.fptoui.v8i1.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v16f32_v16i8 = fptoui <16 x float> undef to <16 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v16f64_v16i8 = fptoui <16 x double> undef to <16 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v16f32_v16i16 = fptoui <16 x float> undef to <16 x i16>
@@ -3834,16 +2741,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16f64_v16i64 = fptoui <16 x double> undef to <16 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 159 for instruction: %v16f32_v16i1 = fptoui <16 x float> undef to <16 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 159 for instruction: %v16f64_v16i1 = fptoui <16 x double> undef to <16 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f32_v16i8 = call <16 x i8> @llvm.vp.fptoui.v16i8.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f64_v16i8 = call <16 x i8> @llvm.vp.fptoui.v16i8.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f32_v16i16 = call <16 x i16> @llvm.vp.fptoui.v16i16.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f64_v16i16 = call <16 x i16> @llvm.vp.fptoui.v16i16.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f32_v16i32 = call <16 x i32> @llvm.vp.fptoui.v16i32.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v16f64_v16i32 = call <16 x i32> @llvm.vp.fptoui.v16i32.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16f32_v16i64 = call <16 x i64> @llvm.vp.fptoui.v16i64.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16f64_v16i64 = call <16 x i64> @llvm.vp.fptoui.v16i64.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 159 for instruction: %vp_v16f32_v16i1 = call <16 x i1> @llvm.vp.fptoui.v16i1.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 159 for instruction: %vp_v16f64_v16i1 = call <16 x i1> @llvm.vp.fptoui.v16i1.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v32f32_v32i8 = fptoui <32 x float> undef to <32 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v32f64_v32i8 = fptoui <32 x double> undef to <32 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v32f32_v32i16 = fptoui <32 x float> undef to <32 x i16>
@@ -3854,16 +2751,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %v32f64_v32i64 = fptoui <32 x double> undef to <32 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 319 for instruction: %v32f32_v32i1 = fptoui <32 x float> undef to <32 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 319 for instruction: %v32f64_v32i1 = fptoui <32 x double> undef to <32 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f32_v32i8 = call <32 x i8> @llvm.vp.fptoui.v32i8.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f64_v32i8 = call <32 x i8> @llvm.vp.fptoui.v32i8.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f32_v32i16 = call <32 x i16> @llvm.vp.fptoui.v32i16.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f64_v32i16 = call <32 x i16> @llvm.vp.fptoui.v32i16.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f32_v32i32 = call <32 x i32> @llvm.vp.fptoui.v32i32.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v32f64_v32i32 = call <32 x i32> @llvm.vp.fptoui.v32i32.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %vp_v32f32_v32i64 = call <32 x i64> @llvm.vp.fptoui.v32i64.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %vp_v32f64_v32i64 = call <32 x i64> @llvm.vp.fptoui.v32i64.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 319 for instruction: %vp_v32f32_v32i1 = call <32 x i1> @llvm.vp.fptoui.v32i1.v32f32(<32 x float> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 319 for instruction: %vp_v32f64_v32i1 = call <32 x i1> @llvm.vp.fptoui.v32i1.v32f64(<32 x double> undef, <32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v64f32_v64i8 = fptoui <64 x float> undef to <64 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v64f64_v64i8 = fptoui <64 x double> undef to <64 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v64f32_v64i16 = fptoui <64 x float> undef to <64 x i16>
@@ -3874,16 +2761,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %v64f64_v64i64 = fptoui <64 x double> undef to <64 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 639 for instruction: %v64f32_v64i1 = fptoui <64 x float> undef to <64 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 639 for instruction: %v64f64_v64i1 = fptoui <64 x double> undef to <64 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v64f32_v64i8 = call <64 x i8> @llvm.vp.fptoui.v64i8.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v64f64_v64i8 = call <64 x i8> @llvm.vp.fptoui.v64i8.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v64f32_v64i16 = call <64 x i16> @llvm.vp.fptoui.v64i16.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v64f64_v64i16 = call <64 x i16> @llvm.vp.fptoui.v64i16.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %vp_v64f32_v64i32 = call <64 x i32> @llvm.vp.fptoui.v64i32.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %vp_v64f64_v64i32 = call <64 x i32> @llvm.vp.fptoui.v64i32.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %vp_v64f32_v64i64 = call <64 x i64> @llvm.vp.fptoui.v64i64.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %vp_v64f64_v64i64 = call <64 x i64> @llvm.vp.fptoui.v64i64.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 639 for instruction: %vp_v64f32_v64i1 = call <64 x i1> @llvm.vp.fptoui.v64i1.v64f32(<64 x float> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 639 for instruction: %vp_v64f64_v64i1 = call <64 x i1> @llvm.vp.fptoui.v64i1.v64f64(<64 x double> undef, <64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 511 for instruction: %v128f32_v128i8 = fptoui <128 x float> undef to <128 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 511 for instruction: %v128f64_v128i8 = fptoui <128 x double> undef to <128 x i8>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 510 for instruction: %v128f32_v128i16 = fptoui <128 x float> undef to <128 x i16>
@@ -3894,16 +2771,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %v128f64_v128i64 = fptoui <128 x double> undef to <128 x i64>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 1279 for instruction: %v128f32_v128i1 = fptoui <128 x float> undef to <128 x i1>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 1279 for instruction: %v128f64_v128i1 = fptoui <128 x double> undef to <128 x i1>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 511 for instruction: %vp_v128f32_v128i8 = call <128 x i8> @llvm.vp.fptoui.v128i8.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 511 for instruction: %vp_v128f64_v128i8 = call <128 x i8> @llvm.vp.fptoui.v128i8.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 510 for instruction: %vp_v128f32_v128i16 = call <128 x i16> @llvm.vp.fptoui.v128i16.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 510 for instruction: %vp_v128f64_v128i16 = call <128 x i16> @llvm.vp.fptoui.v128i16.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 508 for instruction: %vp_v128f32_v128i32 = call <128 x i32> @llvm.vp.fptoui.v128i32.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 508 for instruction: %vp_v128f64_v128i32 = call <128 x i32> @llvm.vp.fptoui.v128i32.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %vp_v128f32_v128i64 = call <128 x i64> @llvm.vp.fptoui.v128i64.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %vp_v128f64_v128i64 = call <128 x i64> @llvm.vp.fptoui.v128i64.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 1279 for instruction: %vp_v128f32_v128i1 = call <128 x i1> @llvm.vp.fptoui.v128i1.v128f32(<128 x float> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 1279 for instruction: %vp_v128f64_v128i1 = call <128 x i1> @llvm.vp.fptoui.v128i1.v128f64(<128 x double> undef, <128 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f32_nxv1i8 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i8 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f32_nxv1i16 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i16>
@@ -3914,16 +2781,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i64 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f32_nxv1i1 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i1 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.fptoui.nxv1i8.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i8 = call <vscale x 1 x i8> @llvm.vp.fptoui.nxv1i8.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.fptoui.nxv1i16.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i16 = call <vscale x 1 x i16> @llvm.vp.fptoui.nxv1i16.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.fptoui.nxv1i32.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i32 = call <vscale x 1 x i32> @llvm.vp.fptoui.nxv1i32.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.fptoui.nxv1i64.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i64 = call <vscale x 1 x i64> @llvm.vp.fptoui.nxv1i64.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f32_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.fptoui.nxv1i1.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1f64_nxv1i1 = call <vscale x 1 x i1> @llvm.vp.fptoui.nxv1i1.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f32_nxv2i8 = fptoui <vscale x 2 x float> undef to <vscale x 2 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i8 = fptoui <vscale x 2 x double> undef to <vscale x 2 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f32_nxv2i16 = fptoui <vscale x 2 x float> undef to <vscale x 2 x i16>
@@ -3934,16 +2791,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i64 = fptoui <vscale x 2 x double> undef to <vscale x 2 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f32_nxv2i1 = fptoui <vscale x 2 x float> undef to <vscale x 2 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i1 = fptoui <vscale x 2 x double> undef to <vscale x 2 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.fptoui.nxv2i8.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i8 = call <vscale x 2 x i8> @llvm.vp.fptoui.nxv2i8.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.fptoui.nxv2i16.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i16 = call <vscale x 2 x i16> @llvm.vp.fptoui.nxv2i16.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.fptoui.nxv2i32.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i32 = call <vscale x 2 x i32> @llvm.vp.fptoui.nxv2i32.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.fptoui.nxv2i64.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i64 = call <vscale x 2 x i64> @llvm.vp.fptoui.nxv2i64.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f32_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.fptoui.nxv2i1.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2f64_nxv2i1 = call <vscale x 2 x i1> @llvm.vp.fptoui.nxv2i1.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f32_nxv4i8 = fptoui <vscale x 4 x float> undef to <vscale x 4 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i8 = fptoui <vscale x 4 x double> undef to <vscale x 4 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f32_nxv4i16 = fptoui <vscale x 4 x float> undef to <vscale x 4 x i16>
@@ -3954,16 +2801,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i64 = fptoui <vscale x 4 x double> undef to <vscale x 4 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f32_nxv4i1 = fptoui <vscale x 4 x float> undef to <vscale x 4 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i1 = fptoui <vscale x 4 x double> undef to <vscale x 4 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.fptoui.nxv4i8.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i8 = call <vscale x 4 x i8> @llvm.vp.fptoui.nxv4i8.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.fptoui.nxv4i16.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i16 = call <vscale x 4 x i16> @llvm.vp.fptoui.nxv4i16.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.fptoui.nxv4i32.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i32 = call <vscale x 4 x i32> @llvm.vp.fptoui.nxv4i32.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.fptoui.nxv4i64.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i64 = call <vscale x 4 x i64> @llvm.vp.fptoui.nxv4i64.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f32_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.fptoui.nxv4i1.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4f64_nxv4i1 = call <vscale x 4 x i1> @llvm.vp.fptoui.nxv4i1.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f32_nxv8i8 = fptoui <vscale x 8 x float> undef to <vscale x 8 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i8 = fptoui <vscale x 8 x double> undef to <vscale x 8 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f32_nxv8i16 = fptoui <vscale x 8 x float> undef to <vscale x 8 x i16>
@@ -3974,16 +2811,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i64 = fptoui <vscale x 8 x double> undef to <vscale x 8 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f32_nxv8i1 = fptoui <vscale x 8 x float> undef to <vscale x 8 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i1 = fptoui <vscale x 8 x double> undef to <vscale x 8 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.fptoui.nxv8i8.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i8 = call <vscale x 8 x i8> @llvm.vp.fptoui.nxv8i8.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.fptoui.nxv8i16.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i16 = call <vscale x 8 x i16> @llvm.vp.fptoui.nxv8i16.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.fptoui.nxv8i32.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i32 = call <vscale x 8 x i32> @llvm.vp.fptoui.nxv8i32.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.fptoui.nxv8i64.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i64 = call <vscale x 8 x i64> @llvm.vp.fptoui.nxv8i64.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f32_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.fptoui.nxv8i1.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8f64_nxv8i1 = call <vscale x 8 x i1> @llvm.vp.fptoui.nxv8i1.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f32_nxv16i8 = fptoui <vscale x 16 x float> undef to <vscale x 16 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i8 = fptoui <vscale x 16 x double> undef to <vscale x 16 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f32_nxv16i16 = fptoui <vscale x 16 x float> undef to <vscale x 16 x i16>
@@ -3994,16 +2821,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i64 = fptoui <vscale x 16 x double> undef to <vscale x 16 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f32_nxv16i1 = fptoui <vscale x 16 x float> undef to <vscale x 16 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i1 = fptoui <vscale x 16 x double> undef to <vscale x 16 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.fptoui.nxv16i8.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i8 = call <vscale x 16 x i8> @llvm.vp.fptoui.nxv16i8.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.fptoui.nxv16i16.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i16 = call <vscale x 16 x i16> @llvm.vp.fptoui.nxv16i16.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.fptoui.nxv16i32.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i32 = call <vscale x 16 x i32> @llvm.vp.fptoui.nxv16i32.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.fptoui.nxv16i64.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i64 = call <vscale x 16 x i64> @llvm.vp.fptoui.nxv16i64.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f32_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.fptoui.nxv16i1.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16f64_nxv16i1 = call <vscale x 16 x i1> @llvm.vp.fptoui.nxv16i1.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f32_nxv32i8 = fptoui <vscale x 32 x float> undef to <vscale x 32 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f64_nxv32i8 = fptoui <vscale x 32 x double> undef to <vscale x 32 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f32_nxv32i16 = fptoui <vscale x 32 x float> undef to <vscale x 32 x i16>
@@ -4014,16 +2831,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f64_nxv32i64 = fptoui <vscale x 32 x double> undef to <vscale x 32 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f32_nxv32i1 = fptoui <vscale x 32 x float> undef to <vscale x 32 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32f64_nxv32i1 = fptoui <vscale x 32 x double> undef to <vscale x 32 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.fptoui.nxv32i8.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i8 = call <vscale x 32 x i8> @llvm.vp.fptoui.nxv32i8.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.fptoui.nxv32i16.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i16 = call <vscale x 32 x i16> @llvm.vp.fptoui.nxv32i16.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.fptoui.nxv32i32.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i32 = call <vscale x 32 x i32> @llvm.vp.fptoui.nxv32i32.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.fptoui.nxv32i64.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i64 = call <vscale x 32 x i64> @llvm.vp.fptoui.nxv32i64.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f32_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.fptoui.nxv32i1.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32f64_nxv32i1 = call <vscale x 32 x i1> @llvm.vp.fptoui.nxv32i1.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f32_nxv64i8 = fptoui <vscale x 64 x float> undef to <vscale x 64 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f64_nxv64i8 = fptoui <vscale x 64 x double> undef to <vscale x 64 x i8>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f32_nxv64i16 = fptoui <vscale x 64 x float> undef to <vscale x 64 x i16>
@@ -4034,16 +2841,6 @@ define void @fptoui() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f64_nxv64i64 = fptoui <vscale x 64 x double> undef to <vscale x 64 x i64>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f32_nxv64i1 = fptoui <vscale x 64 x float> undef to <vscale x 64 x i1>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64f64_nxv64i1 = fptoui <vscale x 64 x double> undef to <vscale x 64 x i1>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.fptoui.nxv64i8.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i8 = call <vscale x 64 x i8> @llvm.vp.fptoui.nxv64i8.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.fptoui.nxv64i16.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i16 = call <vscale x 64 x i16> @llvm.vp.fptoui.nxv64i16.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.fptoui.nxv64i32.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i32 = call <vscale x 64 x i32> @llvm.vp.fptoui.nxv64i32.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.fptoui.nxv64i64.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i64 = call <vscale x 64 x i64> @llvm.vp.fptoui.nxv64i64.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f32_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.fptoui.nxv64i1.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64f64_nxv64i1 = call <vscale x 64 x i1> @llvm.vp.fptoui.nxv64i1.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f32_v2i8 = fptoui <2 x float> undef to <2 x i8>
@@ -4369,16 +3166,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_v2f64 = sitofp <2 x i64> undef to <2 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i1_v2f32 = sitofp <2 x i1> undef to <2 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i1_v2f64 = sitofp <2 x i1> undef to <2 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2fi8_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2fi8_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi16_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2fi16_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi32_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi32_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi64_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi64_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi1_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi1_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i8_v4f32 = sitofp <4 x i8> undef to <4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i8_v4f64 = sitofp <4 x i8> undef to <4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_v4f32 = sitofp <4 x i16> undef to <4 x float>
@@ -4389,16 +3176,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64_v4f64 = sitofp <4 x i64> undef to <4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i1_v4f32 = sitofp <4 x i1> undef to <4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4i1_v4f64 = sitofp <4 x i1> undef to <4 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4fi8_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4fi8_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4fi16_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4fi16_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4fi32_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4fi32_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4fi64_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4fi64_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4fi1_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4fi1_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i8_v8f32 = sitofp <8 x i8> undef to <8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v8i8_v8f64 = sitofp <8 x i8> undef to <8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i16_v8f32 = sitofp <8 x i16> undef to <8 x float>
@@ -4409,16 +3186,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64_v8f64 = sitofp <8 x i64> undef to <8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i1_v8f32 = sitofp <8 x i1> undef to <8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i1_v8f64 = sitofp <8 x i1> undef to <8 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v8fi8_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v8fi8_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8fi16_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v8fi16_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8fi32_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8fi32_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8fi64_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8fi64_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8fi1_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8fi1_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v16i8_v16f32 = sitofp <16 x i8> undef to <16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v16i8_v16f64 = sitofp <16 x i8> undef to <16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i16_v16f32 = sitofp <16 x i16> undef to <16 x float>
@@ -4429,16 +3196,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16i64_v16f64 = sitofp <16 x i64> undef to <16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16i1_v16f32 = sitofp <16 x i1> undef to <16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16i1_v16f64 = sitofp <16 x i1> undef to <16 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v16fi8_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v16fi8_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16fi16_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v16fi16_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16fi32_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16fi32_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16fi64_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16fi64_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16fi1_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16fi1_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v32i8_v32f32 = sitofp <32 x i8> undef to <32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v32i8_v32f64 = sitofp <32 x i8> undef to <32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v32i16_v32f32 = sitofp <32 x i16> undef to <32 x float>
@@ -4449,16 +3206,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v32i64_v32f64 = sitofp <32 x i64> undef to <32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v32i1_v32f32 = sitofp <32 x i1> undef to <32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v32i1_v32f64 = sitofp <32 x i1> undef to <32 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v32fi8_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32fi8_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32fi16_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32fi16_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32fi32_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32fi32_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v32fi64_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v32fi64_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v32fi1_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_v32fi1_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v64i8_v64f32 = sitofp <64 x i8> undef to <64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v64i8_v64f64 = sitofp <64 x i8> undef to <64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v64i16_v64f32 = sitofp <64 x i16> undef to <64 x float>
@@ -4469,16 +3216,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v64i64_v64f64 = sitofp <64 x i64> undef to <64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v64i1_v64f32 = sitofp <64 x i1> undef to <64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %v64i1_v64f64 = sitofp <64 x i1> undef to <64 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v64fi8_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v64fi8_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v64fi16_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v64fi16_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v64fi32_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v64fi32_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v64fi64_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v64fi64_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_v64fi1_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_v64fi1_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v128i8_v128f32 = sitofp <128 x i8> undef to <128 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %v128i8_v128f64 = sitofp <128 x i8> undef to <128 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v128i16_v128f32 = sitofp <128 x i16> undef to <128 x float>
@@ -4489,16 +3226,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v128i64_v128f64 = sitofp <128 x i64> undef to <128 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %v128i1_v128f32 = sitofp <128 x i1> undef to <128 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %v128i1_v128f64 = sitofp <128 x i1> undef to <128 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v128fi8_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %vp_v128fi8_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v128fi16_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %vp_v128fi16_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v128fi32_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v128fi32_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_v128fi64_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %vp_v128fi64_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_v128fi1_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %vp_v128fi1_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i8_nxv1f32 = sitofp <vscale x 1 x i8> undef to <vscale x 1 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i8_nxv1f64 = sitofp <vscale x 1 x i8> undef to <vscale x 1 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16_nxv1f32 = sitofp <vscale x 1 x i16> undef to <vscale x 1 x float>
@@ -4509,16 +3236,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64_nxv1f64 = sitofp <vscale x 1 x i64> undef to <vscale x 1 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1i1_nxv1f32 = sitofp <vscale x 1 x i1> undef to <vscale x 1 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1i1_nxv1f64 = sitofp <vscale x 1 x i1> undef to <vscale x 1 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1fi8_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1fi8_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi16_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1fi16_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi32_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi32_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi64_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi64_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1fi1_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1fi1_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i8_nxv2f32 = sitofp <vscale x 2 x i8> undef to <vscale x 2 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2i8_nxv2f64 = sitofp <vscale x 2 x i8> undef to <vscale x 2 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16_nxv2f32 = sitofp <vscale x 2 x i16> undef to <vscale x 2 x float>
@@ -4529,16 +3246,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64_nxv2f64 = sitofp <vscale x 2 x i64> undef to <vscale x 2 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2i1_nxv2f32 = sitofp <vscale x 2 x i1> undef to <vscale x 2 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv2i1_nxv2f64 = sitofp <vscale x 2 x i1> undef to <vscale x 2 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2fi8_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2fi8_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2fi16_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2fi16_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2fi32_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2fi32_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2fi64_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2fi64_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2fi1_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv2fi1_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv4i8_nxv4f32 = sitofp <vscale x 4 x i8> undef to <vscale x 4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv4i8_nxv4f64 = sitofp <vscale x 4 x i8> undef to <vscale x 4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i16_nxv4f32 = sitofp <vscale x 4 x i16> undef to <vscale x 4 x float>
@@ -4549,16 +3256,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64_nxv4f64 = sitofp <vscale x 4 x i64> undef to <vscale x 4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i1_nxv4f32 = sitofp <vscale x 4 x i1> undef to <vscale x 4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv4i1_nxv4f64 = sitofp <vscale x 4 x i1> undef to <vscale x 4 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv4fi8_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv4fi8_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4fi16_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv4fi16_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4fi32_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4fi32_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4fi64_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4fi64_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4fi1_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv4fi1_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv8i8_nxv8f32 = sitofp <vscale x 8 x i8> undef to <vscale x 8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv8i8_nxv8f64 = sitofp <vscale x 8 x i8> undef to <vscale x 8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i16_nxv8f32 = sitofp <vscale x 8 x i16> undef to <vscale x 8 x float>
@@ -4569,16 +3266,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64_nxv8f64 = sitofp <vscale x 8 x i64> undef to <vscale x 8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i1_nxv8f32 = sitofp <vscale x 8 x i1> undef to <vscale x 8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv8i1_nxv8f64 = sitofp <vscale x 8 x i1> undef to <vscale x 8 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8fi8_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8fi8_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv8fi16_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv8fi16_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv8fi32_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv8fi32_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv8fi64_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv8fi64_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv8fi1_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv8fi1_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv16i8_nxv16f32 = sitofp <vscale x 16 x i8> undef to <vscale x 16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv16i8_nxv16f64 = sitofp <vscale x 16 x i8> undef to <vscale x 16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i16_nxv16f32 = sitofp <vscale x 16 x i16> undef to <vscale x 16 x float>
@@ -4589,16 +3276,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i64_nxv16f64 = sitofp <vscale x 16 x i64> undef to <vscale x 16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv16i1_nxv16f32 = sitofp <vscale x 16 x i1> undef to <vscale x 16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %nxv16i1_nxv16f64 = sitofp <vscale x 16 x i1> undef to <vscale x 16 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv16fi8_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16fi8_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16fi16_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16fi16_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16fi32_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16fi32_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv16fi64_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv16fi64_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv16fi1_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_nxv16fi1_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv32i8_nxv32f32 = sitofp <vscale x 32 x i8> undef to <vscale x 32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv32i8_nxv32f64 = sitofp <vscale x 32 x i8> undef to <vscale x 32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv32i16_nxv32f32 = sitofp <vscale x 32 x i16> undef to <vscale x 32 x float>
@@ -4609,16 +3286,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i64_nxv32f64 = sitofp <vscale x 32 x i64> undef to <vscale x 32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %nxv32i1_nxv32f32 = sitofp <vscale x 32 x i1> undef to <vscale x 32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %nxv32i1_nxv32f64 = sitofp <vscale x 32 x i1> undef to <vscale x 32 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv32fi8_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv32fi8_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv32fi16_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv32fi16_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv32fi32_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv32fi32_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv32fi64_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv32fi64_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_nxv32fi1_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_nxv32fi1_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv64i8_nxv64f32 = sitofp <vscale x 64 x i8> undef to <vscale x 64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %nxv64i8_nxv64f64 = sitofp <vscale x 64 x i8> undef to <vscale x 64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %nxv64i16_nxv64f32 = sitofp <vscale x 64 x i16> undef to <vscale x 64 x float>
@@ -4629,16 +3296,6 @@ define void @sitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv64i64_nxv64f64 = sitofp <vscale x 64 x i64> undef to <vscale x 64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %nxv64i1_nxv64f32 = sitofp <vscale x 64 x i1> undef to <vscale x 64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %nxv64i1_nxv64f64 = sitofp <vscale x 64 x i1> undef to <vscale x 64 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv64fi8_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %vp_nxv64fi8_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv64fi16_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %vp_nxv64fi16_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv64fi32_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv64fi32_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_nxv64fi64_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv64fi64_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_nxv64fi1_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %vp_nxv64fi1_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVE64X-LABEL: 'sitofp'
@@ -4652,16 +3309,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i64_v2f64 = sitofp <2 x i64> undef to <2 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i1_v2f32 = sitofp <2 x i1> undef to <2 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i1_v2f64 = sitofp <2 x i1> undef to <2 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi8_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi8_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi16_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi16_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi32_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi32_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi64_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi64_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi1_v2f32 = call <2 x float> @llvm.vp.sitofp.v2f32.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi1_v2f64 = call <2 x double> @llvm.vp.sitofp.v2f64.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i8_v4f32 = sitofp <4 x i8> undef to <4 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i8_v4f64 = sitofp <4 x i8> undef to <4 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i16_v4f32 = sitofp <4 x i16> undef to <4 x float>
@@ -4672,16 +3319,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i64_v4f64 = sitofp <4 x i64> undef to <4 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i1_v4f32 = sitofp <4 x i1> undef to <4 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i1_v4f64 = sitofp <4 x i1> undef to <4 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi8_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi8_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi16_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi16_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi32_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi32_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi64_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi64_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi1_v4f32 = call <4 x float> @llvm.vp.sitofp.v4f32.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi1_v4f64 = call <4 x double> @llvm.vp.sitofp.v4f64.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i8_v8f32 = sitofp <8 x i8> undef to <8 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i8_v8f64 = sitofp <8 x i8> undef to <8 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i16_v8f32 = sitofp <8 x i16> undef to <8 x float>
@@ -4692,16 +3329,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i64_v8f64 = sitofp <8 x i64> undef to <8 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i1_v8f32 = sitofp <8 x i1> undef to <8 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i1_v8f64 = sitofp <8 x i1> undef to <8 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi8_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi8_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi16_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi16_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi32_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi32_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi64_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi64_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi1_v8f32 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi1_v8f64 = call <8 x double> @llvm.vp.sitofp.v8f64.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i8_v16f32 = sitofp <16 x i8> undef to <16 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i8_v16f64 = sitofp <16 x i8> undef to <16 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i16_v16f32 = sitofp <16 x i16> undef to <16 x float>
@@ -4712,16 +3339,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i64_v16f64 = sitofp <16 x i64> undef to <16 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i1_v16f32 = sitofp <16 x i1> undef to <16 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i1_v16f64 = sitofp <16 x i1> undef to <16 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi8_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi8_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi16_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi16_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi32_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi32_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi64_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi64_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi1_v16f32 = call <16 x float> @llvm.vp.sitofp.v16f32.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi1_v16f64 = call <16 x double> @llvm.vp.sitofp.v16f64.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i8_v32f32 = sitofp <32 x i8> undef to <32 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i8_v32f64 = sitofp <32 x i8> undef to <32 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i16_v32f32 = sitofp <32 x i16> undef to <32 x float>
@@ -4732,16 +3349,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %v32i64_v32f64 = sitofp <32 x i64> undef to <32 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i1_v32f32 = sitofp <32 x i1> undef to <32 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i1_v32f64 = sitofp <32 x i1> undef to <32 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi8_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi8_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi16_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi16_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi32_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi32_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %vp_v32fi64_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %vp_v32fi64_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi1_v32f32 = call <32 x float> @llvm.vp.sitofp.v32f32.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi1_v32f64 = call <32 x double> @llvm.vp.sitofp.v32f64.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i8_v64f32 = sitofp <64 x i8> undef to <64 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i8_v64f64 = sitofp <64 x i8> undef to <64 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i16_v64f32 = sitofp <64 x i16> undef to <64 x float>
@@ -4752,16 +3359,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %v64i64_v64f64 = sitofp <64 x i64> undef to <64 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i1_v64f32 = sitofp <64 x i1> undef to <64 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i1_v64f64 = sitofp <64 x i1> undef to <64 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi8_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi8_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi16_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi16_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %vp_v64fi32_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %vp_v64fi32_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %vp_v64fi64_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %vp_v64fi64_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi1_v64f32 = call <64 x float> @llvm.vp.sitofp.v64f32.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi1_v64f64 = call <64 x double> @llvm.vp.sitofp.v64f64.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v128i8_v128f32 = sitofp <128 x i8> undef to <128 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v128i8_v128f64 = sitofp <128 x i8> undef to <128 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %v128i16_v128f32 = sitofp <128 x i16> undef to <128 x float>
@@ -4772,16 +3369,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %v128i64_v128f64 = sitofp <128 x i64> undef to <128 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v128i1_v128f32 = sitofp <128 x i1> undef to <128 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v128i1_v128f64 = sitofp <128 x i1> undef to <128 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v128fi8_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v128fi8_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %vp_v128fi16_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %vp_v128fi16_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 252 for instruction: %vp_v128fi32_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 252 for instruction: %vp_v128fi32_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %vp_v128fi64_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %vp_v128fi64_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v128fi1_v128f32 = call <128 x float> @llvm.vp.sitofp.v128f32.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v128fi1_v128f64 = call <128 x double> @llvm.vp.sitofp.v128f64.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i8_nxv1f32 = sitofp <vscale x 1 x i8> undef to <vscale x 1 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i8_nxv1f64 = sitofp <vscale x 1 x i8> undef to <vscale x 1 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i16_nxv1f32 = sitofp <vscale x 1 x i16> undef to <vscale x 1 x float>
@@ -4792,16 +3379,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i64_nxv1f64 = sitofp <vscale x 1 x i64> undef to <vscale x 1 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i1_nxv1f32 = sitofp <vscale x 1 x i1> undef to <vscale x 1 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i1_nxv1f64 = sitofp <vscale x 1 x i1> undef to <vscale x 1 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi8_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi8_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi16_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi16_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi32_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi32_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi64_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi64_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi1_nxv1f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi1_nxv1f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i8_nxv2f32 = sitofp <vscale x 2 x i8> undef to <vscale x 2 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i8_nxv2f64 = sitofp <vscale x 2 x i8> undef to <vscale x 2 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i16_nxv2f32 = sitofp <vscale x 2 x i16> undef to <vscale x 2 x float>
@@ -4812,16 +3389,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i64_nxv2f64 = sitofp <vscale x 2 x i64> undef to <vscale x 2 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i1_nxv2f32 = sitofp <vscale x 2 x i1> undef to <vscale x 2 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i1_nxv2f64 = sitofp <vscale x 2 x i1> undef to <vscale x 2 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi8_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi8_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi16_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi16_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi32_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi32_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi64_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi64_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi1_nxv2f32 = call <vscale x 2 x float> @llvm.vp.sitofp.nxv2f32.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi1_nxv2f64 = call <vscale x 2 x double> @llvm.vp.sitofp.nxv2f64.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i8_nxv4f32 = sitofp <vscale x 4 x i8> undef to <vscale x 4 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i8_nxv4f64 = sitofp <vscale x 4 x i8> undef to <vscale x 4 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i16_nxv4f32 = sitofp <vscale x 4 x i16> undef to <vscale x 4 x float>
@@ -4832,16 +3399,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i64_nxv4f64 = sitofp <vscale x 4 x i64> undef to <vscale x 4 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i1_nxv4f32 = sitofp <vscale x 4 x i1> undef to <vscale x 4 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i1_nxv4f64 = sitofp <vscale x 4 x i1> undef to <vscale x 4 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi8_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi8_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi16_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi16_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi32_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi32_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi64_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi64_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi1_nxv4f32 = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi1_nxv4f64 = call <vscale x 4 x double> @llvm.vp.sitofp.nxv4f64.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i8_nxv8f32 = sitofp <vscale x 8 x i8> undef to <vscale x 8 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i8_nxv8f64 = sitofp <vscale x 8 x i8> undef to <vscale x 8 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i16_nxv8f32 = sitofp <vscale x 8 x i16> undef to <vscale x 8 x float>
@@ -4852,16 +3409,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i64_nxv8f64 = sitofp <vscale x 8 x i64> undef to <vscale x 8 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i1_nxv8f32 = sitofp <vscale x 8 x i1> undef to <vscale x 8 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i1_nxv8f64 = sitofp <vscale x 8 x i1> undef to <vscale x 8 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi8_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi8_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi16_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi16_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi32_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi32_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi64_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi64_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi1_nxv8f32 = call <vscale x 1 x float> @llvm.vp.sitofp.nxv1f32.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi1_nxv8f64 = call <vscale x 1 x double> @llvm.vp.sitofp.nxv1f64.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i8_nxv16f32 = sitofp <vscale x 16 x i8> undef to <vscale x 16 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i8_nxv16f64 = sitofp <vscale x 16 x i8> undef to <vscale x 16 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i16_nxv16f32 = sitofp <vscale x 16 x i16> undef to <vscale x 16 x float>
@@ -4872,16 +3419,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i64_nxv16f64 = sitofp <vscale x 16 x i64> undef to <vscale x 16 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i1_nxv16f32 = sitofp <vscale x 16 x i1> undef to <vscale x 16 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i1_nxv16f64 = sitofp <vscale x 16 x i1> undef to <vscale x 16 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi8_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi8_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi16_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi16_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi32_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi32_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi64_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi64_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi1_nxv16f32 = call <vscale x 16 x float> @llvm.vp.sitofp.nxv16f32.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi1_nxv16f64 = call <vscale x 16 x double> @llvm.vp.sitofp.nxv16f64.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i8_nxv32f32 = sitofp <vscale x 32 x i8> undef to <vscale x 32 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i8_nxv32f64 = sitofp <vscale x 32 x i8> undef to <vscale x 32 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i16_nxv32f32 = sitofp <vscale x 32 x i16> undef to <vscale x 32 x float>
@@ -4892,16 +3429,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i64_nxv32f64 = sitofp <vscale x 32 x i64> undef to <vscale x 32 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i1_nxv32f32 = sitofp <vscale x 32 x i1> undef to <vscale x 32 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i1_nxv32f64 = sitofp <vscale x 32 x i1> undef to <vscale x 32 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi8_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi8_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi16_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi16_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi32_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi32_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi64_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi64_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi1_nxv32f32 = call <vscale x 32 x float> @llvm.vp.sitofp.nxv32f32.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi1_nxv32f64 = call <vscale x 32 x double> @llvm.vp.sitofp.nxv32f64.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i8_nxv64f32 = sitofp <vscale x 64 x i8> undef to <vscale x 64 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i8_nxv64f64 = sitofp <vscale x 64 x i8> undef to <vscale x 64 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i16_nxv64f32 = sitofp <vscale x 64 x i16> undef to <vscale x 64 x float>
@@ -4912,16 +3439,6 @@ define void @sitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i64_nxv64f64 = sitofp <vscale x 64 x i64> undef to <vscale x 64 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i1_nxv64f32 = sitofp <vscale x 64 x i1> undef to <vscale x 64 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i1_nxv64f64 = sitofp <vscale x 64 x i1> undef to <vscale x 64 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi8_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi8_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi16_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi16_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi32_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi32_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi64_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi64_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi1_nxv64f32 = call <vscale x 64 x float> @llvm.vp.sitofp.nxv64f32.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi1_nxv64f64 = call <vscale x 64 x double> @llvm.vp.sitofp.nxv64f64.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8_v2f32 = sitofp <2 x i8> undef to <2 x float>
@@ -5247,16 +3764,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_v2f64 = uitofp <2 x i64> undef to <2 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i1_v2f32 = uitofp <2 x i1> undef to <2 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i1_v2f64 = uitofp <2 x i1> undef to <2 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2fi8_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2fi8_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi16_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v2fi16_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi32_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi32_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi64_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v2fi64_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi1_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi1_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i8_v4f32 = uitofp <4 x i8> undef to <4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i8_v4f64 = uitofp <4 x i8> undef to <4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_v4f32 = uitofp <4 x i16> undef to <4 x float>
@@ -5267,16 +3774,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64_v4f64 = uitofp <4 x i64> undef to <4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i1_v4f32 = uitofp <4 x i1> undef to <4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4i1_v4f64 = uitofp <4 x i1> undef to <4 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4fi8_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4fi8_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4fi16_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4fi16_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4fi32_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4fi32_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_v4fi64_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v4fi64_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v4fi1_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v4fi1_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i8_v8f32 = uitofp <8 x i8> undef to <8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v8i8_v8f64 = uitofp <8 x i8> undef to <8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i16_v8f32 = uitofp <8 x i16> undef to <8 x float>
@@ -5287,16 +3784,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64_v8f64 = uitofp <8 x i64> undef to <8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i1_v8f32 = uitofp <8 x i1> undef to <8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i1_v8f64 = uitofp <8 x i1> undef to <8 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v8fi8_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v8fi8_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8fi16_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v8fi16_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8fi32_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8fi32_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_v8fi64_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8fi64_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v8fi1_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v8fi1_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v16i8_v16f32 = uitofp <16 x i8> undef to <16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v16i8_v16f64 = uitofp <16 x i8> undef to <16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i16_v16f32 = uitofp <16 x i16> undef to <16 x float>
@@ -5307,16 +3794,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16i64_v16f64 = uitofp <16 x i64> undef to <16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16i1_v16f32 = uitofp <16 x i1> undef to <16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v16i1_v16f64 = uitofp <16 x i1> undef to <16 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_v16fi8_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v16fi8_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16fi16_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v16fi16_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16fi32_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16fi32_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_v16fi64_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16fi64_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v16fi1_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v16fi1_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v32i8_v32f32 = uitofp <32 x i8> undef to <32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v32i8_v32f64 = uitofp <32 x i8> undef to <32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v32i16_v32f32 = uitofp <32 x i16> undef to <32 x float>
@@ -5327,16 +3804,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v32i64_v32f64 = uitofp <32 x i64> undef to <32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v32i1_v32f32 = uitofp <32 x i1> undef to <32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v32i1_v32f64 = uitofp <32 x i1> undef to <32 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_v32fi8_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32fi8_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32fi16_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v32fi16_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_v32fi32_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v32fi32_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_v32fi64_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v32fi64_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v32fi1_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_v32fi1_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %v64i8_v64f32 = uitofp <64 x i8> undef to <64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v64i8_v64f64 = uitofp <64 x i8> undef to <64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %v64i16_v64f32 = uitofp <64 x i16> undef to <64 x float>
@@ -5347,16 +3814,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v64i64_v64f64 = uitofp <64 x i64> undef to <64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %v64i1_v64f32 = uitofp <64 x i1> undef to <64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %v64i1_v64f64 = uitofp <64 x i1> undef to <64 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_v64fi8_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v64fi8_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_v64fi16_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v64fi16_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_v64fi32_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v64fi32_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_v64fi64_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v64fi64_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_v64fi1_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_v64fi1_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %v128i8_v128f32 = uitofp <128 x i8> undef to <128 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %v128i8_v128f64 = uitofp <128 x i8> undef to <128 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %v128i16_v128f32 = uitofp <128 x i16> undef to <128 x float>
@@ -5367,16 +3824,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v128i64_v128f64 = uitofp <128 x i64> undef to <128 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %v128i1_v128f32 = uitofp <128 x i1> undef to <128 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %v128i1_v128f64 = uitofp <128 x i1> undef to <128 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_v128fi8_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %vp_v128fi8_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_v128fi16_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %vp_v128fi16_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %vp_v128fi32_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_v128fi32_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_v128fi64_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %vp_v128fi64_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_v128fi1_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %vp_v128fi1_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i8_nxv1f32 = uitofp <vscale x 1 x i8> undef to <vscale x 1 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv1i8_nxv1f64 = uitofp <vscale x 1 x i8> undef to <vscale x 1 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16_nxv1f32 = uitofp <vscale x 1 x i16> undef to <vscale x 1 x float>
@@ -5387,16 +3834,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64_nxv1f64 = uitofp <vscale x 1 x i64> undef to <vscale x 1 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1i1_nxv1f32 = uitofp <vscale x 1 x i1> undef to <vscale x 1 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv1i1_nxv1f64 = uitofp <vscale x 1 x i1> undef to <vscale x 1 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1fi8_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1fi8_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi16_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv1fi16_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi32_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi32_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi64_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv1fi64_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1fi1_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv1fi1_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i8_nxv2f32 = uitofp <vscale x 2 x i8> undef to <vscale x 2 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2i8_nxv2f64 = uitofp <vscale x 2 x i8> undef to <vscale x 2 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16_nxv2f32 = uitofp <vscale x 2 x i16> undef to <vscale x 2 x float>
@@ -5407,16 +3844,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64_nxv2f64 = uitofp <vscale x 2 x i64> undef to <vscale x 2 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv2i1_nxv2f32 = uitofp <vscale x 2 x i1> undef to <vscale x 2 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv2i1_nxv2f64 = uitofp <vscale x 2 x i1> undef to <vscale x 2 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2fi8_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2fi8_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2fi16_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2fi16_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2fi32_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2fi32_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %vp_nxv2fi64_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv2fi64_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv2fi1_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv2fi1_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %nxv4i8_nxv4f32 = uitofp <vscale x 4 x i8> undef to <vscale x 4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv4i8_nxv4f64 = uitofp <vscale x 4 x i8> undef to <vscale x 4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i16_nxv4f32 = uitofp <vscale x 4 x i16> undef to <vscale x 4 x float>
@@ -5427,16 +3854,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64_nxv4f64 = uitofp <vscale x 4 x i64> undef to <vscale x 4 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i1_nxv4f32 = uitofp <vscale x 4 x i1> undef to <vscale x 4 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv4i1_nxv4f64 = uitofp <vscale x 4 x i1> undef to <vscale x 4 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_nxv4fi8_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv4fi8_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4fi16_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv4fi16_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4fi32_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4fi32_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv4fi64_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4fi64_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv4fi1_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv4fi1_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nxv8i8_nxv8f32 = uitofp <vscale x 8 x i8> undef to <vscale x 8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv8i8_nxv8f64 = uitofp <vscale x 8 x i8> undef to <vscale x 8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i16_nxv8f32 = uitofp <vscale x 8 x i16> undef to <vscale x 8 x float>
@@ -5447,16 +3864,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64_nxv8f64 = uitofp <vscale x 8 x i64> undef to <vscale x 8 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i1_nxv8f32 = uitofp <vscale x 8 x i1> undef to <vscale x 8 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv8i1_nxv8f64 = uitofp <vscale x 8 x i1> undef to <vscale x 8 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %vp_nxv8fi8_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv8fi8_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8fi16_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv8fi16_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8fi32_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8fi32_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv8fi64_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8fi64_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv8fi1_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv8fi1_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %nxv16i8_nxv16f32 = uitofp <vscale x 16 x i8> undef to <vscale x 16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv16i8_nxv16f64 = uitofp <vscale x 16 x i8> undef to <vscale x 16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i16_nxv16f32 = uitofp <vscale x 16 x i16> undef to <vscale x 16 x float>
@@ -5467,16 +3874,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i64_nxv16f64 = uitofp <vscale x 16 x i64> undef to <vscale x 16 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %nxv16i1_nxv16f32 = uitofp <vscale x 16 x i1> undef to <vscale x 16 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %nxv16i1_nxv16f64 = uitofp <vscale x 16 x i1> undef to <vscale x 16 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %vp_nxv16fi8_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16fi8_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16fi16_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv16fi16_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv16fi32_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv16fi32_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %vp_nxv16fi64_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv16fi64_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %vp_nxv16fi1_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_nxv16fi1_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %nxv32i8_nxv32f32 = uitofp <vscale x 32 x i8> undef to <vscale x 32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv32i8_nxv32f64 = uitofp <vscale x 32 x i8> undef to <vscale x 32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %nxv32i16_nxv32f32 = uitofp <vscale x 32 x i16> undef to <vscale x 32 x float>
@@ -5487,16 +3884,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i64_nxv32f64 = uitofp <vscale x 32 x i64> undef to <vscale x 32 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %nxv32i1_nxv32f32 = uitofp <vscale x 32 x i1> undef to <vscale x 32 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %nxv32i1_nxv32f64 = uitofp <vscale x 32 x i1> undef to <vscale x 32 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %vp_nxv32fi8_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv32fi8_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %vp_nxv32fi16_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv32fi16_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %vp_nxv32fi32_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv32fi32_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %vp_nxv32fi64_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv32fi64_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %vp_nxv32fi1_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_nxv32fi1_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %nxv64i8_nxv64f32 = uitofp <vscale x 64 x i8> undef to <vscale x 64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %nxv64i8_nxv64f64 = uitofp <vscale x 64 x i8> undef to <vscale x 64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %nxv64i16_nxv64f32 = uitofp <vscale x 64 x i16> undef to <vscale x 64 x float>
@@ -5507,16 +3894,6 @@ define void @uitofp() {
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv64i64_nxv64f64 = uitofp <vscale x 64 x i64> undef to <vscale x 64 x double>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %nxv64i1_nxv64f32 = uitofp <vscale x 64 x i1> undef to <vscale x 64 x float>
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %nxv64i1_nxv64f64 = uitofp <vscale x 64 x i1> undef to <vscale x 64 x double>
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %vp_nxv64fi8_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 103 for instruction: %vp_nxv64fi8_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %vp_nxv64fi16_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 102 for instruction: %vp_nxv64fi16_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %vp_nxv64fi32_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %vp_nxv64fi32_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %vp_nxv64fi64_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %vp_nxv64fi64_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %vp_nxv64fi1_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64D-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %vp_nxv64fi1_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64D-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVE64X-LABEL: 'uitofp'
@@ -5530,16 +3907,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i64_v2f64 = uitofp <2 x i64> undef to <2 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i1_v2f32 = uitofp <2 x i1> undef to <2 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i1_v2f64 = uitofp <2 x i1> undef to <2 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi8_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi8_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i8(<2 x i8> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi16_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi16_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi32_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi32_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi64_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi64_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi1_v2f32 = call <2 x float> @llvm.vp.uitofp.v2f32.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %vp_v2fi1_v2f64 = call <2 x double> @llvm.vp.uitofp.v2f64.v2i1(<2 x i1> undef, <2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i8_v4f32 = uitofp <4 x i8> undef to <4 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i8_v4f64 = uitofp <4 x i8> undef to <4 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i16_v4f32 = uitofp <4 x i16> undef to <4 x float>
@@ -5550,16 +3917,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i64_v4f64 = uitofp <4 x i64> undef to <4 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i1_v4f32 = uitofp <4 x i1> undef to <4 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %v4i1_v4f64 = uitofp <4 x i1> undef to <4 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi8_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi8_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i8(<4 x i8> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi16_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi16_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi32_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi32_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi64_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi64_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi1_v4f32 = call <4 x float> @llvm.vp.uitofp.v4f32.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %vp_v4fi1_v4f64 = call <4 x double> @llvm.vp.uitofp.v4f64.v4i1(<4 x i1> undef, <4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i8_v8f32 = uitofp <8 x i8> undef to <8 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i8_v8f64 = uitofp <8 x i8> undef to <8 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i16_v8f32 = uitofp <8 x i16> undef to <8 x float>
@@ -5570,16 +3927,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i64_v8f64 = uitofp <8 x i64> undef to <8 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i1_v8f32 = uitofp <8 x i1> undef to <8 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %v8i1_v8f64 = uitofp <8 x i1> undef to <8 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi8_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi8_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i8(<8 x i8> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi16_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi16_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi32_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi32_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi64_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi64_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi1_v8f32 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %vp_v8fi1_v8f64 = call <8 x double> @llvm.vp.uitofp.v8f64.v8i1(<8 x i1> undef, <8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i8_v16f32 = uitofp <16 x i8> undef to <16 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i8_v16f64 = uitofp <16 x i8> undef to <16 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i16_v16f32 = uitofp <16 x i16> undef to <16 x float>
@@ -5590,16 +3937,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i64_v16f64 = uitofp <16 x i64> undef to <16 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i1_v16f32 = uitofp <16 x i1> undef to <16 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %v16i1_v16f64 = uitofp <16 x i1> undef to <16 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi8_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi8_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i8(<16 x i8> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi16_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi16_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi32_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi32_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi64_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi64_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi1_v16f32 = call <16 x float> @llvm.vp.uitofp.v16f32.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %vp_v16fi1_v16f64 = call <16 x double> @llvm.vp.uitofp.v16f64.v16i1(<16 x i1> undef, <16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i8_v32f32 = uitofp <32 x i8> undef to <32 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i8_v32f64 = uitofp <32 x i8> undef to <32 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i16_v32f32 = uitofp <32 x i16> undef to <32 x float>
@@ -5610,16 +3947,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %v32i64_v32f64 = uitofp <32 x i64> undef to <32 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i1_v32f32 = uitofp <32 x i1> undef to <32 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %v32i1_v32f64 = uitofp <32 x i1> undef to <32 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi8_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi8_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i8(<32 x i8> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi16_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi16_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i16(<32 x i16> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi32_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi32_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i32(<32 x i32> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %vp_v32fi64_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %vp_v32fi64_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i64(<32 x i64> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi1_v32f32 = call <32 x float> @llvm.vp.uitofp.v32f32.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %vp_v32fi1_v32f64 = call <32 x double> @llvm.vp.uitofp.v32f64.v32i1(<32 x i1> undef, <32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i8_v64f32 = uitofp <64 x i8> undef to <64 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i8_v64f64 = uitofp <64 x i8> undef to <64 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i16_v64f32 = uitofp <64 x i16> undef to <64 x float>
@@ -5630,16 +3957,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %v64i64_v64f64 = uitofp <64 x i64> undef to <64 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i1_v64f32 = uitofp <64 x i1> undef to <64 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %v64i1_v64f64 = uitofp <64 x i1> undef to <64 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi8_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi8_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i8(<64 x i8> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi16_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi16_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i16(<64 x i16> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %vp_v64fi32_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %vp_v64fi32_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i32(<64 x i32> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %vp_v64fi64_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %vp_v64fi64_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i64(<64 x i64> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi1_v64f32 = call <64 x float> @llvm.vp.uitofp.v64f32.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %vp_v64fi1_v64f64 = call <64 x double> @llvm.vp.uitofp.v64f64.v64i1(<64 x i1> undef, <64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v128i8_v128f32 = uitofp <128 x i8> undef to <128 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v128i8_v128f64 = uitofp <128 x i8> undef to <128 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %v128i16_v128f32 = uitofp <128 x i16> undef to <128 x float>
@@ -5650,16 +3967,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %v128i64_v128f64 = uitofp <128 x i64> undef to <128 x double>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v128i1_v128f32 = uitofp <128 x i1> undef to <128 x float>
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %v128i1_v128f64 = uitofp <128 x i1> undef to <128 x double>
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v128fi8_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v128fi8_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i8(<128 x i8> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %vp_v128fi16_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 254 for instruction: %vp_v128fi16_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i16(<128 x i16> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 252 for instruction: %vp_v128fi32_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 252 for instruction: %vp_v128fi32_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i32(<128 x i32> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %vp_v128fi64_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %vp_v128fi64_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i64(<128 x i64> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v128fi1_v128f32 = call <128 x float> @llvm.vp.uitofp.v128f32.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Found an estimated cost of 255 for instruction: %vp_v128fi1_v128f64 = call <128 x double> @llvm.vp.uitofp.v128f64.v128i1(<128 x i1> undef, <128 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i8_nxv1f32 = uitofp <vscale x 1 x i8> undef to <vscale x 1 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i8_nxv1f64 = uitofp <vscale x 1 x i8> undef to <vscale x 1 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i16_nxv1f32 = uitofp <vscale x 1 x i16> undef to <vscale x 1 x float>
@@ -5670,16 +3977,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i64_nxv1f64 = uitofp <vscale x 1 x i64> undef to <vscale x 1 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i1_nxv1f32 = uitofp <vscale x 1 x i1> undef to <vscale x 1 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv1i1_nxv1f64 = uitofp <vscale x 1 x i1> undef to <vscale x 1 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi8_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi8_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi16_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi16_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi32_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi32_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi64_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi64_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi1_nxv1f32 = call <vscale x 1 x float> @llvm.vp.uitofp.nxv1f32.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv1fi1_nxv1f64 = call <vscale x 1 x double> @llvm.vp.uitofp.nxv1f64.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i8_nxv2f32 = uitofp <vscale x 2 x i8> undef to <vscale x 2 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i8_nxv2f64 = uitofp <vscale x 2 x i8> undef to <vscale x 2 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i16_nxv2f32 = uitofp <vscale x 2 x i16> undef to <vscale x 2 x float>
@@ -5690,16 +3987,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i64_nxv2f64 = uitofp <vscale x 2 x i64> undef to <vscale x 2 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i1_nxv2f32 = uitofp <vscale x 2 x i1> undef to <vscale x 2 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv2i1_nxv2f64 = uitofp <vscale x 2 x i1> undef to <vscale x 2 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi8_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi8_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi16_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi16_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi32_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi32_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi64_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi64_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi1_nxv2f32 = call <vscale x 2 x float> @llvm.vp.uitofp.nxv2f32.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv2fi1_nxv2f64 = call <vscale x 2 x double> @llvm.vp.uitofp.nxv2f64.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i8_nxv4f32 = uitofp <vscale x 4 x i8> undef to <vscale x 4 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i8_nxv4f64 = uitofp <vscale x 4 x i8> undef to <vscale x 4 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i16_nxv4f32 = uitofp <vscale x 4 x i16> undef to <vscale x 4 x float>
@@ -5710,16 +3997,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i64_nxv4f64 = uitofp <vscale x 4 x i64> undef to <vscale x 4 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i1_nxv4f32 = uitofp <vscale x 4 x i1> undef to <vscale x 4 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv4i1_nxv4f64 = uitofp <vscale x 4 x i1> undef to <vscale x 4 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi8_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi8_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi16_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi16_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi32_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi32_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi64_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi64_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi1_nxv4f32 = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv4fi1_nxv4f64 = call <vscale x 4 x double> @llvm.vp.uitofp.nxv4f64.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i8_nxv8f32 = uitofp <vscale x 8 x i8> undef to <vscale x 8 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i8_nxv8f64 = uitofp <vscale x 8 x i8> undef to <vscale x 8 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i16_nxv8f32 = uitofp <vscale x 8 x i16> undef to <vscale x 8 x float>
@@ -5730,16 +4007,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i64_nxv8f64 = uitofp <vscale x 8 x i64> undef to <vscale x 8 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i1_nxv8f32 = uitofp <vscale x 8 x i1> undef to <vscale x 8 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv8i1_nxv8f64 = uitofp <vscale x 8 x i1> undef to <vscale x 8 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi8_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi8_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi16_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi16_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi32_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi32_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi64_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi64_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi1_nxv8f32 = call <vscale x 8 x float> @llvm.vp.uitofp.nxv8f32.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv8fi1_nxv8f64 = call <vscale x 8 x double> @llvm.vp.uitofp.nxv8f64.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i8_nxv16f32 = uitofp <vscale x 16 x i8> undef to <vscale x 16 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i8_nxv16f64 = uitofp <vscale x 16 x i8> undef to <vscale x 16 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i16_nxv16f32 = uitofp <vscale x 16 x i16> undef to <vscale x 16 x float>
@@ -5750,16 +4017,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i64_nxv16f64 = uitofp <vscale x 16 x i64> undef to <vscale x 16 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i1_nxv16f32 = uitofp <vscale x 16 x i1> undef to <vscale x 16 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv16i1_nxv16f64 = uitofp <vscale x 16 x i1> undef to <vscale x 16 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi8_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi8_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi16_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi16_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi32_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi32_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi64_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi64_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi1_nxv16f32 = call <vscale x 16 x float> @llvm.vp.uitofp.nxv16f32.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv16fi1_nxv16f64 = call <vscale x 16 x double> @llvm.vp.uitofp.nxv16f64.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i8_nxv32f32 = uitofp <vscale x 32 x i8> undef to <vscale x 32 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i8_nxv32f64 = uitofp <vscale x 32 x i8> undef to <vscale x 32 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i16_nxv32f32 = uitofp <vscale x 32 x i16> undef to <vscale x 32 x float>
@@ -5770,16 +4027,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i64_nxv32f64 = uitofp <vscale x 32 x i64> undef to <vscale x 32 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i1_nxv32f32 = uitofp <vscale x 32 x i1> undef to <vscale x 32 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv32i1_nxv32f64 = uitofp <vscale x 32 x i1> undef to <vscale x 32 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi8_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi8_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi16_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi16_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi32_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi32_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi64_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi64_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi1_nxv32f32 = call <vscale x 32 x float> @llvm.vp.uitofp.nxv32f32.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv32fi1_nxv32f64 = call <vscale x 32 x double> @llvm.vp.uitofp.nxv32f64.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i8_nxv64f32 = uitofp <vscale x 64 x i8> undef to <vscale x 64 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i8_nxv64f64 = uitofp <vscale x 64 x i8> undef to <vscale x 64 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i16_nxv64f32 = uitofp <vscale x 64 x i16> undef to <vscale x 64 x float>
@@ -5790,16 +4037,6 @@ define void @uitofp() {
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i64_nxv64f64 = uitofp <vscale x 64 x i64> undef to <vscale x 64 x double>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i1_nxv64f32 = uitofp <vscale x 64 x i1> undef to <vscale x 64 x float>
; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %nxv64i1_nxv64f64 = uitofp <vscale x 64 x i1> undef to <vscale x 64 x double>
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi8_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi8_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi16_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi16_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi32_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi32_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi64_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi64_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi1_nxv64f32 = call <vscale x 64 x float> @llvm.vp.uitofp.nxv64f32.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
-; ZVE64X-NEXT: Cost Model: Invalid cost for instruction: %vp_nxv64fi1_nxv64f64 = call <vscale x 64 x double> @llvm.vp.uitofp.nxv64f64.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, i32 undef)
; ZVE64X-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8_v2f32 = uitofp <2 x i8> undef to <2 x float>
diff --git a/llvm/test/Analysis/CostModel/RISCV/cmp.ll b/llvm/test/Analysis/CostModel/RISCV/cmp.ll
index 793f0dd2fe049..d41c17745d849 100644
--- a/llvm/test/Analysis/CostModel/RISCV/cmp.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/cmp.ll
@@ -9,161 +9,81 @@ define void @icmp() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = icmp slt <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = icmp slt <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = icmp slt <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <2 x i1> @llvm.vp.icmp.v2i1(<2 x i1> undef, <2 x i1> undef, metadata !"slt", <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <2 x i1> @llvm.vp.icmp.v2i8(<2 x i8> undef, <2 x i8> undef, metadata !"slt", <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <2 x i1> @llvm.vp.icmp.v2i16(<2 x i16> undef, <2 x i16> undef, metadata !"slt", <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <2 x i1> @llvm.vp.icmp.v2i32(<2 x i32> undef, <2 x i32> undef, metadata !"slt", <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <2 x i1> @llvm.vp.icmp.v2i64(<2 x i64> undef, <2 x i64> undef, metadata !"slt", <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = icmp slt <4 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = icmp slt <4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = icmp slt <4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = icmp slt <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = icmp slt <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <4 x i1> @llvm.vp.icmp.v4i1(<4 x i1> undef, <4 x i1> undef, metadata !"slt", <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <4 x i1> @llvm.vp.icmp.v4i8(<4 x i8> undef, <4 x i8> undef, metadata !"slt", <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <4 x i1> @llvm.vp.icmp.v4i16(<4 x i16> undef, <4 x i16> undef, metadata !"slt", <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <4 x i1> @llvm.vp.icmp.v4i32(<4 x i32> undef, <4 x i32> undef, metadata !"slt", <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %20 = call <4 x i1> @llvm.vp.icmp.v4i64(<4 x i64> undef, <4 x i64> undef, metadata !"slt", <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = icmp slt <8 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = icmp slt <8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = icmp slt <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = icmp slt <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %25 = icmp slt <8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <8 x i1> @llvm.vp.icmp.v8i1(<8 x i1> undef, <8 x i1> undef, metadata !"slt", <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <8 x i1> @llvm.vp.icmp.v8i8(<8 x i8> undef, <8 x i8> undef, metadata !"slt", <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <8 x i1> @llvm.vp.icmp.v8i16(<8 x i16> undef, <8 x i16> undef, metadata !"slt", <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %29 = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> undef, <8 x i32> undef, metadata !"slt", <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %30 = call <8 x i1> @llvm.vp.icmp.v8i64(<8 x i64> undef, <8 x i64> undef, metadata !"slt", <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = icmp slt <16 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = icmp slt <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = icmp slt <16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = icmp slt <16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = icmp slt <16 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <16 x i1> @llvm.vp.icmp.v16i1(<16 x i1> undef, <16 x i1> undef, metadata !"slt", <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <16 x i1> @llvm.vp.icmp.v16i8(<16 x i8> undef, <16 x i8> undef, metadata !"slt", <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %38 = call <16 x i1> @llvm.vp.icmp.v16i16(<16 x i16> undef, <16 x i16> undef, metadata !"slt", <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %39 = call <16 x i1> @llvm.vp.icmp.v16i32(<16 x i32> undef, <16 x i32> undef, metadata !"slt", <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %40 = call <16 x i1> @llvm.vp.icmp.v16i64(<16 x i64> undef, <16 x i64> undef, metadata !"slt", <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %41 = icmp slt <32 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %42 = icmp slt <32 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %43 = icmp slt <32 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %44 = icmp slt <32 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %45 = icmp slt <32 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %46 = call <32 x i1> @llvm.vp.icmp.v32i1(<32 x i1> undef, <32 x i1> undef, metadata !"slt", <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %47 = call <32 x i1> @llvm.vp.icmp.v32i8(<32 x i8> undef, <32 x i8> undef, metadata !"slt", <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %48 = call <32 x i1> @llvm.vp.icmp.v32i16(<32 x i16> undef, <32 x i16> undef, metadata !"slt", <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %49 = call <32 x i1> @llvm.vp.icmp.v32i32(<32 x i32> undef, <32 x i32> undef, metadata !"slt", <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %50 = call <32 x i1> @llvm.vp.icmp.v32i64(<32 x i64> undef, <32 x i64> undef, metadata !"slt", <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %51 = icmp slt <64 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %52 = icmp slt <64 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %53 = icmp slt <64 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %54 = icmp slt <64 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %55 = icmp slt <64 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %56 = call <64 x i1> @llvm.vp.icmp.v64i1(<64 x i1> undef, <64 x i1> undef, metadata !"slt", <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %57 = call <64 x i1> @llvm.vp.icmp.v64i8(<64 x i8> undef, <64 x i8> undef, metadata !"slt", <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %58 = call <64 x i1> @llvm.vp.icmp.v64i16(<64 x i16> undef, <64 x i16> undef, metadata !"slt", <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %59 = call <64 x i1> @llvm.vp.icmp.v64i32(<64 x i32> undef, <64 x i32> undef, metadata !"slt", <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %60 = call <64 x i1> @llvm.vp.icmp.v64i64(<64 x i64> undef, <64 x i64> undef, metadata !"slt", <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %61 = icmp slt <128 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %62 = icmp slt <128 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %63 = icmp slt <128 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %64 = icmp slt <128 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %65 = icmp slt <128 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %66 = call <128 x i1> @llvm.vp.icmp.v128i1(<128 x i1> undef, <128 x i1> undef, metadata !"slt", <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %67 = call <128 x i1> @llvm.vp.icmp.v128i8(<128 x i8> undef, <128 x i8> undef, metadata !"slt", <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %68 = call <128 x i1> @llvm.vp.icmp.v128i16(<128 x i16> undef, <128 x i16> undef, metadata !"slt", <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %69 = call <128 x i1> @llvm.vp.icmp.v128i32(<128 x i32> undef, <128 x i32> undef, metadata !"slt", <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %70 = call <128 x i1> @llvm.vp.icmp.v128i64(<128 x i64> undef, <128 x i64> undef, metadata !"slt", <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %71 = icmp slt <256 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %72 = icmp slt <256 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %73 = icmp slt <256 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %74 = icmp slt <256 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %75 = icmp slt <256 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %76 = call <256 x i1> @llvm.vp.icmp.v256i1(<256 x i1> undef, <256 x i1> undef, metadata !"slt", <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %77 = call <256 x i1> @llvm.vp.icmp.v256i8(<256 x i8> undef, <256 x i8> undef, metadata !"slt", <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %78 = call <256 x i1> @llvm.vp.icmp.v256i16(<256 x i16> undef, <256 x i16> undef, metadata !"slt", <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %79 = call <256 x i1> @llvm.vp.icmp.v256i32(<256 x i32> undef, <256 x i32> undef, metadata !"slt", <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %80 = call <256 x i1> @llvm.vp.icmp.v256i64(<256 x i64> undef, <256 x i64> undef, metadata !"slt", <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %81 = icmp slt <vscale x 1 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %82 = icmp slt <vscale x 1 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %83 = icmp slt <vscale x 1 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %84 = icmp slt <vscale x 1 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %85 = icmp slt <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %86 = call <vscale x 1 x i1> @llvm.vp.icmp.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, metadata !"slt", <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %87 = call <vscale x 1 x i1> @llvm.vp.icmp.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, metadata !"slt", <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %88 = call <vscale x 1 x i1> @llvm.vp.icmp.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, metadata !"slt", <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %89 = call <vscale x 1 x i1> @llvm.vp.icmp.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, metadata !"slt", <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %90 = call <vscale x 1 x i1> @llvm.vp.icmp.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, metadata !"slt", <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %91 = icmp slt <vscale x 2 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %92 = icmp slt <vscale x 2 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %93 = icmp slt <vscale x 2 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %94 = icmp slt <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %95 = icmp slt <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %96 = call <vscale x 2 x i1> @llvm.vp.icmp.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, metadata !"slt", <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %97 = call <vscale x 2 x i1> @llvm.vp.icmp.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, metadata !"slt", <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %98 = call <vscale x 2 x i1> @llvm.vp.icmp.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, metadata !"slt", <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %99 = call <vscale x 2 x i1> @llvm.vp.icmp.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, metadata !"slt", <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %100 = call <vscale x 2 x i1> @llvm.vp.icmp.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, metadata !"slt", <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %101 = icmp slt <vscale x 4 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %102 = icmp slt <vscale x 4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %103 = icmp slt <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %104 = icmp slt <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %105 = icmp slt <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %106 = call <vscale x 4 x i1> @llvm.vp.icmp.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, metadata !"slt", <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %107 = call <vscale x 4 x i1> @llvm.vp.icmp.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, metadata !"slt", <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %108 = call <vscale x 4 x i1> @llvm.vp.icmp.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, metadata !"slt", <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %109 = call <vscale x 4 x i1> @llvm.vp.icmp.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, metadata !"slt", <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %110 = call <vscale x 4 x i1> @llvm.vp.icmp.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, metadata !"slt", <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %111 = icmp slt <vscale x 8 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %112 = icmp slt <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %113 = icmp slt <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %114 = icmp slt <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %115 = icmp slt <vscale x 8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %116 = call <vscale x 8 x i1> @llvm.vp.icmp.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, metadata !"slt", <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %117 = call <vscale x 8 x i1> @llvm.vp.icmp.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, metadata !"slt", <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %118 = call <vscale x 8 x i1> @llvm.vp.icmp.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, metadata !"slt", <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %119 = call <vscale x 8 x i1> @llvm.vp.icmp.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, metadata !"slt", <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %120 = call <vscale x 8 x i1> @llvm.vp.icmp.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, metadata !"slt", <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %121 = icmp slt <vscale x 16 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %122 = icmp slt <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %123 = icmp slt <vscale x 16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %124 = icmp slt <vscale x 16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %125 = icmp slt <vscale x 16 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %126 = call <vscale x 16 x i1> @llvm.vp.icmp.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, metadata !"slt", <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %127 = call <vscale x 16 x i1> @llvm.vp.icmp.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, metadata !"slt", <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %128 = call <vscale x 16 x i1> @llvm.vp.icmp.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, metadata !"slt", <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %129 = call <vscale x 16 x i1> @llvm.vp.icmp.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, metadata !"slt", <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %130 = call <vscale x 16 x i1> @llvm.vp.icmp.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, metadata !"slt", <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %131 = icmp slt <vscale x 32 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %132 = icmp slt <vscale x 32 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %133 = icmp slt <vscale x 32 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %134 = icmp slt <vscale x 32 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %135 = icmp slt <vscale x 32 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %136 = call <vscale x 32 x i1> @llvm.vp.icmp.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, metadata !"slt", <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %137 = call <vscale x 32 x i1> @llvm.vp.icmp.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, metadata !"slt", <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %138 = call <vscale x 32 x i1> @llvm.vp.icmp.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, metadata !"slt", <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %139 = call <vscale x 32 x i1> @llvm.vp.icmp.nxv32i32(<vscale x 32 x i32> undef, <vscale x 32 x i32> undef, metadata !"slt", <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %140 = call <vscale x 32 x i1> @llvm.vp.icmp.nxv32i64(<vscale x 32 x i64> undef, <vscale x 32 x i64> undef, metadata !"slt", <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %141 = icmp slt <vscale x 64 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %142 = icmp slt <vscale x 64 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %143 = icmp slt <vscale x 64 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %144 = icmp slt <vscale x 64 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %145 = icmp slt <vscale x 64 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %146 = call <vscale x 64 x i1> @llvm.vp.icmp.nxv64i1(<vscale x 64 x i1> undef, <vscale x 64 x i1> undef, metadata !"slt", <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %147 = call <vscale x 64 x i1> @llvm.vp.icmp.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, metadata !"slt", <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %148 = call <vscale x 64 x i1> @llvm.vp.icmp.nxv64i16(<vscale x 64 x i16> undef, <vscale x 64 x i16> undef, metadata !"slt", <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %149 = call <vscale x 64 x i1> @llvm.vp.icmp.nxv64i32(<vscale x 64 x i32> undef, <vscale x 64 x i32> undef, metadata !"slt", <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %150 = call <vscale x 64 x i1> @llvm.vp.icmp.nxv64i64(<vscale x 64 x i64> undef, <vscale x 64 x i64> undef, metadata !"slt", <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %151 = icmp slt <vscale x 128 x i1> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %152 = icmp slt <vscale x 128 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %153 = icmp slt <vscale x 128 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %154 = icmp slt <vscale x 128 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %155 = icmp slt <vscale x 128 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %156 = call <vscale x 128 x i1> @llvm.vp.icmp.nxv128i1(<vscale x 128 x i1> undef, <vscale x 128 x i1> undef, metadata !"slt", <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %157 = call <vscale x 128 x i1> @llvm.vp.icmp.nxv128i8(<vscale x 128 x i8> undef, <vscale x 128 x i8> undef, metadata !"slt", <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %158 = call <vscale x 128 x i1> @llvm.vp.icmp.nxv128i16(<vscale x 128 x i16> undef, <vscale x 128 x i16> undef, metadata !"slt", <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %159 = call <vscale x 128 x i1> @llvm.vp.icmp.nxv128i32(<vscale x 128 x i32> undef, <vscale x 128 x i32> undef, metadata !"slt", <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %160 = call <vscale x 128 x i1> @llvm.vp.icmp.nxv128i64(<vscale x 128 x i64> undef, <vscale x 128 x i64> undef, metadata !"slt", <vscale x 128 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = icmp slt <4 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = icmp slt <4 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = icmp slt <4 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = icmp slt <4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = icmp slt <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = icmp slt <8 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = icmp slt <8 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = icmp slt <8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = icmp slt <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %15 = icmp slt <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = icmp slt <16 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = icmp slt <16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = icmp slt <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %19 = icmp slt <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = icmp slt <16 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = icmp slt <32 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = icmp slt <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = icmp slt <32 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %24 = icmp slt <32 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %25 = icmp slt <32 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = icmp slt <64 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %27 = icmp slt <64 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = icmp slt <64 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %29 = icmp slt <64 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %30 = icmp slt <64 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = icmp slt <128 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %32 = icmp slt <128 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %33 = icmp slt <128 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %34 = icmp slt <128 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %35 = icmp slt <128 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %36 = icmp slt <256 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %37 = icmp slt <256 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %38 = icmp slt <256 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %39 = icmp slt <256 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %40 = icmp slt <256 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %41 = icmp slt <vscale x 1 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %42 = icmp slt <vscale x 1 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %43 = icmp slt <vscale x 1 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %44 = icmp slt <vscale x 1 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %45 = icmp slt <vscale x 1 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %46 = icmp slt <vscale x 2 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %47 = icmp slt <vscale x 2 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %48 = icmp slt <vscale x 2 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %49 = icmp slt <vscale x 2 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %50 = icmp slt <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %51 = icmp slt <vscale x 4 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %52 = icmp slt <vscale x 4 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %53 = icmp slt <vscale x 4 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %54 = icmp slt <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %55 = icmp slt <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %56 = icmp slt <vscale x 8 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %57 = icmp slt <vscale x 8 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %58 = icmp slt <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %59 = icmp slt <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %60 = icmp slt <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %61 = icmp slt <vscale x 16 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %62 = icmp slt <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %63 = icmp slt <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %64 = icmp slt <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %65 = icmp slt <vscale x 16 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %66 = icmp slt <vscale x 32 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %67 = icmp slt <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %68 = icmp slt <vscale x 32 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %69 = icmp slt <vscale x 32 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %70 = icmp slt <vscale x 32 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %71 = icmp slt <vscale x 64 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %72 = icmp slt <vscale x 64 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %73 = icmp slt <vscale x 64 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %74 = icmp slt <vscale x 64 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %75 = icmp slt <vscale x 64 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %76 = icmp slt <vscale x 128 x i1> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %77 = icmp slt <vscale x 128 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %78 = icmp slt <vscale x 128 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %79 = icmp slt <vscale x 128 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %80 = icmp slt <vscale x 128 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
icmp slt <2 x i1> undef, undef
@@ -349,68 +269,36 @@ define void @fcmp() {
; CHECK-LABEL: 'fcmp'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = fcmp olt <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = fcmp olt <2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <2 x i1> @llvm.vp.fcmp.v2f32(<2 x float> undef, <2 x float> undef, metadata !"olt", <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <2 x i1> @llvm.vp.fcmp.v2f64(<2 x double> undef, <2 x double> undef, metadata !"olt", <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = fcmp olt <4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = fcmp olt <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x i1> @llvm.vp.fcmp.v4f32(<4 x float> undef, <4 x float> undef, metadata !"olt", <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <4 x i1> @llvm.vp.fcmp.v4f64(<4 x double> undef, <4 x double> undef, metadata !"olt", <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = fcmp olt <8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %10 = fcmp olt <8 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float> undef, <8 x float> undef, metadata !"olt", <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %12 = call <8 x i1> @llvm.vp.fcmp.v8f64(<8 x double> undef, <8 x double> undef, metadata !"olt", <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %13 = fcmp olt <16 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %14 = fcmp olt <16 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %15 = call <16 x i1> @llvm.vp.fcmp.v16f32(<16 x float> undef, <16 x float> undef, metadata !"olt", <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %16 = call <16 x i1> @llvm.vp.fcmp.v16f64(<16 x double> undef, <16 x double> undef, metadata !"olt", <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %17 = fcmp olt <32 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %18 = fcmp olt <32 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %19 = call <32 x i1> @llvm.vp.fcmp.v32f32(<32 x float> undef, <32 x float> undef, metadata !"olt", <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %20 = call <32 x i1> @llvm.vp.fcmp.v32f64(<32 x double> undef, <32 x double> undef, metadata !"olt", <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %21 = fcmp olt <64 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %22 = fcmp olt <64 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %23 = call <64 x i1> @llvm.vp.fcmp.v64f32(<64 x float> undef, <64 x float> undef, metadata !"olt", <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %24 = call <64 x i1> @llvm.vp.fcmp.v64f64(<64 x double> undef, <64 x double> undef, metadata !"olt", <64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %25 = fcmp olt <128 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %26 = fcmp olt <128 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %27 = call <128 x i1> @llvm.vp.fcmp.v128f32(<128 x float> undef, <128 x float> undef, metadata !"olt", <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %28 = call <128 x i1> @llvm.vp.fcmp.v128f64(<128 x double> undef, <128 x double> undef, metadata !"olt", <128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %29 = fcmp olt <256 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %30 = fcmp olt <256 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %31 = call <256 x i1> @llvm.vp.fcmp.v256f32(<256 x float> undef, <256 x float> undef, metadata !"olt", <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %32 = call <256 x i1> @llvm.vp.fcmp.v256f64(<256 x double> undef, <256 x double> undef, metadata !"olt", <256 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = fcmp olt <vscale x 1 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = fcmp olt <vscale x 1 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 1 x i1> @llvm.vp.fcmp.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef, metadata !"olt", <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i1> @llvm.vp.fcmp.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef, metadata !"olt", <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = fcmp olt <vscale x 2 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %38 = fcmp olt <vscale x 2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 2 x i1> @llvm.vp.fcmp.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, metadata !"olt", <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %40 = call <vscale x 2 x i1> @llvm.vp.fcmp.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, metadata !"olt", <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %41 = fcmp olt <vscale x 4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %42 = fcmp olt <vscale x 4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %43 = call <vscale x 4 x i1> @llvm.vp.fcmp.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, metadata !"olt", <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %44 = call <vscale x 4 x i1> @llvm.vp.fcmp.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, metadata !"olt", <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %45 = fcmp olt <vscale x 8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %46 = fcmp olt <vscale x 8 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %47 = call <vscale x 8 x i1> @llvm.vp.fcmp.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, metadata !"olt", <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %48 = call <vscale x 8 x i1> @llvm.vp.fcmp.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, metadata !"olt", <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %49 = fcmp olt <vscale x 16 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %50 = fcmp olt <vscale x 16 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %51 = call <vscale x 16 x i1> @llvm.vp.fcmp.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, metadata !"olt", <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %52 = call <vscale x 16 x i1> @llvm.vp.fcmp.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, metadata !"olt", <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %53 = fcmp olt <vscale x 32 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %54 = fcmp olt <vscale x 32 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %55 = call <vscale x 32 x i1> @llvm.vp.fcmp.nxv32f32(<vscale x 32 x float> undef, <vscale x 32 x float> undef, metadata !"olt", <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %56 = call <vscale x 32 x i1> @llvm.vp.fcmp.nxv32f64(<vscale x 32 x double> undef, <vscale x 32 x double> undef, metadata !"olt", <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %57 = fcmp olt <vscale x 64 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %58 = fcmp olt <vscale x 64 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %59 = call <vscale x 64 x i1> @llvm.vp.fcmp.nxv64f32(<vscale x 64 x float> undef, <vscale x 64 x float> undef, metadata !"olt", <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %60 = call <vscale x 64 x i1> @llvm.vp.fcmp.nxv64f64(<vscale x 64 x double> undef, <vscale x 64 x double> undef, metadata !"olt", <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %61 = fcmp olt <vscale x 128 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %62 = fcmp olt <vscale x 128 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %63 = call <vscale x 128 x i1> @llvm.vp.fcmp.nxv128f32(<vscale x 128 x float> undef, <vscale x 128 x float> undef, metadata !"olt", <vscale x 128 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %64 = call <vscale x 128 x i1> @llvm.vp.fcmp.nxv128f64(<vscale x 128 x double> undef, <vscale x 128 x double> undef, metadata !"olt", <vscale x 128 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = fcmp olt <4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = fcmp olt <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = fcmp olt <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %6 = fcmp olt <8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %7 = fcmp olt <16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %8 = fcmp olt <16 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %9 = fcmp olt <32 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %10 = fcmp olt <32 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %11 = fcmp olt <64 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %12 = fcmp olt <64 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %13 = fcmp olt <128 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %14 = fcmp olt <128 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %15 = fcmp olt <256 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %16 = fcmp olt <256 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = fcmp olt <vscale x 1 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = fcmp olt <vscale x 1 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = fcmp olt <vscale x 2 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %20 = fcmp olt <vscale x 2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = fcmp olt <vscale x 4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %22 = fcmp olt <vscale x 4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = fcmp olt <vscale x 8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %24 = fcmp olt <vscale x 8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %25 = fcmp olt <vscale x 16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %26 = fcmp olt <vscale x 16 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %27 = fcmp olt <vscale x 32 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %28 = fcmp olt <vscale x 32 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %29 = fcmp olt <vscale x 64 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %30 = fcmp olt <vscale x 64 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %31 = fcmp olt <vscale x 128 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %32 = fcmp olt <vscale x 128 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
fcmp olt <2 x float> undef, undef
diff --git a/llvm/test/Analysis/CostModel/RISCV/fround.ll b/llvm/test/Analysis/CostModel/RISCV/fround.ll
index 235728980cd46..ebf1066dcfb75 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fround.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fround.ll
@@ -1269,32 +1269,32 @@ define void @roundeven_fp16() {
define void @vp_ceil() {
; CHECK-LABEL: 'vp_ceil'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.vp.ceil.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.vp.ceil.v4bf16(<4 x bfloat> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.vp.ceil.v8bf16(<8 x bfloat> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.vp.ceil.v16bf16(<16 x bfloat> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.vp.ceil.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.vp.ceil.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.vp.ceil.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.vp.ceil.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.vp.ceil.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.vp.ceil.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.vp.ceil.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.vp.ceil.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.vp.ceil.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.vp.ceil.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.vp.ceil.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.vp.ceil.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.vp.ceil.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.vp.ceil.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.vp.ceil.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.ceil.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.ceil.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.ceil.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.ceil.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.ceil.nxv1bf16(<vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.ceil.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.ceil.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.ceil.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.ceil.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.ceil.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.ceil.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.ceil.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x bfloat> @llvm.vp.ceil.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
@@ -1328,27 +1328,27 @@ define void @vp_ceil() {
define void @vp_ceil_f16() {
; ZVFH-LABEL: 'vp_ceil_f16'
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.vp.ceil.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.vp.ceil.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.vp.ceil.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.vp.ceil.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.ceil.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.ceil.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.ceil.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.ceil.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.ceil.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.ceil.v2f16(<2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.ceil.v4f16(<4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.ceil.v8f16(<8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.ceil.v16f16(<16 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.ceil.nxv1f16(<vscale x 1 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.ceil.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.ceil.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.ceil.nxv16f16(<vscale x 16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'vp_ceil_f16'
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.vp.ceil.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.vp.ceil.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.vp.ceil.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.vp.ceil.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.ceil.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.ceil.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.ceil.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.ceil.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.ceil.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.ceil.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.ceil.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.ceil.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.ceil.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.ceil.nxv1f16(<vscale x 1 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.ceil.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.ceil.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.ceil.nxv16f16(<vscale x 16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x half> @llvm.vp.ceil.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
@@ -1365,32 +1365,32 @@ define void @vp_ceil_f16() {
define void @vp_floor() {
; CHECK-LABEL: 'vp_floor'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.vp.floor.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.vp.floor.v4bf16(<4 x bfloat> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.vp.floor.v8bf16(<8 x bfloat> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.vp.floor.v16bf16(<16 x bfloat> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.vp.floor.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.vp.floor.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.vp.floor.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.vp.floor.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.vp.floor.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.vp.floor.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.vp.floor.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.vp.floor.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.vp.floor.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.vp.floor.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.vp.floor.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.vp.floor.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.vp.floor.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.vp.floor.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.vp.floor.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.vp.floor.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.vp.floor.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.vp.floor.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.vp.floor.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.vp.floor.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.vp.floor.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.vp.floor.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.floor.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.floor.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.floor.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.floor.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.floor.nxv1bf16(<vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.floor.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.floor.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.floor.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.floor.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.floor.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.floor.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.floor.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.floor.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x bfloat> @llvm.vp.floor.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
@@ -1424,27 +1424,27 @@ define void @vp_floor() {
define void @vp_floor_f16() {
; ZVFH-LABEL: 'vp_floor_f16'
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.vp.floor.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.vp.floor.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.vp.floor.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.vp.floor.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.floor.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.floor.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.floor.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.floor.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.floor.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.floor.v2f16(<2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.floor.v4f16(<4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.floor.v8f16(<8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.floor.v16f16(<16 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.floor.nxv1f16(<vscale x 1 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.floor.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.floor.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.floor.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.floor.nxv16f16(<vscale x 16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'vp_floor_f16'
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.vp.floor.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.vp.floor.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.vp.floor.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.vp.floor.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.floor.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.floor.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.floor.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.floor.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.floor.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.floor.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.floor.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.floor.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.floor.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.floor.nxv1f16(<vscale x 1 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.floor.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.floor.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.floor.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.floor.nxv16f16(<vscale x 16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x half> @llvm.vp.floor.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
@@ -1461,32 +1461,32 @@ define void @vp_floor_f16() {
define void @vp_round() {
; CHECK-LABEL: 'vp_round'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.vp.round.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.vp.round.v4bf16(<4 x bfloat> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.vp.round.v8bf16(<8 x bfloat> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.vp.round.v16bf16(<16 x bfloat> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.vp.round.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.vp.round.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.vp.round.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.vp.round.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.vp.round.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.vp.round.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.vp.round.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.vp.round.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.vp.round.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.vp.round.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.vp.round.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.vp.round.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.vp.round.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.vp.round.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.vp.round.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.vp.round.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.vp.round.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.vp.round.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.vp.round.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.vp.round.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.vp.round.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.vp.round.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.round.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.round.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.round.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.round.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.round.nxv1bf16(<vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.round.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.round.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.round.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.round.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.round.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.round.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.round.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.round.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.round.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x bfloat> @llvm.vp.round.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
@@ -1520,27 +1520,27 @@ define void @vp_round() {
define void @vp_round_f16() {
; ZVFH-LABEL: 'vp_round_f16'
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.vp.round.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.vp.round.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.vp.round.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.vp.round.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.round.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.round.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.round.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.round.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.round.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.round.v2f16(<2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.round.v4f16(<4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.round.v8f16(<8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.round.v16f16(<16 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.round.nxv1f16(<vscale x 1 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.round.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.round.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.round.nxv16f16(<vscale x 16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'vp_round_f16'
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.vp.round.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.vp.round.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.vp.round.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.vp.round.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.round.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.round.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.round.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.round.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.round.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.round.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.round.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.round.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.round.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.round.nxv1f16(<vscale x 1 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.round.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.round.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.round.nxv16f16(<vscale x 16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x half> @llvm.vp.round.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
@@ -1557,32 +1557,32 @@ define void @vp_round_f16() {
define void @vp_roundeven() {
; CHECK-LABEL: 'vp_roundeven'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.vp.roundeven.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.vp.roundeven.v4bf16(<4 x bfloat> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.vp.roundeven.v8bf16(<8 x bfloat> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.vp.roundeven.v16bf16(<16 x bfloat> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.vp.roundeven.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.vp.roundeven.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.vp.roundeven.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.vp.roundeven.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.vp.roundeven.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.vp.roundeven.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.vp.roundeven.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.vp.roundeven.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.vp.roundeven.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.vp.roundeven.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.vp.roundeven.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.vp.roundeven.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.vp.roundeven.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.vp.roundeven.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.vp.roundeven.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.vp.roundeven.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.vp.roundeven.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.vp.roundeven.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.vp.roundeven.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.vp.roundeven.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.vp.roundeven.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.vp.roundeven.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.roundeven.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.roundeven.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.roundeven.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.roundeven.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.roundeven.nxv1bf16(<vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.roundeven.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.roundeven.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.roundeven.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.roundeven.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.roundeven.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.roundeven.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.roundeven.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.roundeven.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.roundeven.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.roundeven.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.roundeven.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.roundeven.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.roundeven.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.roundeven.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.roundeven.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.roundeven.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.roundeven.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.roundeven.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x bfloat> @llvm.vp.roundeven.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
@@ -1616,27 +1616,27 @@ define void @vp_roundeven() {
define void @vp_roundeven_f16() {
; ZVFH-LABEL: 'vp_roundeven_f16'
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.vp.roundeven.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.vp.roundeven.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.vp.roundeven.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.vp.roundeven.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.roundeven.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.roundeven.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.roundeven.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.roundeven.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.roundeven.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.roundeven.v2f16(<2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.roundeven.v4f16(<4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.roundeven.v8f16(<8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.roundeven.v16f16(<16 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.roundeven.nxv1f16(<vscale x 1 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.roundeven.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.roundeven.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.roundeven.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.roundeven.nxv16f16(<vscale x 16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'vp_roundeven_f16'
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.vp.roundeven.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.vp.roundeven.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.vp.roundeven.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.vp.roundeven.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.roundeven.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.roundeven.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.roundeven.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.roundeven.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.roundeven.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.roundeven.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.roundeven.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.roundeven.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.roundeven.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.roundeven.nxv1f16(<vscale x 1 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.roundeven.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.roundeven.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.roundeven.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.roundeven.nxv16f16(<vscale x 16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x half> @llvm.vp.roundeven.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
@@ -1653,32 +1653,32 @@ define void @vp_roundeven_f16() {
define void @vp_roundtozero() {
; CHECK-LABEL: 'vp_roundtozero'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.vp.roundtozero.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.vp.roundtozero.v4bf16(<4 x bfloat> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.vp.roundtozero.v8bf16(<8 x bfloat> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.vp.roundtozero.v16bf16(<16 x bfloat> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.vp.roundtozero.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.vp.roundtozero.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.vp.roundtozero.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.vp.roundtozero.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.vp.roundtozero.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x float> @llvm.vp.roundtozero.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x float> @llvm.vp.roundtozero.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x float> @llvm.vp.roundtozero.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x float> @llvm.vp.roundtozero.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x float> @llvm.vp.roundtozero.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x float> @llvm.vp.roundtozero.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x float> @llvm.vp.roundtozero.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x float> @llvm.vp.roundtozero.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 16 x float> @llvm.vp.roundtozero.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <2 x double> @llvm.vp.roundtozero.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %20 = call <4 x double> @llvm.vp.roundtozero.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %21 = call <8 x double> @llvm.vp.roundtozero.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <16 x double> @llvm.vp.roundtozero.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <vscale x 1 x double> @llvm.vp.roundtozero.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <vscale x 2 x double> @llvm.vp.roundtozero.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %25 = call <vscale x 4 x double> @llvm.vp.roundtozero.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 8 x double> @llvm.vp.roundtozero.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.trunc.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.trunc.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.trunc.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.trunc.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.trunc.nxv1bf16(<vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.trunc.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.trunc.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.trunc.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.trunc.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x float> @llvm.trunc.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x float> @llvm.trunc.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x float> @llvm.trunc.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %20 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %21 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <vscale x 1 x double> @llvm.trunc.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %25 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x bfloat> @llvm.vp.roundtozero.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
@@ -1712,27 +1712,27 @@ define void @vp_roundtozero() {
define void @vp_roundtozero_f16() {
; ZVFH-LABEL: 'vp_roundtozero_f16'
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.vp.roundtozero.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.vp.roundtozero.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.vp.roundtozero.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.vp.roundtozero.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.roundtozero.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.roundtozero.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.roundtozero.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.roundtozero.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.roundtozero.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.trunc.v2f16(<2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.trunc.v4f16(<4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.trunc.v8f16(<8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.trunc.v16f16(<16 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.trunc.nxv1f16(<vscale x 1 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.trunc.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.trunc.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.trunc.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.trunc.nxv16f16(<vscale x 16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'vp_roundtozero_f16'
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.vp.roundtozero.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.vp.roundtozero.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.vp.roundtozero.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.vp.roundtozero.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.roundtozero.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.roundtozero.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.roundtozero.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.roundtozero.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.roundtozero.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.trunc.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.trunc.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.trunc.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.trunc.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.trunc.nxv1f16(<vscale x 1 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.trunc.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.trunc.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.trunc.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.trunc.nxv16f16(<vscale x 16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x half> @llvm.vp.roundtozero.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
@@ -1749,32 +1749,32 @@ define void @vp_roundtozero_f16() {
define void @vp_rint() {
; CHECK-LABEL: 'vp_rint'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.vp.rint.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.vp.rint.v4bf16(<4 x bfloat> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.vp.rint.v8bf16(<8 x bfloat> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.vp.rint.v16bf16(<16 x bfloat> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.vp.rint.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.vp.rint.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.vp.rint.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.vp.rint.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.vp.rint.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x float> @llvm.vp.rint.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x float> @llvm.vp.rint.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x float> @llvm.vp.rint.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x float> @llvm.vp.rint.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x float> @llvm.vp.rint.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x float> @llvm.vp.rint.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x float> @llvm.vp.rint.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x float> @llvm.vp.rint.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 16 x float> @llvm.vp.rint.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <2 x double> @llvm.vp.rint.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %20 = call <4 x double> @llvm.vp.rint.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %21 = call <8 x double> @llvm.vp.rint.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <16 x double> @llvm.vp.rint.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <vscale x 1 x double> @llvm.vp.rint.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <vscale x 2 x double> @llvm.vp.rint.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %25 = call <vscale x 4 x double> @llvm.vp.rint.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 8 x double> @llvm.vp.rint.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.rint.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.rint.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.rint.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.rint.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.rint.nxv1bf16(<vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.rint.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.rint.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.rint.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.rint.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x float> @llvm.rint.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x float> @llvm.rint.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x float> @llvm.rint.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x float> @llvm.rint.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 16 x float> @llvm.rint.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %20 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %21 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <16 x double> @llvm.rint.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <vscale x 1 x double> @llvm.rint.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %25 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 8 x double> @llvm.rint.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x bfloat> @llvm.vp.rint.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
@@ -1808,27 +1808,27 @@ define void @vp_rint() {
define void @vp_rint_f16() {
; ZVFH-LABEL: 'vp_rint_f16'
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.vp.rint.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.vp.rint.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.vp.rint.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.vp.rint.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.rint.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.rint.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.rint.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.rint.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.rint.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.rint.v2f16(<2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.rint.v4f16(<4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.rint.v8f16(<8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.rint.v16f16(<16 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.rint.nxv1f16(<vscale x 1 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.rint.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.rint.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.rint.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.rint.nxv16f16(<vscale x 16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'vp_rint_f16'
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.vp.rint.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.vp.rint.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.vp.rint.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.vp.rint.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.rint.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.rint.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.rint.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.rint.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.rint.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.rint.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.rint.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.rint.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.rint.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.rint.nxv1f16(<vscale x 1 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.rint.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.rint.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.rint.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.rint.nxv16f16(<vscale x 16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x half> @llvm.vp.rint.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
@@ -1845,32 +1845,32 @@ define void @vp_rint_f16() {
define void @vp_nearbyint() {
; CHECK-LABEL: 'vp_nearbyint'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.vp.nearbyint.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.vp.nearbyint.v4bf16(<4 x bfloat> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.vp.nearbyint.v8bf16(<8 x bfloat> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.vp.nearbyint.v16bf16(<16 x bfloat> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.vp.nearbyint.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.vp.nearbyint.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.vp.nearbyint.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.vp.nearbyint.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.vp.nearbyint.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.vp.nearbyint.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.vp.nearbyint.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.vp.nearbyint.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.vp.nearbyint.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.vp.nearbyint.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.vp.nearbyint.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.vp.nearbyint.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.vp.nearbyint.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.vp.nearbyint.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.vp.nearbyint.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.vp.nearbyint.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.vp.nearbyint.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.vp.nearbyint.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.vp.nearbyint.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.vp.nearbyint.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.vp.nearbyint.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.vp.nearbyint.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x bfloat> @llvm.nearbyint.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x bfloat> @llvm.nearbyint.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x bfloat> @llvm.nearbyint.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x bfloat> @llvm.nearbyint.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x bfloat> @llvm.nearbyint.nxv1bf16(<vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.nearbyint.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.nearbyint.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.nearbyint.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.nearbyint.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <2 x float> @llvm.nearbyint.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %11 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <vscale x 1 x float> @llvm.nearbyint.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 2 x float> @llvm.nearbyint.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 8 x float> @llvm.nearbyint.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 16 x float> @llvm.nearbyint.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %20 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %21 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %22 = call <16 x double> @llvm.nearbyint.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %23 = call <vscale x 1 x double> @llvm.nearbyint.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %24 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %25 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %26 = call <vscale x 8 x double> @llvm.nearbyint.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x bfloat> @llvm.vp.nearbyint.v2bf16(<2 x bfloat> undef, <2 x i1> undef, i32 undef)
@@ -1904,27 +1904,27 @@ define void @vp_nearbyint() {
define void @vp_nearbyint_f16() {
; ZVFH-LABEL: 'vp_nearbyint_f16'
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.vp.nearbyint.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.vp.nearbyint.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.vp.nearbyint.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.vp.nearbyint.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.nearbyint.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.nearbyint.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.nearbyint.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.nearbyint.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.nearbyint.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x half> @llvm.nearbyint.v2f16(<2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x half> @llvm.nearbyint.v4f16(<4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x half> @llvm.nearbyint.v8f16(<8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x half> @llvm.nearbyint.v16f16(<16 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 1 x half> @llvm.nearbyint.nxv1f16(<vscale x 1 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x half> @llvm.nearbyint.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x half> @llvm.nearbyint.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.nearbyint.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x half> @llvm.nearbyint.nxv16f16(<vscale x 16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'vp_nearbyint_f16'
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.vp.nearbyint.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.vp.nearbyint.v4f16(<4 x half> undef, <4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.vp.nearbyint.v8f16(<8 x half> undef, <8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.vp.nearbyint.v16f16(<16 x half> undef, <16 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.vp.nearbyint.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.vp.nearbyint.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.vp.nearbyint.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.vp.nearbyint.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> undef, i32 undef)
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.vp.nearbyint.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x i1> undef, i32 undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x half> @llvm.nearbyint.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x half> @llvm.nearbyint.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x half> @llvm.nearbyint.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x half> @llvm.nearbyint.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x half> @llvm.nearbyint.nxv1f16(<vscale x 1 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.nearbyint.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.nearbyint.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.nearbyint.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.nearbyint.nxv16f16(<vscale x 16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x half> @llvm.vp.nearbyint.v2f16(<2 x half> undef, <2 x i1> undef, i32 undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
index fe24594d806af..47d80c2c857f3 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
@@ -543,33 +543,33 @@ define void @ctpop() {
define void @vp_bswap() {
; CHECK-LABEL: 'vp_bswap'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %1 = call <2 x i16> @llvm.vp.bswap.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %2 = call <4 x i16> @llvm.vp.bswap.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %3 = call <8 x i16> @llvm.vp.bswap.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %4 = call <16 x i16> @llvm.vp.bswap.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %5 = call <vscale x 1 x i16> @llvm.vp.bswap.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x i16> @llvm.vp.bswap.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x i16> @llvm.vp.bswap.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.bswap.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.bswap.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %10 = call <2 x i32> @llvm.vp.bswap.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %12 = call <8 x i32> @llvm.vp.bswap.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %13 = call <16 x i32> @llvm.vp.bswap.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %14 = call <vscale x 1 x i32> @llvm.vp.bswap.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x i32> @llvm.vp.bswap.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %16 = call <vscale x 4 x i32> @llvm.vp.bswap.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %17 = call <vscale x 8 x i32> @llvm.vp.bswap.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %18 = call <vscale x 16 x i32> @llvm.vp.bswap.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %19 = call <2 x i64> @llvm.vp.bswap.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %20 = call <4 x i64> @llvm.vp.bswap.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %21 = call <8 x i64> @llvm.vp.bswap.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %22 = call <16 x i64> @llvm.vp.bswap.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %23 = call <vscale x 1 x i64> @llvm.vp.bswap.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %24 = call <vscale x 2 x i64> @llvm.vp.bswap.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %25 = call <vscale x 4 x i64> @llvm.vp.bswap.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %26 = call <vscale x 8 x i64> @llvm.vp.bswap.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %27 = call <vscale x 16 x i64> @llvm.vp.bswap.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %1 = call <2 x i16> @llvm.bswap.v2i16(<2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %2 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %3 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %4 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %5 = call <vscale x 1 x i16> @llvm.bswap.nxv1i16(<vscale x 1 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x i16> @llvm.bswap.nxv2i16(<vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x i16> @llvm.bswap.nxv4i16(<vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %8 = call <vscale x 8 x i16> @llvm.bswap.nxv8i16(<vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %9 = call <vscale x 16 x i16> @llvm.bswap.nxv16i16(<vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %10 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %12 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %13 = call <16 x i32> @llvm.bswap.v16i32(<16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %14 = call <vscale x 1 x i32> @llvm.bswap.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x i32> @llvm.bswap.nxv2i32(<vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %16 = call <vscale x 4 x i32> @llvm.bswap.nxv4i32(<vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %17 = call <vscale x 8 x i32> @llvm.bswap.nxv8i32(<vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %18 = call <vscale x 16 x i32> @llvm.bswap.nxv16i32(<vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %19 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %20 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %21 = call <8 x i64> @llvm.bswap.v8i64(<8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %22 = call <16 x i64> @llvm.bswap.v16i64(<16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %23 = call <vscale x 1 x i64> @llvm.bswap.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %24 = call <vscale x 2 x i64> @llvm.bswap.nxv2i64(<vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %25 = call <vscale x 4 x i64> @llvm.bswap.nxv4i64(<vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %26 = call <vscale x 8 x i64> @llvm.bswap.nxv8i64(<vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %27 = call <vscale x 16 x i64> @llvm.bswap.nxv16i64(<vscale x 16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i16> @llvm.vp.bswap.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
@@ -603,44 +603,83 @@ define void @vp_bswap() {
}
define void @vp_ctpop() {
-; CHECK-LABEL: 'vp_ctpop'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %1 = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %2 = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %3 = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %4 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %5 = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %10 = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %11 = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %12 = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %13 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %14 = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %15 = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %19 = call <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %20 = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %21 = call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %22 = call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %23 = call <vscale x 1 x i32> @llvm.vp.ctpop.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %24 = call <vscale x 2 x i32> @llvm.vp.ctpop.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %25 = call <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %28 = call <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %29 = call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %30 = call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %31 = call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %32 = call <vscale x 1 x i64> @llvm.vp.ctpop.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %33 = call <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %34 = call <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %35 = call <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %36 = call <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; NOZVBB-LABEL: 'vp_ctpop'
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %1 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %2 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %3 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %4 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %5 = call <vscale x 1 x i16> @llvm.ctpop.nxv1i16(<vscale x 1 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %10 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %11 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %12 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %13 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %14 = call <vscale x 1 x i16> @llvm.ctpop.nxv1i16(<vscale x 1 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %15 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %19 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %20 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %21 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %22 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %23 = call <vscale x 1 x i32> @llvm.ctpop.nxv1i32(<vscale x 1 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %24 = call <vscale x 2 x i32> @llvm.ctpop.nxv2i32(<vscale x 2 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %25 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %28 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %29 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %30 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %31 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %32 = call <vscale x 1 x i64> @llvm.ctpop.nxv1i64(<vscale x 1 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %33 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %34 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %35 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %36 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVBB-LABEL: 'vp_ctpop'
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x i16> @llvm.ctpop.nxv1i16(<vscale x 1 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 1 x i16> @llvm.ctpop.nxv1i16(<vscale x 1 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %22 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <vscale x 1 x i32> @llvm.ctpop.nxv1i32(<vscale x 1 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.ctpop.nxv2i32(<vscale x 2 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %29 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %30 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %31 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <vscale x 1 x i64> @llvm.ctpop.nxv1i64(<vscale x 1 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %36 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
@@ -682,57 +721,109 @@ define void @vp_ctpop() {
}
define void @vp_ctlz() {
-; CHECK-LABEL: 'vp_ctlz'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %1 = call <2 x i8> @llvm.vp.ctlz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %2 = call <4 x i8> @llvm.vp.ctlz.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %3 = call <8 x i8> @llvm.vp.ctlz.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %4 = call <16 x i8> @llvm.vp.ctlz.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %5 = call <vscale x 1 x i8> @llvm.vp.ctlz.nxv1i8(<vscale x 1 x i8> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.ctlz.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.ctlz.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.ctlz.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %12 = call <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %13 = call <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %14 = call <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %15 = call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %22 = call <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %23 = call <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %24 = call <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %25 = call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %26 = call <vscale x 1 x i16> @llvm.vp.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %27 = call <vscale x 2 x i16> @llvm.vp.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %28 = call <vscale x 4 x i16> @llvm.vp.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %29 = call <vscale x 8 x i16> @llvm.vp.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %30 = call <vscale x 16 x i16> @llvm.vp.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %31 = call <vscale x 32 x i16> @llvm.vp.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %32 = call <2 x i32> @llvm.vp.ctlz.v2i32(<2 x i32> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %33 = call <4 x i32> @llvm.vp.ctlz.v4i32(<4 x i32> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %34 = call <8 x i32> @llvm.vp.ctlz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %35 = call <16 x i32> @llvm.vp.ctlz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %36 = call <vscale x 1 x i32> @llvm.vp.ctlz.nxv1i32(<vscale x 1 x i32> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %37 = call <vscale x 2 x i32> @llvm.vp.ctlz.nxv2i32(<vscale x 2 x i32> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %38 = call <vscale x 4 x i32> @llvm.vp.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %39 = call <vscale x 8 x i32> @llvm.vp.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %40 = call <vscale x 16 x i32> @llvm.vp.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %41 = call <2 x i64> @llvm.vp.ctlz.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %42 = call <4 x i64> @llvm.vp.ctlz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %43 = call <8 x i64> @llvm.vp.ctlz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %44 = call <16 x i64> @llvm.vp.ctlz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %45 = call <vscale x 1 x i64> @llvm.vp.ctlz.nxv1i64(<vscale x 1 x i64> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %46 = call <vscale x 2 x i64> @llvm.vp.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %47 = call <vscale x 4 x i64> @llvm.vp.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %48 = call <vscale x 8 x i64> @llvm.vp.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %49 = call <vscale x 16 x i64> @llvm.vp.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; NOZVBB-LABEL: 'vp_ctlz'
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %1 = call <2 x i8> @llvm.ctlz.v2i8(<2 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %2 = call <4 x i8> @llvm.ctlz.v4i8(<4 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %3 = call <8 x i8> @llvm.ctlz.v8i8(<8 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %4 = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %5 = call <vscale x 1 x i8> @llvm.ctlz.nxv1i8(<vscale x 1 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i8> @llvm.ctlz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i8> @llvm.ctlz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i8> @llvm.ctlz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i8> @llvm.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %10 = call <vscale x 32 x i8> @llvm.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %11 = call <vscale x 64 x i8> @llvm.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %12 = call <2 x i16> @llvm.ctlz.v2i16(<2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %13 = call <4 x i16> @llvm.ctlz.v4i16(<4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %14 = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %15 = call <16 x i16> @llvm.ctlz.v16i16(<16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %16 = call <vscale x 1 x i16> @llvm.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %17 = call <vscale x 2 x i16> @llvm.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %18 = call <vscale x 4 x i16> @llvm.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %21 = call <vscale x 32 x i16> @llvm.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %22 = call <2 x i16> @llvm.ctlz.v2i16(<2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %23 = call <4 x i16> @llvm.ctlz.v4i16(<4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %24 = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %25 = call <16 x i16> @llvm.ctlz.v16i16(<16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %26 = call <vscale x 1 x i16> @llvm.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %27 = call <vscale x 2 x i16> @llvm.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %28 = call <vscale x 4 x i16> @llvm.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %29 = call <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %30 = call <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %31 = call <vscale x 32 x i16> @llvm.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %32 = call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %33 = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %34 = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %35 = call <16 x i32> @llvm.ctlz.v16i32(<16 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %36 = call <vscale x 1 x i32> @llvm.ctlz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %37 = call <vscale x 2 x i32> @llvm.ctlz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %38 = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %39 = call <vscale x 8 x i32> @llvm.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %40 = call <vscale x 16 x i32> @llvm.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %41 = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %42 = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %43 = call <8 x i64> @llvm.ctlz.v8i64(<8 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %44 = call <16 x i64> @llvm.ctlz.v16i64(<16 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %45 = call <vscale x 1 x i64> @llvm.ctlz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %46 = call <vscale x 2 x i64> @llvm.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %47 = call <vscale x 4 x i64> @llvm.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %48 = call <vscale x 8 x i64> @llvm.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %49 = call <vscale x 16 x i64> @llvm.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVBB-LABEL: 'vp_ctlz'
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x i8> @llvm.ctlz.v2i8(<2 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x i8> @llvm.ctlz.v4i8(<4 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x i8> @llvm.ctlz.v8i8(<8 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x i8> @llvm.ctlz.nxv1i8(<vscale x 1 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.ctlz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.ctlz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.ctlz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %10 = call <vscale x 32 x i8> @llvm.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call <vscale x 64 x i8> @llvm.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.ctlz.v2i16(<2 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.ctlz.v4i16(<4 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i16> @llvm.ctlz.v16i16(<16 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %21 = call <vscale x 32 x i16> @llvm.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i16> @llvm.ctlz.v2i16(<2 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i16> @llvm.ctlz.v4i16(<4 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <16 x i16> @llvm.ctlz.v16i16(<16 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i16> @llvm.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i16> @llvm.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i16> @llvm.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %29 = call <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %30 = call <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %31 = call <vscale x 32 x i16> @llvm.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %35 = call <16 x i32> @llvm.ctlz.v16i32(<16 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i32> @llvm.ctlz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i32> @llvm.ctlz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %38 = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %39 = call <vscale x 8 x i32> @llvm.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %40 = call <vscale x 16 x i32> @llvm.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %41 = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %42 = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %43 = call <8 x i64> @llvm.ctlz.v8i64(<8 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %44 = call <16 x i64> @llvm.ctlz.v16i64(<16 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %45 = call <vscale x 1 x i64> @llvm.ctlz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %46 = call <vscale x 2 x i64> @llvm.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %47 = call <vscale x 4 x i64> @llvm.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %48 = call <vscale x 8 x i64> @llvm.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %49 = call <vscale x 16 x i64> @llvm.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.ctlz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
call <4 x i8> @llvm.vp.ctlz.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
@@ -787,57 +878,109 @@ define void @vp_ctlz() {
}
define void @vp_cttz() {
-; CHECK-LABEL: 'vp_cttz'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %1 = call <2 x i8> @llvm.vp.cttz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %2 = call <4 x i8> @llvm.vp.cttz.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %3 = call <8 x i8> @llvm.vp.cttz.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %4 = call <16 x i8> @llvm.vp.cttz.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %5 = call <vscale x 1 x i8> @llvm.vp.cttz.nxv1i8(<vscale x 1 x i8> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.cttz.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.cttz.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.cttz.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %13 = call <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %14 = call <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %15 = call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %22 = call <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %23 = call <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %24 = call <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %25 = call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %26 = call <vscale x 1 x i16> @llvm.vp.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %27 = call <vscale x 2 x i16> @llvm.vp.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %28 = call <vscale x 4 x i16> @llvm.vp.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %29 = call <vscale x 8 x i16> @llvm.vp.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %30 = call <vscale x 16 x i16> @llvm.vp.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %31 = call <vscale x 32 x i16> @llvm.vp.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %32 = call <2 x i32> @llvm.vp.cttz.v2i32(<2 x i32> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %33 = call <4 x i32> @llvm.vp.cttz.v4i32(<4 x i32> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %34 = call <8 x i32> @llvm.vp.cttz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %35 = call <16 x i32> @llvm.vp.cttz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %36 = call <vscale x 1 x i32> @llvm.vp.cttz.nxv1i32(<vscale x 1 x i32> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %37 = call <vscale x 2 x i32> @llvm.vp.cttz.nxv2i32(<vscale x 2 x i32> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %38 = call <vscale x 4 x i32> @llvm.vp.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %39 = call <vscale x 8 x i32> @llvm.vp.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %40 = call <vscale x 16 x i32> @llvm.vp.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %41 = call <2 x i64> @llvm.vp.cttz.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %42 = call <4 x i64> @llvm.vp.cttz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %43 = call <8 x i64> @llvm.vp.cttz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %44 = call <16 x i64> @llvm.vp.cttz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %45 = call <vscale x 1 x i64> @llvm.vp.cttz.nxv1i64(<vscale x 1 x i64> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %46 = call <vscale x 2 x i64> @llvm.vp.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %47 = call <vscale x 4 x i64> @llvm.vp.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %48 = call <vscale x 8 x i64> @llvm.vp.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %49 = call <vscale x 16 x i64> @llvm.vp.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; NOZVBB-LABEL: 'vp_cttz'
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %1 = call <2 x i8> @llvm.cttz.v2i8(<2 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %2 = call <4 x i8> @llvm.cttz.v4i8(<4 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %3 = call <8 x i8> @llvm.cttz.v8i8(<8 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %4 = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %5 = call <vscale x 1 x i8> @llvm.cttz.nxv1i8(<vscale x 1 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %6 = call <vscale x 2 x i8> @llvm.cttz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %7 = call <vscale x 4 x i8> @llvm.cttz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %8 = call <vscale x 8 x i8> @llvm.cttz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %9 = call <vscale x 16 x i8> @llvm.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %10 = call <vscale x 32 x i8> @llvm.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %11 = call <vscale x 64 x i8> @llvm.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x i16> @llvm.cttz.v2i16(<2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %13 = call <4 x i16> @llvm.cttz.v4i16(<4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %14 = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %15 = call <16 x i16> @llvm.cttz.v16i16(<16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %16 = call <vscale x 1 x i16> @llvm.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %17 = call <vscale x 2 x i16> @llvm.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %18 = call <vscale x 4 x i16> @llvm.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %19 = call <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %20 = call <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %21 = call <vscale x 32 x i16> @llvm.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %22 = call <2 x i16> @llvm.cttz.v2i16(<2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %23 = call <4 x i16> @llvm.cttz.v4i16(<4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %24 = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %25 = call <16 x i16> @llvm.cttz.v16i16(<16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %26 = call <vscale x 1 x i16> @llvm.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %27 = call <vscale x 2 x i16> @llvm.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %28 = call <vscale x 4 x i16> @llvm.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %29 = call <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %30 = call <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %31 = call <vscale x 32 x i16> @llvm.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %32 = call <2 x i32> @llvm.cttz.v2i32(<2 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %33 = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %34 = call <8 x i32> @llvm.cttz.v8i32(<8 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %35 = call <16 x i32> @llvm.cttz.v16i32(<16 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %36 = call <vscale x 1 x i32> @llvm.cttz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %37 = call <vscale x 2 x i32> @llvm.cttz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %38 = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %39 = call <vscale x 8 x i32> @llvm.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %40 = call <vscale x 16 x i32> @llvm.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %41 = call <2 x i64> @llvm.cttz.v2i64(<2 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %42 = call <4 x i64> @llvm.cttz.v4i64(<4 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %43 = call <8 x i64> @llvm.cttz.v8i64(<8 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %44 = call <16 x i64> @llvm.cttz.v16i64(<16 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %45 = call <vscale x 1 x i64> @llvm.cttz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %46 = call <vscale x 2 x i64> @llvm.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %47 = call <vscale x 4 x i64> @llvm.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %48 = call <vscale x 8 x i64> @llvm.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %49 = call <vscale x 16 x i64> @llvm.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVBB-LABEL: 'vp_cttz'
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <2 x i8> @llvm.cttz.v2i8(<2 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x i8> @llvm.cttz.v4i8(<4 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <8 x i8> @llvm.cttz.v8i8(<8 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 1 x i8> @llvm.cttz.nxv1i8(<vscale x 1 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.cttz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.cttz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.cttz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %10 = call <vscale x 32 x i8> @llvm.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call <vscale x 64 x i8> @llvm.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.cttz.v2i16(<2 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.cttz.v4i16(<4 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i16> @llvm.cttz.v16i16(<16 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %21 = call <vscale x 32 x i16> @llvm.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i16> @llvm.cttz.v2i16(<2 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i16> @llvm.cttz.v4i16(<4 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <16 x i16> @llvm.cttz.v16i16(<16 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i16> @llvm.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i16> @llvm.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i16> @llvm.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %29 = call <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %30 = call <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %31 = call <vscale x 32 x i16> @llvm.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i32> @llvm.cttz.v2i32(<2 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <8 x i32> @llvm.cttz.v8i32(<8 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %35 = call <16 x i32> @llvm.cttz.v16i32(<16 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i32> @llvm.cttz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i32> @llvm.cttz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %38 = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %39 = call <vscale x 8 x i32> @llvm.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %40 = call <vscale x 16 x i32> @llvm.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %41 = call <2 x i64> @llvm.cttz.v2i64(<2 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %42 = call <4 x i64> @llvm.cttz.v4i64(<4 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %43 = call <8 x i64> @llvm.cttz.v8i64(<8 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %44 = call <16 x i64> @llvm.cttz.v16i64(<16 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %45 = call <vscale x 1 x i64> @llvm.cttz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %46 = call <vscale x 2 x i64> @llvm.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %47 = call <vscale x 4 x i64> @llvm.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %48 = call <vscale x 8 x i64> @llvm.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %49 = call <vscale x 16 x i64> @llvm.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.cttz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
call <4 x i8> @llvm.vp.cttz.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-select.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-select.ll
index 39f55b441ba27..490f66afb06a6 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-select.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-select.ll
@@ -31,166 +31,106 @@ define void @select() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %23 = select <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i1> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %24 = select <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i1> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %25 = select <vscale x 32 x i1> undef, <vscale x 32 x i1> undef, <vscale x 32 x i1> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %26 = call <1 x i1> @llvm.vp.select.v1i1(<1 x i1> undef, <1 x i1> undef, <1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %27 = call <2 x i1> @llvm.vp.select.v2i1(<2 x i1> undef, <2 x i1> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %28 = call <4 x i1> @llvm.vp.select.v4i1(<4 x i1> undef, <4 x i1> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %29 = call <8 x i1> @llvm.vp.select.v8i1(<8 x i1> undef, <8 x i1> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %30 = call <16 x i1> @llvm.vp.select.v16i1(<16 x i1> undef, <16 x i1> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %31 = call <32 x i1> @llvm.vp.select.v32i1(<32 x i1> undef, <32 x i1> undef, <32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %32 = call <vscale x 1 x i1> @llvm.vp.select.nxv1i1(<vscale x 1 x i1> undef, <vscale x 1 x i1> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %33 = call <vscale x 2 x i1> @llvm.vp.select.nxv2i1(<vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %34 = call <vscale x 4 x i1> @llvm.vp.select.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %35 = call <vscale x 8 x i1> @llvm.vp.select.nxv8i1(<vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %36 = call <vscale x 16 x i1> @llvm.vp.select.nxv16i1(<vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %37 = call <vscale x 32 x i1> @llvm.vp.select.nxv32i1(<vscale x 32 x i1> undef, <vscale x 32 x i1> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %38 = select i1 undef, i8 undef, i8 undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %39 = select i1 undef, <1 x i8> undef, <1 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %40 = select i1 undef, <2 x i8> undef, <2 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %41 = select i1 undef, <4 x i8> undef, <4 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %42 = select i1 undef, <8 x i8> undef, <8 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %43 = select i1 undef, <16 x i8> undef, <16 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %44 = select i1 undef, <32 x i8> undef, <32 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %45 = select <1 x i1> undef, <1 x i8> undef, <1 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %46 = select <2 x i1> undef, <2 x i8> undef, <2 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %47 = select <4 x i1> undef, <4 x i8> undef, <4 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %48 = select <8 x i1> undef, <8 x i8> undef, <8 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %49 = select <16 x i1> undef, <16 x i8> undef, <16 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %50 = select <32 x i1> undef, <32 x i8> undef, <32 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %51 = select i1 undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %52 = select i1 undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %53 = select i1 undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %54 = select i1 undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %55 = select i1 undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %56 = select i1 undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %57 = select <vscale x 1 x i1> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %58 = select <vscale x 2 x i1> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %59 = select <vscale x 4 x i1> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %60 = select <vscale x 8 x i1> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %61 = select <vscale x 16 x i1> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %62 = select <vscale x 32 x i1> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %63 = call <1 x i8> @llvm.vp.select.v1i8(<1 x i1> undef, <1 x i8> undef, <1 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %64 = call <2 x i8> @llvm.vp.select.v2i8(<2 x i1> undef, <2 x i8> undef, <2 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %65 = call <4 x i8> @llvm.vp.select.v4i8(<4 x i1> undef, <4 x i8> undef, <4 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %66 = call <8 x i8> @llvm.vp.select.v8i8(<8 x i1> undef, <8 x i8> undef, <8 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %67 = call <16 x i8> @llvm.vp.select.v16i8(<16 x i1> undef, <16 x i8> undef, <16 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %68 = call <32 x i8> @llvm.vp.select.v32i8(<32 x i1> undef, <32 x i8> undef, <32 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %69 = call <vscale x 1 x i8> @llvm.vp.select.nxv1i8(<vscale x 1 x i1> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %70 = call <vscale x 2 x i8> @llvm.vp.select.nxv2i8(<vscale x 2 x i1> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %71 = call <vscale x 4 x i8> @llvm.vp.select.nxv4i8(<vscale x 4 x i1> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %72 = call <vscale x 8 x i8> @llvm.vp.select.nxv8i8(<vscale x 8 x i1> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %73 = call <vscale x 16 x i8> @llvm.vp.select.nxv16i8(<vscale x 16 x i1> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %74 = call <vscale x 32 x i8> @llvm.vp.select.nxv32i8(<vscale x 32 x i1> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %75 = select i1 undef, i16 undef, i16 undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %76 = select i1 undef, <1 x i16> undef, <1 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %77 = select i1 undef, <2 x i16> undef, <2 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %78 = select i1 undef, <4 x i16> undef, <4 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %79 = select i1 undef, <8 x i16> undef, <8 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %80 = select i1 undef, <16 x i16> undef, <16 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %81 = select i1 undef, <32 x i16> undef, <32 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %82 = select <1 x i1> undef, <1 x i16> undef, <1 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %83 = select <2 x i1> undef, <2 x i16> undef, <2 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %84 = select <4 x i1> undef, <4 x i16> undef, <4 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %85 = select <8 x i1> undef, <8 x i16> undef, <8 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %86 = select <16 x i1> undef, <16 x i16> undef, <16 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %87 = select <32 x i1> undef, <32 x i16> undef, <32 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %88 = select i1 undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %89 = select i1 undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %90 = select i1 undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %91 = select i1 undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %92 = select i1 undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %93 = select i1 undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %94 = select <vscale x 1 x i1> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %95 = select <vscale x 2 x i1> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %96 = select <vscale x 4 x i1> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %97 = select <vscale x 8 x i1> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %98 = select <vscale x 16 x i1> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %99 = select <vscale x 32 x i1> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %100 = call <1 x i16> @llvm.vp.select.v1i16(<1 x i1> undef, <1 x i16> undef, <1 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %101 = call <2 x i16> @llvm.vp.select.v2i16(<2 x i1> undef, <2 x i16> undef, <2 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %102 = call <4 x i16> @llvm.vp.select.v4i16(<4 x i1> undef, <4 x i16> undef, <4 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %103 = call <8 x i16> @llvm.vp.select.v8i16(<8 x i1> undef, <8 x i16> undef, <8 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %104 = call <16 x i16> @llvm.vp.select.v16i16(<16 x i1> undef, <16 x i16> undef, <16 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %105 = call <32 x i16> @llvm.vp.select.v32i16(<32 x i1> undef, <32 x i16> undef, <32 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %106 = call <vscale x 1 x i16> @llvm.vp.select.nxv1i16(<vscale x 1 x i1> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %107 = call <vscale x 2 x i16> @llvm.vp.select.nxv2i16(<vscale x 2 x i1> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %108 = call <vscale x 4 x i16> @llvm.vp.select.nxv4i16(<vscale x 4 x i1> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %109 = call <vscale x 8 x i16> @llvm.vp.select.nxv8i16(<vscale x 8 x i1> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %110 = call <vscale x 16 x i16> @llvm.vp.select.nxv16i16(<vscale x 16 x i1> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %111 = call <vscale x 32 x i16> @llvm.vp.select.nxv32i16(<vscale x 32 x i1> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %112 = select i1 undef, i32 undef, i32 undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %113 = select i1 undef, <1 x i32> undef, <1 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %114 = select i1 undef, <2 x i32> undef, <2 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %115 = select i1 undef, <4 x i32> undef, <4 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %116 = select i1 undef, <8 x i32> undef, <8 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %117 = select i1 undef, <16 x i32> undef, <16 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %118 = select i1 undef, <32 x i32> undef, <32 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %119 = select <1 x i1> undef, <1 x i32> undef, <1 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %120 = select <2 x i1> undef, <2 x i32> undef, <2 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %121 = select <4 x i1> undef, <4 x i32> undef, <4 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %122 = select <8 x i1> undef, <8 x i32> undef, <8 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %123 = select <16 x i1> undef, <16 x i32> undef, <16 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %124 = select <32 x i1> undef, <32 x i32> undef, <32 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %125 = select i1 undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %126 = select i1 undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %127 = select i1 undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %128 = select i1 undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %129 = select i1 undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %130 = select i1 undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %131 = select <vscale x 1 x i1> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %132 = select <vscale x 2 x i1> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %133 = select <vscale x 4 x i1> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %134 = select <vscale x 8 x i1> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %135 = select <vscale x 16 x i1> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %136 = select <vscale x 32 x i1> undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %137 = call <1 x i32> @llvm.vp.select.v1i32(<1 x i1> undef, <1 x i32> undef, <1 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %138 = call <2 x i32> @llvm.vp.select.v2i32(<2 x i1> undef, <2 x i32> undef, <2 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %139 = call <4 x i32> @llvm.vp.select.v4i32(<4 x i1> undef, <4 x i32> undef, <4 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %140 = call <8 x i32> @llvm.vp.select.v8i32(<8 x i1> undef, <8 x i32> undef, <8 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %141 = call <16 x i32> @llvm.vp.select.v16i32(<16 x i1> undef, <16 x i32> undef, <16 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %142 = call <32 x i32> @llvm.vp.select.v32i32(<32 x i1> undef, <32 x i32> undef, <32 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %143 = call <vscale x 1 x i32> @llvm.vp.select.nxv1i32(<vscale x 1 x i1> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %144 = call <vscale x 2 x i32> @llvm.vp.select.nxv2i32(<vscale x 2 x i1> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %145 = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %146 = call <vscale x 8 x i32> @llvm.vp.select.nxv8i32(<vscale x 8 x i1> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %147 = call <vscale x 16 x i32> @llvm.vp.select.nxv16i32(<vscale x 16 x i1> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %148 = call <vscale x 32 x i32> @llvm.vp.select.nxv32i32(<vscale x 32 x i1> undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %149 = select i1 undef, i64 undef, i64 undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %150 = select i1 undef, <1 x i64> undef, <1 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %151 = select i1 undef, <2 x i64> undef, <2 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %152 = select i1 undef, <4 x i64> undef, <4 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %153 = select i1 undef, <8 x i64> undef, <8 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %154 = select i1 undef, <16 x i64> undef, <16 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %155 = select i1 undef, <32 x i64> undef, <32 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %156 = select <1 x i1> undef, <1 x i64> undef, <1 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %157 = select <2 x i1> undef, <2 x i64> undef, <2 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %158 = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %159 = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %160 = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %161 = select <32 x i1> undef, <32 x i64> undef, <32 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %162 = select i1 undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %163 = select i1 undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %164 = select i1 undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %165 = select i1 undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %166 = select i1 undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %167 = select i1 undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %168 = select <vscale x 1 x i1> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %169 = select <vscale x 2 x i1> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %170 = select <vscale x 4 x i1> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %171 = select <vscale x 8 x i1> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %172 = select <vscale x 16 x i1> undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %173 = select <vscale x 32 x i1> undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %174 = call <1 x i64> @llvm.vp.select.v1i64(<1 x i1> undef, <1 x i64> undef, <1 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %175 = call <2 x i64> @llvm.vp.select.v2i64(<2 x i1> undef, <2 x i64> undef, <2 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %176 = call <4 x i64> @llvm.vp.select.v4i64(<4 x i1> undef, <4 x i64> undef, <4 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %177 = call <8 x i64> @llvm.vp.select.v8i64(<8 x i1> undef, <8 x i64> undef, <8 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %178 = call <16 x i64> @llvm.vp.select.v16i64(<16 x i1> undef, <16 x i64> undef, <16 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %179 = call <32 x i64> @llvm.vp.select.v32i64(<32 x i1> undef, <32 x i64> undef, <32 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %180 = call <vscale x 1 x i64> @llvm.vp.select.nxv1i64(<vscale x 1 x i1> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %181 = call <vscale x 2 x i64> @llvm.vp.select.nxv2i64(<vscale x 2 x i1> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %182 = call <vscale x 4 x i64> @llvm.vp.select.nxv4i64(<vscale x 4 x i1> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %183 = call <vscale x 8 x i64> @llvm.vp.select.nxv8i64(<vscale x 8 x i1> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %184 = call <vscale x 16 x i64> @llvm.vp.select.nxv16i64(<vscale x 16 x i1> undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %185 = call <vscale x 32 x i64> @llvm.vp.select.nxv32i64(<vscale x 32 x i1> undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = select i1 undef, i8 undef, i8 undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %27 = select i1 undef, <1 x i8> undef, <1 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %28 = select i1 undef, <2 x i8> undef, <2 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %29 = select i1 undef, <4 x i8> undef, <4 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %30 = select i1 undef, <8 x i8> undef, <8 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %31 = select i1 undef, <16 x i8> undef, <16 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %32 = select i1 undef, <32 x i8> undef, <32 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = select <1 x i1> undef, <1 x i8> undef, <1 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = select <2 x i1> undef, <2 x i8> undef, <2 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = select <4 x i1> undef, <4 x i8> undef, <4 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = select <8 x i1> undef, <8 x i8> undef, <8 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = select <16 x i1> undef, <16 x i8> undef, <16 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %38 = select <32 x i1> undef, <32 x i8> undef, <32 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %39 = select i1 undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %40 = select i1 undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %41 = select i1 undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %42 = select i1 undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %43 = select i1 undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %44 = select i1 undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %45 = select <vscale x 1 x i1> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %46 = select <vscale x 2 x i1> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %47 = select <vscale x 4 x i1> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %48 = select <vscale x 8 x i1> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %49 = select <vscale x 16 x i1> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %50 = select <vscale x 32 x i1> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %51 = select i1 undef, i16 undef, i16 undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %52 = select i1 undef, <1 x i16> undef, <1 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %53 = select i1 undef, <2 x i16> undef, <2 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %54 = select i1 undef, <4 x i16> undef, <4 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %55 = select i1 undef, <8 x i16> undef, <8 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %56 = select i1 undef, <16 x i16> undef, <16 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %57 = select i1 undef, <32 x i16> undef, <32 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %58 = select <1 x i1> undef, <1 x i16> undef, <1 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %59 = select <2 x i1> undef, <2 x i16> undef, <2 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %60 = select <4 x i1> undef, <4 x i16> undef, <4 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %61 = select <8 x i1> undef, <8 x i16> undef, <8 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %62 = select <16 x i1> undef, <16 x i16> undef, <16 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %63 = select <32 x i1> undef, <32 x i16> undef, <32 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %64 = select i1 undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %65 = select i1 undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %66 = select i1 undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %67 = select i1 undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %68 = select i1 undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %69 = select i1 undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %70 = select <vscale x 1 x i1> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %71 = select <vscale x 2 x i1> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %72 = select <vscale x 4 x i1> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %73 = select <vscale x 8 x i1> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %74 = select <vscale x 16 x i1> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %75 = select <vscale x 32 x i1> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %76 = select i1 undef, i32 undef, i32 undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %77 = select i1 undef, <1 x i32> undef, <1 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %78 = select i1 undef, <2 x i32> undef, <2 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %79 = select i1 undef, <4 x i32> undef, <4 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %80 = select i1 undef, <8 x i32> undef, <8 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %81 = select i1 undef, <16 x i32> undef, <16 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %82 = select i1 undef, <32 x i32> undef, <32 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %83 = select <1 x i1> undef, <1 x i32> undef, <1 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %84 = select <2 x i1> undef, <2 x i32> undef, <2 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %85 = select <4 x i1> undef, <4 x i32> undef, <4 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %86 = select <8 x i1> undef, <8 x i32> undef, <8 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %87 = select <16 x i1> undef, <16 x i32> undef, <16 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %88 = select <32 x i1> undef, <32 x i32> undef, <32 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %89 = select i1 undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %90 = select i1 undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %91 = select i1 undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %92 = select i1 undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %93 = select i1 undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %94 = select i1 undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %95 = select <vscale x 1 x i1> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %96 = select <vscale x 2 x i1> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %97 = select <vscale x 4 x i1> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %98 = select <vscale x 8 x i1> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %99 = select <vscale x 16 x i1> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %100 = select <vscale x 32 x i1> undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %101 = select i1 undef, i64 undef, i64 undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %102 = select i1 undef, <1 x i64> undef, <1 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %103 = select i1 undef, <2 x i64> undef, <2 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %104 = select i1 undef, <4 x i64> undef, <4 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %105 = select i1 undef, <8 x i64> undef, <8 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %106 = select i1 undef, <16 x i64> undef, <16 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %107 = select i1 undef, <32 x i64> undef, <32 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %108 = select <1 x i1> undef, <1 x i64> undef, <1 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %109 = select <2 x i1> undef, <2 x i64> undef, <2 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %110 = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %111 = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %112 = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %113 = select <32 x i1> undef, <32 x i64> undef, <32 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %114 = select i1 undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %115 = select i1 undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %116 = select i1 undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %117 = select i1 undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %118 = select i1 undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %119 = select i1 undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %120 = select <vscale x 1 x i1> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %121 = select <vscale x 2 x i1> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %122 = select <vscale x 4 x i1> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %123 = select <vscale x 8 x i1> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %124 = select <vscale x 16 x i1> undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %125 = select <vscale x 32 x i1> undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
select i1 undef, i1 undef, i1 undef
diff --git a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
index 9e8f727978001..fa83958c4360f 100644
--- a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
@@ -45,46 +45,87 @@ define void @fshl(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i3
}
define void @vp_fshr() {
-; CHECK-LABEL: 'vp_fshr'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x i8> @llvm.vp.fshr.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x i8> @llvm.vp.fshr.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x i8> @llvm.vp.fshr.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x i8> @llvm.vp.fshr.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x i8> @llvm.vp.fshr.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.fshr.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.fshr.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.fshr.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.fshr.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.fshr.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x i16> @llvm.vp.fshr.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x i16> @llvm.vp.fshr.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x i16> @llvm.vp.fshr.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x i16> @llvm.vp.fshr.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.fshr.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.fshr.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.fshr.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.fshr.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.fshr.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <2 x i32> @llvm.vp.fshr.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <4 x i32> @llvm.vp.fshr.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <8 x i32> @llvm.vp.fshr.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %25 = call <16 x i32> @llvm.vp.fshr.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 1 x i32> @llvm.vp.fshr.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %27 = call <vscale x 2 x i32> @llvm.vp.fshr.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call <vscale x 4 x i32> @llvm.vp.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %29 = call <vscale x 8 x i32> @llvm.vp.fshr.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %30 = call <vscale x 16 x i32> @llvm.vp.fshr.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %31 = call <2 x i64> @llvm.vp.fshr.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %32 = call <4 x i64> @llvm.vp.fshr.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %33 = call <8 x i64> @llvm.vp.fshr.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %34 = call <16 x i64> @llvm.vp.fshr.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 1 x i64> @llvm.vp.fshr.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %36 = call <vscale x 2 x i64> @llvm.vp.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshr.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshr.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ARGBASED-LABEL: 'vp_fshr'
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %1 = call <2 x i8> @llvm.fshr.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %2 = call <4 x i8> @llvm.fshr.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %3 = call <8 x i8> @llvm.fshr.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %4 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %5 = call <vscale x 1 x i8> @llvm.fshr.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %6 = call <vscale x 2 x i8> @llvm.fshr.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %7 = call <vscale x 4 x i8> @llvm.fshr.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %8 = call <vscale x 8 x i8> @llvm.fshr.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %9 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %10 = call <vscale x 32 x i8> @llvm.fshr.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %11 = call <vscale x 64 x i8> @llvm.fshr.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %12 = call <2 x i16> @llvm.fshr.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %13 = call <4 x i16> @llvm.fshr.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %14 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %15 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %16 = call <vscale x 1 x i16> @llvm.fshr.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %17 = call <vscale x 2 x i16> @llvm.fshr.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %18 = call <vscale x 4 x i16> @llvm.fshr.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %20 = call <vscale x 16 x i16> @llvm.fshr.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %21 = call <vscale x 32 x i16> @llvm.fshr.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %22 = call <2 x i32> @llvm.fshr.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %23 = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %24 = call <8 x i32> @llvm.fshr.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %25 = call <16 x i32> @llvm.fshr.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %26 = call <vscale x 1 x i32> @llvm.fshr.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %27 = call <vscale x 2 x i32> @llvm.fshr.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %29 = call <vscale x 8 x i32> @llvm.fshr.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %30 = call <vscale x 16 x i32> @llvm.fshr.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %31 = call <2 x i64> @llvm.fshr.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %32 = call <4 x i64> @llvm.fshr.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %33 = call <8 x i64> @llvm.fshr.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %34 = call <16 x i64> @llvm.fshr.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %35 = call <vscale x 1 x i64> @llvm.fshr.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %36 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %37 = call <vscale x 4 x i64> @llvm.fshr.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %38 = call <vscale x 8 x i64> @llvm.fshr.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'vp_fshr'
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x i8> @llvm.fshr.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x i8> @llvm.fshr.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x i8> @llvm.fshr.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x i8> @llvm.fshr.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x i8> @llvm.fshr.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.fshr.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x i8> @llvm.fshr.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x i8> @llvm.fshr.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %9 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %10 = call <vscale x 32 x i8> @llvm.fshr.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %11 = call <vscale x 64 x i8> @llvm.fshr.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x i16> @llvm.fshr.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x i16> @llvm.fshr.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %15 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x i16> @llvm.fshr.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x i16> @llvm.fshr.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x i16> @llvm.fshr.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %19 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %20 = call <vscale x 16 x i16> @llvm.fshr.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %21 = call <vscale x 32 x i16> @llvm.fshr.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <2 x i32> @llvm.fshr.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %24 = call <8 x i32> @llvm.fshr.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %25 = call <16 x i32> @llvm.fshr.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 1 x i32> @llvm.fshr.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %27 = call <vscale x 2 x i32> @llvm.fshr.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %28 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %29 = call <vscale x 8 x i32> @llvm.fshr.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %30 = call <vscale x 16 x i32> @llvm.fshr.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %31 = call <2 x i64> @llvm.fshr.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %32 = call <4 x i64> @llvm.fshr.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %33 = call <8 x i64> @llvm.fshr.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %34 = call <16 x i64> @llvm.fshr.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 1 x i64> @llvm.fshr.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %36 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %37 = call <vscale x 4 x i64> @llvm.fshr.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %38 = call <vscale x 8 x i64> @llvm.fshr.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.fshr.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
call <4 x i8> @llvm.vp.fshr.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
@@ -128,46 +169,87 @@ define void @vp_fshr() {
}
define void @vp_fshl() {
-; CHECK-LABEL: 'vp_fshl'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x i8> @llvm.vp.fshl.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x i8> @llvm.vp.fshl.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x i8> @llvm.vp.fshl.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x i8> @llvm.vp.fshl.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x i8> @llvm.vp.fshl.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.fshl.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.fshl.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.fshl.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.fshl.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.fshl.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x i16> @llvm.vp.fshl.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x i16> @llvm.vp.fshl.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x i16> @llvm.vp.fshl.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x i16> @llvm.vp.fshl.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.fshl.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.fshl.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.fshl.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.fshl.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.fshl.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <2 x i32> @llvm.vp.fshl.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <4 x i32> @llvm.vp.fshl.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <8 x i32> @llvm.vp.fshl.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %25 = call <16 x i32> @llvm.vp.fshl.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 1 x i32> @llvm.vp.fshl.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %27 = call <vscale x 2 x i32> @llvm.vp.fshl.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call <vscale x 4 x i32> @llvm.vp.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %29 = call <vscale x 8 x i32> @llvm.vp.fshl.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %30 = call <vscale x 16 x i32> @llvm.vp.fshl.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %31 = call <2 x i64> @llvm.vp.fshl.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %32 = call <4 x i64> @llvm.vp.fshl.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %33 = call <8 x i64> @llvm.vp.fshl.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %34 = call <16 x i64> @llvm.vp.fshl.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 1 x i64> @llvm.vp.fshl.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %36 = call <vscale x 2 x i64> @llvm.vp.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshl.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshl.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ARGBASED-LABEL: 'vp_fshl'
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %1 = call <2 x i8> @llvm.fshl.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %2 = call <4 x i8> @llvm.fshl.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %3 = call <8 x i8> @llvm.fshl.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %4 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %5 = call <vscale x 1 x i8> @llvm.fshl.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %6 = call <vscale x 2 x i8> @llvm.fshl.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %7 = call <vscale x 4 x i8> @llvm.fshl.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %8 = call <vscale x 8 x i8> @llvm.fshl.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %9 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %10 = call <vscale x 32 x i8> @llvm.fshl.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %11 = call <vscale x 64 x i8> @llvm.fshl.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %12 = call <2 x i16> @llvm.fshl.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %13 = call <4 x i16> @llvm.fshl.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %14 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %15 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %16 = call <vscale x 1 x i16> @llvm.fshl.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %17 = call <vscale x 2 x i16> @llvm.fshl.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %18 = call <vscale x 4 x i16> @llvm.fshl.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %19 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %20 = call <vscale x 16 x i16> @llvm.fshl.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %21 = call <vscale x 32 x i16> @llvm.fshl.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %22 = call <2 x i32> @llvm.fshl.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %23 = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %24 = call <8 x i32> @llvm.fshl.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %25 = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %26 = call <vscale x 1 x i32> @llvm.fshl.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %27 = call <vscale x 2 x i32> @llvm.fshl.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %28 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %29 = call <vscale x 8 x i32> @llvm.fshl.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %30 = call <vscale x 16 x i32> @llvm.fshl.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %31 = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %32 = call <4 x i64> @llvm.fshl.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %33 = call <8 x i64> @llvm.fshl.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %34 = call <16 x i64> @llvm.fshl.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %35 = call <vscale x 1 x i64> @llvm.fshl.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %36 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %37 = call <vscale x 4 x i64> @llvm.fshl.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %38 = call <vscale x 8 x i64> @llvm.fshl.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'vp_fshl'
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x i8> @llvm.fshl.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x i8> @llvm.fshl.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x i8> @llvm.fshl.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x i8> @llvm.fshl.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x i8> @llvm.fshl.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.fshl.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x i8> @llvm.fshl.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x i8> @llvm.fshl.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %9 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %10 = call <vscale x 32 x i8> @llvm.fshl.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %11 = call <vscale x 64 x i8> @llvm.fshl.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x i16> @llvm.fshl.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x i16> @llvm.fshl.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %15 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x i16> @llvm.fshl.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x i16> @llvm.fshl.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x i16> @llvm.fshl.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %19 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %20 = call <vscale x 16 x i16> @llvm.fshl.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %21 = call <vscale x 32 x i16> @llvm.fshl.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <2 x i32> @llvm.fshl.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %24 = call <8 x i32> @llvm.fshl.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %25 = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 1 x i32> @llvm.fshl.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %27 = call <vscale x 2 x i32> @llvm.fshl.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %28 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %29 = call <vscale x 8 x i32> @llvm.fshl.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %30 = call <vscale x 16 x i32> @llvm.fshl.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %31 = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %32 = call <4 x i64> @llvm.fshl.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %33 = call <8 x i64> @llvm.fshl.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %34 = call <16 x i64> @llvm.fshl.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 1 x i64> @llvm.fshl.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %36 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %37 = call <vscale x 4 x i64> @llvm.fshl.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %38 = call <vscale x 8 x i64> @llvm.fshl.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.fshl.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
call <4 x i8> @llvm.vp.fshl.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
@@ -212,69 +294,37 @@ define void @vp_fshl() {
define void @add() {
; CHECK-LABEL: 'add'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t1 = add <2 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t3 = add <4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t5 = add <8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t7 = add <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t9 = add <2 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t11 = add <4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t13 = add <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t15 = add <16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t17 = add <2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t19 = add <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t21 = add <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t23 = add <16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t25 = add <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t27 = add <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t29 = add <8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t31 = add <16 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t33 = add <vscale x 2 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t35 = add <vscale x 4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t37 = add <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t39 = add <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.add.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t41 = add <vscale x 2 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.add.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t43 = add <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.add.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t45 = add <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.add.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t47 = add <vscale x 16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.add.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t49 = add <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t51 = add <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.add.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t53 = add <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.add.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t55 = add <vscale x 16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t57 = add <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t59 = add <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t61 = add <vscale x 8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t63 = add <vscale x 16 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -347,69 +397,37 @@ define void @add() {
define void @and() {
; CHECK-LABEL: 'and'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.and.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t1 = and <2 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.and.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t3 = and <4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.and.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t5 = and <8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.and.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t7 = and <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.and.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t9 = and <2 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.and.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t11 = and <4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.and.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t13 = and <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.and.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t15 = and <16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.and.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t17 = and <2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.and.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t19 = and <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t21 = and <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.and.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t23 = and <16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.and.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t25 = and <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.and.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t27 = and <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.and.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t29 = and <8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.and.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t31 = and <16 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.and.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t33 = and <vscale x 2 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.and.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t35 = and <vscale x 4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.and.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t37 = and <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.and.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t39 = and <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.and.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t41 = and <vscale x 2 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.and.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t43 = and <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.and.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t45 = and <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.and.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t47 = and <vscale x 16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.and.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t49 = and <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t51 = and <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.and.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t53 = and <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.and.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t55 = and <vscale x 16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.and.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t57 = and <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.and.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t59 = and <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.and.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t61 = and <vscale x 8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.and.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t63 = and <vscale x 16 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -482,38 +500,38 @@ define void @and() {
define void @smax() {
; CHECK-LABEL: 'smax'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.smax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.smax.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.smax.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.smax.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.smax.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.smax.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.smax.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.smax.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.smax.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.smax.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.smax.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.smax.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.smax.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.smax.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.smax.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.smax.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.smax.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.smax.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.smax.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%t0 = call <2 x i8> @llvm.vp.smax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -554,38 +572,38 @@ define void @smax() {
define void @smin() {
; CHECK-LABEL: 'smin'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.smin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.smin.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.smin.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.smin.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.smin.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.smin.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.smin.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.smin.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.smin.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.smin.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.smin.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.smin.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.smin.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.smin.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.smin.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.smin.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.smin.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.smin.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.smin.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%t0 = call <2 x i8> @llvm.vp.smin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -625,38 +643,38 @@ define void @smin() {
define void @umax() {
; CHECK-LABEL: 'umax'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.umax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.umax.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.umax.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.umax.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.umax.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.umax.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.umax.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.umax.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.umax.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.umax.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.umax.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.umax.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.umax.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.umax.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.umax.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.umax.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.umax.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.umax.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.umax.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%t0 = call <2 x i8> @llvm.vp.umax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -696,38 +714,38 @@ define void @umax() {
define void @umin() {
; CHECK-LABEL: 'umin'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.umin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.umin.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.umin.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.umin.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.umin.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.umin.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.umin.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.umin.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.umin.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.umin.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.umin.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.umin.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.umin.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.umin.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.umin.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.umin.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.umin.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.umin.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.umin.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%t0 = call <2 x i8> @llvm.vp.umin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -767,37 +785,37 @@ define void @umin() {
define void @abs() {
; CHECK-LABEL: 'abs'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %11 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %12 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %13 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %14 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %15 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %16 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x i8> @llvm.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 2 x i8> @llvm.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 4 x i8> @llvm.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %20 = call <vscale x 4 x i8> @llvm.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %24 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %25 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %29 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %30 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %31 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -1407,22 +1425,6 @@ define void @reduce_other() {
define void @vp_fadd(){
; CHECK-LABEL: 'vp_fadd'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t0 = call <2 x float> @llvm.vp.fadd.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t2 = call <4 x float> @llvm.vp.fadd.v4f32(<4 x float> undef, <4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t4 = call <8 x float> @llvm.vp.fadd.v8f32(<8 x float> undef, <8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t6 = call <16 x float> @llvm.vp.fadd.v16f32(<16 x float> undef, <16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t8 = call <2 x double> @llvm.vp.fadd.v2f64(<2 x double> undef, <2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t10 = call <4 x double> @llvm.vp.fadd.v4f64(<4 x double> undef, <4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t12 = call <8 x double> @llvm.vp.fadd.v8f64(<8 x double> undef, <8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t14 = call <16 x double> @llvm.vp.fadd.v16f64(<16 x double> undef, <16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t17 = call <vscale x 2 x float> @llvm.vp.fadd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t19 = call <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t21 = call <vscale x 8 x float> @llvm.vp.fadd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t23 = call <vscale x 16 x float> @llvm.vp.fadd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t25 = call <vscale x 2 x double> @llvm.vp.fadd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t27 = call <vscale x 4 x double> @llvm.vp.fadd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t29 = call <vscale x 8 x double> @llvm.vp.fadd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %t31 = call <vscale x 16 x double> @llvm.vp.fadd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %t32 = fadd <vscale x 16 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -1452,22 +1454,6 @@ define void @vp_fadd(){
define void @vp_fsub(){
; CHECK-LABEL: 'vp_fsub'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t0 = call <2 x float> @llvm.vp.fsub.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t2 = call <4 x float> @llvm.vp.fsub.v4f32(<4 x float> undef, <4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t4 = call <8 x float> @llvm.vp.fsub.v8f32(<8 x float> undef, <8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t6 = call <16 x float> @llvm.vp.fsub.v16f32(<16 x float> undef, <16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t8 = call <2 x double> @llvm.vp.fsub.v2f64(<2 x double> undef, <2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t10 = call <4 x double> @llvm.vp.fsub.v4f64(<4 x double> undef, <4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t12 = call <8 x double> @llvm.vp.fsub.v8f64(<8 x double> undef, <8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t14 = call <16 x double> @llvm.vp.fsub.v16f64(<16 x double> undef, <16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t17 = call <vscale x 2 x float> @llvm.vp.fsub.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t19 = call <vscale x 4 x float> @llvm.vp.fsub.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t21 = call <vscale x 8 x float> @llvm.vp.fsub.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t23 = call <vscale x 16 x float> @llvm.vp.fsub.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t25 = call <vscale x 2 x double> @llvm.vp.fsub.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t27 = call <vscale x 4 x double> @llvm.vp.fsub.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t29 = call <vscale x 8 x double> @llvm.vp.fsub.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %t31 = call <vscale x 16 x double> @llvm.vp.fsub.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%t0 = call <2 x float> @llvm.vp.fsub.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
@@ -1495,22 +1481,6 @@ define void @vp_fsub(){
define void @vp_fmul(){
; CHECK-LABEL: 'vp_fmul'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t0 = call <2 x float> @llvm.vp.fmul.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t2 = call <4 x float> @llvm.vp.fmul.v4f32(<4 x float> undef, <4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t4 = call <8 x float> @llvm.vp.fmul.v8f32(<8 x float> undef, <8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t6 = call <16 x float> @llvm.vp.fmul.v16f32(<16 x float> undef, <16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t8 = call <2 x double> @llvm.vp.fmul.v2f64(<2 x double> undef, <2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t10 = call <4 x double> @llvm.vp.fmul.v4f64(<4 x double> undef, <4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t12 = call <8 x double> @llvm.vp.fmul.v8f64(<8 x double> undef, <8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t14 = call <16 x double> @llvm.vp.fmul.v16f64(<16 x double> undef, <16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t17 = call <vscale x 2 x float> @llvm.vp.fmul.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t19 = call <vscale x 4 x float> @llvm.vp.fmul.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t21 = call <vscale x 8 x float> @llvm.vp.fmul.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t23 = call <vscale x 16 x float> @llvm.vp.fmul.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t25 = call <vscale x 2 x double> @llvm.vp.fmul.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t27 = call <vscale x 4 x double> @llvm.vp.fmul.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t29 = call <vscale x 8 x double> @llvm.vp.fmul.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %t31 = call <vscale x 16 x double> @llvm.vp.fmul.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%t0 = call <2 x float> @llvm.vp.fmul.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
@@ -1538,22 +1508,6 @@ define void @vp_fmul(){
define void @vp_fdiv(){
; CHECK-LABEL: 'vp_fdiv'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t0 = call <2 x float> @llvm.vp.fdiv.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t2 = call <4 x float> @llvm.vp.fdiv.v4f32(<4 x float> undef, <4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t4 = call <8 x float> @llvm.vp.fdiv.v8f32(<8 x float> undef, <8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t6 = call <16 x float> @llvm.vp.fdiv.v16f32(<16 x float> undef, <16 x float> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t8 = call <2 x double> @llvm.vp.fdiv.v2f64(<2 x double> undef, <2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t10 = call <4 x double> @llvm.vp.fdiv.v4f64(<4 x double> undef, <4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t12 = call <8 x double> @llvm.vp.fdiv.v8f64(<8 x double> undef, <8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t14 = call <16 x double> @llvm.vp.fdiv.v16f64(<16 x double> undef, <16 x double> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t17 = call <vscale x 2 x float> @llvm.vp.fdiv.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t19 = call <vscale x 4 x float> @llvm.vp.fdiv.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t21 = call <vscale x 8 x float> @llvm.vp.fdiv.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t23 = call <vscale x 16 x float> @llvm.vp.fdiv.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t25 = call <vscale x 2 x double> @llvm.vp.fdiv.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t27 = call <vscale x 4 x double> @llvm.vp.fdiv.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t29 = call <vscale x 8 x double> @llvm.vp.fdiv.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %t31 = call <vscale x 16 x double> @llvm.vp.fdiv.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%t0 = call <2 x float> @llvm.vp.fdiv.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
@@ -1616,73 +1570,73 @@ define void @splice() {
define void @is.fpclass() {
; ARGBASED-LABEL: 'is.fpclass'
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %1 = call <2 x i1> @llvm.vp.is.fpclass.v2bf16(<2 x bfloat> poison, i32 0, <2 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %2 = call <4 x i1> @llvm.vp.is.fpclass.v4bf16(<4 x bfloat> poison, i32 0, <4 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %3 = call <8 x i1> @llvm.vp.is.fpclass.v8bf16(<8 x bfloat> poison, i32 0, <8 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %4 = call <16 x i1> @llvm.vp.is.fpclass.v16bf16(<16 x bfloat> poison, i32 0, <16 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %5 = call <2 x i1> @llvm.vp.is.fpclass.v2f16(<2 x half> poison, i32 0, <2 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %6 = call <4 x i1> @llvm.vp.is.fpclass.v4f16(<4 x half> poison, i32 0, <4 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %7 = call <8 x i1> @llvm.vp.is.fpclass.v8f16(<8 x half> poison, i32 0, <8 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %8 = call <16 x i1> @llvm.vp.is.fpclass.v16f16(<16 x half> poison, i32 0, <16 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %9 = call <2 x i1> @llvm.vp.is.fpclass.v2f32(<2 x float> poison, i32 0, <2 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call <4 x i1> @llvm.vp.is.fpclass.v4f32(<4 x float> poison, i32 0, <4 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %11 = call <8 x i1> @llvm.vp.is.fpclass.v8f32(<8 x float> poison, i32 0, <8 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %12 = call <16 x i1> @llvm.vp.is.fpclass.v16f32(<16 x float> poison, i32 0, <16 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %13 = call <2 x i1> @llvm.vp.is.fpclass.v2f64(<2 x double> poison, i32 0, <2 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %14 = call <4 x i1> @llvm.vp.is.fpclass.v4f64(<4 x double> poison, i32 0, <4 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %15 = call <8 x i1> @llvm.vp.is.fpclass.v8f64(<8 x double> poison, i32 0, <8 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %16 = call <16 x i1> @llvm.vp.is.fpclass.v16f64(<16 x double> poison, i32 0, <16 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2bf16(<vscale x 2 x bfloat> poison, i32 0, <vscale x 2 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x i1> @llvm.vp.is.fpclass.nxv4bf16(<vscale x 4 x bfloat> poison, i32 0, <vscale x 4 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x i1> @llvm.vp.is.fpclass.nxv8bf16(<vscale x 8 x bfloat> poison, i32 0, <vscale x 8 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %20 = call <vscale x 16 x i1> @llvm.vp.is.fpclass.nxv16bf16(<vscale x 16 x bfloat> poison, i32 0, <vscale x 16 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %21 = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2f16(<vscale x 2 x half> poison, i32 0, <vscale x 2 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %22 = call <vscale x 4 x i1> @llvm.vp.is.fpclass.nxv4f16(<vscale x 4 x half> poison, i32 0, <vscale x 4 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %23 = call <vscale x 8 x i1> @llvm.vp.is.fpclass.nxv8f16(<vscale x 8 x half> poison, i32 0, <vscale x 8 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %24 = call <vscale x 16 x i1> @llvm.vp.is.fpclass.nxv16f16(<vscale x 16 x half> poison, i32 0, <vscale x 16 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2f32(<vscale x 2 x float> poison, i32 0, <vscale x 2 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %26 = call <vscale x 4 x i1> @llvm.vp.is.fpclass.nxv4f32(<vscale x 4 x float> poison, i32 0, <vscale x 4 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %27 = call <vscale x 8 x i1> @llvm.vp.is.fpclass.nxv8f32(<vscale x 8 x float> poison, i32 0, <vscale x 8 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %28 = call <vscale x 16 x i1> @llvm.vp.is.fpclass.nxv16f32(<vscale x 16 x float> poison, i32 0, <vscale x 16 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %29 = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2f64(<vscale x 2 x double> poison, i32 0, <vscale x 2 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %30 = call <vscale x 4 x i1> @llvm.vp.is.fpclass.nxv4f64(<vscale x 4 x double> poison, i32 0, <vscale x 4 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %31 = call <vscale x 8 x i1> @llvm.vp.is.fpclass.nxv8f64(<vscale x 8 x double> poison, i32 0, <vscale x 8 x i1> poison, i32 poison)
-; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %32 = call <vscale x 16 x i1> @llvm.vp.is.fpclass.nxv16f64(<vscale x 16 x double> poison, i32 0, <vscale x 16 x i1> poison, i32 poison)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %1 = call <2 x i1> @llvm.is.fpclass.v2bf16(<2 x bfloat> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %2 = call <4 x i1> @llvm.is.fpclass.v4bf16(<4 x bfloat> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %3 = call <8 x i1> @llvm.is.fpclass.v8bf16(<8 x bfloat> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %4 = call <16 x i1> @llvm.is.fpclass.v16bf16(<16 x bfloat> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %5 = call <2 x i1> @llvm.is.fpclass.v2f16(<2 x half> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %6 = call <4 x i1> @llvm.is.fpclass.v4f16(<4 x half> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %7 = call <8 x i1> @llvm.is.fpclass.v8f16(<8 x half> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %8 = call <16 x i1> @llvm.is.fpclass.v16f16(<16 x half> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %9 = call <2 x i1> @llvm.is.fpclass.v2f32(<2 x float> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call <4 x i1> @llvm.is.fpclass.v4f32(<4 x float> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %11 = call <8 x i1> @llvm.is.fpclass.v8f32(<8 x float> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %12 = call <16 x i1> @llvm.is.fpclass.v16f32(<16 x float> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %13 = call <2 x i1> @llvm.is.fpclass.v2f64(<2 x double> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %14 = call <4 x i1> @llvm.is.fpclass.v4f64(<4 x double> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %15 = call <8 x i1> @llvm.is.fpclass.v8f64(<8 x double> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %16 = call <16 x i1> @llvm.is.fpclass.v16f64(<16 x double> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i1> @llvm.is.fpclass.nxv2bf16(<vscale x 2 x bfloat> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x i1> @llvm.is.fpclass.nxv4bf16(<vscale x 4 x bfloat> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x i1> @llvm.is.fpclass.nxv8bf16(<vscale x 8 x bfloat> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %20 = call <vscale x 16 x i1> @llvm.is.fpclass.nxv16bf16(<vscale x 16 x bfloat> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %21 = call <vscale x 2 x i1> @llvm.is.fpclass.nxv2f16(<vscale x 2 x half> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %22 = call <vscale x 4 x i1> @llvm.is.fpclass.nxv4f16(<vscale x 4 x half> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %23 = call <vscale x 8 x i1> @llvm.is.fpclass.nxv8f16(<vscale x 8 x half> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %24 = call <vscale x 16 x i1> @llvm.is.fpclass.nxv16f16(<vscale x 16 x half> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i1> @llvm.is.fpclass.nxv2f32(<vscale x 2 x float> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %26 = call <vscale x 4 x i1> @llvm.is.fpclass.nxv4f32(<vscale x 4 x float> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %27 = call <vscale x 8 x i1> @llvm.is.fpclass.nxv8f32(<vscale x 8 x float> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %28 = call <vscale x 16 x i1> @llvm.is.fpclass.nxv16f32(<vscale x 16 x float> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %29 = call <vscale x 2 x i1> @llvm.is.fpclass.nxv2f64(<vscale x 2 x double> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %30 = call <vscale x 4 x i1> @llvm.is.fpclass.nxv4f64(<vscale x 4 x double> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %31 = call <vscale x 8 x i1> @llvm.is.fpclass.nxv8f64(<vscale x 8 x double> poison, /* (none) */ i32 0)
+; ARGBASED-NEXT: Cost Model: Invalid cost for instruction: %32 = call <vscale x 16 x i1> @llvm.is.fpclass.nxv16f64(<vscale x 16 x double> poison, /* (none) */ i32 0)
; ARGBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPEBASED-LABEL: 'is.fpclass'
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %1 = call <2 x i1> @llvm.vp.is.fpclass.v2bf16(<2 x bfloat> poison, i32 0, <2 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %2 = call <4 x i1> @llvm.vp.is.fpclass.v4bf16(<4 x bfloat> poison, i32 0, <4 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %3 = call <8 x i1> @llvm.vp.is.fpclass.v8bf16(<8 x bfloat> poison, i32 0, <8 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %4 = call <16 x i1> @llvm.vp.is.fpclass.v16bf16(<16 x bfloat> poison, i32 0, <16 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %5 = call <2 x i1> @llvm.vp.is.fpclass.v2f16(<2 x half> poison, i32 0, <2 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %6 = call <4 x i1> @llvm.vp.is.fpclass.v4f16(<4 x half> poison, i32 0, <4 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %7 = call <8 x i1> @llvm.vp.is.fpclass.v8f16(<8 x half> poison, i32 0, <8 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %8 = call <16 x i1> @llvm.vp.is.fpclass.v16f16(<16 x half> poison, i32 0, <16 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %9 = call <2 x i1> @llvm.vp.is.fpclass.v2f32(<2 x float> poison, i32 0, <2 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %10 = call <4 x i1> @llvm.vp.is.fpclass.v4f32(<4 x float> poison, i32 0, <4 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %11 = call <8 x i1> @llvm.vp.is.fpclass.v8f32(<8 x float> poison, i32 0, <8 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %12 = call <16 x i1> @llvm.vp.is.fpclass.v16f32(<16 x float> poison, i32 0, <16 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <2 x i1> @llvm.vp.is.fpclass.v2f64(<2 x double> poison, i32 0, <2 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %14 = call <4 x i1> @llvm.vp.is.fpclass.v4f64(<4 x double> poison, i32 0, <4 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %15 = call <8 x i1> @llvm.vp.is.fpclass.v8f64(<8 x double> poison, i32 0, <8 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %16 = call <16 x i1> @llvm.vp.is.fpclass.v16f64(<16 x double> poison, i32 0, <16 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2bf16(<vscale x 2 x bfloat> poison, i32 0, <vscale x 2 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x i1> @llvm.vp.is.fpclass.nxv4bf16(<vscale x 4 x bfloat> poison, i32 0, <vscale x 4 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x i1> @llvm.vp.is.fpclass.nxv8bf16(<vscale x 8 x bfloat> poison, i32 0, <vscale x 8 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %20 = call <vscale x 16 x i1> @llvm.vp.is.fpclass.nxv16bf16(<vscale x 16 x bfloat> poison, i32 0, <vscale x 16 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %21 = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2f16(<vscale x 2 x half> poison, i32 0, <vscale x 2 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %22 = call <vscale x 4 x i1> @llvm.vp.is.fpclass.nxv4f16(<vscale x 4 x half> poison, i32 0, <vscale x 4 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %23 = call <vscale x 8 x i1> @llvm.vp.is.fpclass.nxv8f16(<vscale x 8 x half> poison, i32 0, <vscale x 8 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %24 = call <vscale x 16 x i1> @llvm.vp.is.fpclass.nxv16f16(<vscale x 16 x half> poison, i32 0, <vscale x 16 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2f32(<vscale x 2 x float> poison, i32 0, <vscale x 2 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %26 = call <vscale x 4 x i1> @llvm.vp.is.fpclass.nxv4f32(<vscale x 4 x float> poison, i32 0, <vscale x 4 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %27 = call <vscale x 8 x i1> @llvm.vp.is.fpclass.nxv8f32(<vscale x 8 x float> poison, i32 0, <vscale x 8 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %28 = call <vscale x 16 x i1> @llvm.vp.is.fpclass.nxv16f32(<vscale x 16 x float> poison, i32 0, <vscale x 16 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %29 = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2f64(<vscale x 2 x double> poison, i32 0, <vscale x 2 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %30 = call <vscale x 4 x i1> @llvm.vp.is.fpclass.nxv4f64(<vscale x 4 x double> poison, i32 0, <vscale x 4 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %31 = call <vscale x 8 x i1> @llvm.vp.is.fpclass.nxv8f64(<vscale x 8 x double> poison, i32 0, <vscale x 8 x i1> poison, i32 poison)
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %32 = call <vscale x 16 x i1> @llvm.vp.is.fpclass.nxv16f64(<vscale x 16 x double> poison, i32 0, <vscale x 16 x i1> poison, i32 poison)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %1 = call <2 x i1> @llvm.is.fpclass.v2bf16(<2 x bfloat> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %2 = call <4 x i1> @llvm.is.fpclass.v4bf16(<4 x bfloat> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %3 = call <8 x i1> @llvm.is.fpclass.v8bf16(<8 x bfloat> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %4 = call <16 x i1> @llvm.is.fpclass.v16bf16(<16 x bfloat> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %5 = call <2 x i1> @llvm.is.fpclass.v2f16(<2 x half> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %6 = call <4 x i1> @llvm.is.fpclass.v4f16(<4 x half> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %7 = call <8 x i1> @llvm.is.fpclass.v8f16(<8 x half> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %8 = call <16 x i1> @llvm.is.fpclass.v16f16(<16 x half> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %9 = call <2 x i1> @llvm.is.fpclass.v2f32(<2 x float> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %10 = call <4 x i1> @llvm.is.fpclass.v4f32(<4 x float> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %11 = call <8 x i1> @llvm.is.fpclass.v8f32(<8 x float> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %12 = call <16 x i1> @llvm.is.fpclass.v16f32(<16 x float> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <2 x i1> @llvm.is.fpclass.v2f64(<2 x double> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %14 = call <4 x i1> @llvm.is.fpclass.v4f64(<4 x double> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %15 = call <8 x i1> @llvm.is.fpclass.v8f64(<8 x double> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %16 = call <16 x i1> @llvm.is.fpclass.v16f64(<16 x double> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i1> @llvm.is.fpclass.nxv2bf16(<vscale x 2 x bfloat> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x i1> @llvm.is.fpclass.nxv4bf16(<vscale x 4 x bfloat> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x i1> @llvm.is.fpclass.nxv8bf16(<vscale x 8 x bfloat> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %20 = call <vscale x 16 x i1> @llvm.is.fpclass.nxv16bf16(<vscale x 16 x bfloat> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %21 = call <vscale x 2 x i1> @llvm.is.fpclass.nxv2f16(<vscale x 2 x half> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %22 = call <vscale x 4 x i1> @llvm.is.fpclass.nxv4f16(<vscale x 4 x half> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %23 = call <vscale x 8 x i1> @llvm.is.fpclass.nxv8f16(<vscale x 8 x half> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %24 = call <vscale x 16 x i1> @llvm.is.fpclass.nxv16f16(<vscale x 16 x half> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i1> @llvm.is.fpclass.nxv2f32(<vscale x 2 x float> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %26 = call <vscale x 4 x i1> @llvm.is.fpclass.nxv4f32(<vscale x 4 x float> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %27 = call <vscale x 8 x i1> @llvm.is.fpclass.nxv8f32(<vscale x 8 x float> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %28 = call <vscale x 16 x i1> @llvm.is.fpclass.nxv16f32(<vscale x 16 x float> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %29 = call <vscale x 2 x i1> @llvm.is.fpclass.nxv2f64(<vscale x 2 x double> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %30 = call <vscale x 4 x i1> @llvm.is.fpclass.nxv4f64(<vscale x 4 x double> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %31 = call <vscale x 8 x i1> @llvm.is.fpclass.nxv8f64(<vscale x 8 x double> poison, /* (none) */ i32 0)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %32 = call <vscale x 16 x i1> @llvm.is.fpclass.nxv16f64(<vscale x 16 x double> poison, /* (none) */ i32 0)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i1> @llvm.vp.is.fpclass.v2bf16(<2 x bfloat> poison, i32 0, <2 x i1> poison, i32 poison)
diff --git a/llvm/test/Assembler/auto_upgrade_vp.ll b/llvm/test/Assembler/auto_upgrade_vp.ll
index e914815afd527..11b9d5f08f582 100644
--- a/llvm/test/Assembler/auto_upgrade_vp.ll
+++ b/llvm/test/Assembler/auto_upgrade_vp.ll
@@ -4,70 +4,70 @@
define void @f(<4 x i32> %x, <4 x i32> %y, <4 x i32> %z, <4 x float> %fx, <4 x float> %fy, <4 x float> %fz, <4 x ptr> %px, <4 x i1> %mask, i32 %evl) {
; CHECK-LABEL: define void @f(
; CHECK-SAME: <4 x i32> [[X:%.*]], <4 x i32> [[Y:%.*]], <4 x i32> [[Z:%.*]], <4 x float> [[FX:%.*]], <4 x float> [[FY:%.*]], <4 x float> [[FZ:%.*]], <4 x ptr> [[PX:%.*]], <4 x i1> [[MASK:%.*]], i32 [[EVL:%.*]]) {
-; CHECK-NEXT: [[TMP1:%.*]] = call <4 x i32> @llvm.vp.select.v4i32(<4 x i1> [[MASK]], <4 x i32> [[X]], <4 x i32> [[Y]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.vp.sub.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.vp.mul.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP5:%.*]] = call <4 x i32> @llvm.vp.ashr.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP6:%.*]] = call <4 x i32> @llvm.vp.lshr.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP7:%.*]] = call <4 x i32> @llvm.vp.shl.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP8:%.*]] = call <4 x i32> @llvm.vp.or.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP9:%.*]] = call <4 x i32> @llvm.vp.and.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP10:%.*]] = call <4 x i32> @llvm.vp.xor.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP11:%.*]] = call <4 x i32> @llvm.vp.abs.v4i32(<4 x i32> [[X]], i1 false, <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP12:%.*]] = call <4 x i32> @llvm.vp.smax.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP13:%.*]] = call <4 x i32> @llvm.vp.smin.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP14:%.*]] = call <4 x i32> @llvm.vp.umax.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP15:%.*]] = call <4 x i32> @llvm.vp.umin.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP16:%.*]] = call <4 x float> @llvm.vp.copysign.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP17:%.*]] = call <4 x float> @llvm.vp.minnum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP18:%.*]] = call <4 x float> @llvm.vp.maxnum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP19:%.*]] = call <4 x float> @llvm.vp.minimum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP20:%.*]] = call <4 x float> @llvm.vp.maximum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP21:%.*]] = call <4 x float> @llvm.vp.fadd.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP22:%.*]] = call <4 x float> @llvm.vp.fsub.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP23:%.*]] = call <4 x float> @llvm.vp.fmul.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP24:%.*]] = call <4 x float> @llvm.vp.fdiv.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP25:%.*]] = call <4 x float> @llvm.vp.frem.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP26:%.*]] = call <4 x float> @llvm.vp.fneg.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP27:%.*]] = call <4 x float> @llvm.vp.fabs.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP28:%.*]] = call <4 x float> @llvm.vp.sqrt.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP29:%.*]] = call <4 x float> @llvm.vp.fma.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x float> [[FZ]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP30:%.*]] = call <4 x float> @llvm.vp.fmuladd.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x float> [[FZ]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP31:%.*]] = call <4 x i16> @llvm.vp.trunc.v4i16.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP32:%.*]] = call <4 x i64> @llvm.vp.zext.v4i64.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP33:%.*]] = call <4 x i64> @llvm.vp.sext.v4i64.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP34:%.*]] = call <4 x half> @llvm.vp.fptrunc.v4f16.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP35:%.*]] = call <4 x double> @llvm.vp.fpext.v4f64.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP36:%.*]] = call <4 x i32> @llvm.vp.fptoui.v4i32.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP37:%.*]] = call <4 x i32> @llvm.vp.fptosi.v4i32.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP38:%.*]] = call <4 x float> @llvm.vp.uitofp.v4f32.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP39:%.*]] = call <4 x float> @llvm.vp.sitofp.v4f32.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP40:%.*]] = call <4 x i32> @llvm.vp.ptrtoint.v4i32.v4p0(<4 x ptr> [[PX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP41:%.*]] = call <4 x ptr> @llvm.vp.inttoptr.v4p0.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP42:%.*]] = call <4 x i1> @llvm.vp.fcmp.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], metadata !"oeq", <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP43:%.*]] = call <4 x i1> @llvm.vp.icmp.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], metadata !"eq", <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP44:%.*]] = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP45:%.*]] = call <4 x float> @llvm.vp.floor.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP46:%.*]] = call <4 x float> @llvm.vp.rint.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP47:%.*]] = call <4 x float> @llvm.vp.nearbyint.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP48:%.*]] = call <4 x float> @llvm.vp.round.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP49:%.*]] = call <4 x float> @llvm.vp.roundeven.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP50:%.*]] = call <4 x float> @llvm.vp.roundtozero.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP51:%.*]] = call <4 x i32> @llvm.vp.lrint.v4i32.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP52:%.*]] = call <4 x i64> @llvm.vp.llrint.v4i64.v4f32(<4 x float> [[FX]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP53:%.*]] = call <4 x i32> @llvm.vp.bitreverse.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP54:%.*]] = call <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP55:%.*]] = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> [[X]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP56:%.*]] = call <4 x i32> @llvm.vp.ctlz.v4i32(<4 x i32> [[X]], i1 false, <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP57:%.*]] = call <4 x i32> @llvm.vp.cttz.v4i32(<4 x i32> [[X]], i1 false, <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP58:%.*]] = call <4 x i32> @llvm.vp.sadd.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP59:%.*]] = call <4 x i32> @llvm.vp.uadd.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP60:%.*]] = call <4 x i32> @llvm.vp.ssub.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP61:%.*]] = call <4 x i32> @llvm.vp.usub.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP62:%.*]] = call <4 x i32> @llvm.vp.fshl.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i32> [[Z]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP63:%.*]] = call <4 x i32> @llvm.vp.fshr.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i32> [[Z]], <4 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[TMP64:%.*]] = call <4 x i1> @llvm.vp.is.fpclass.v4f32(<4 x float> [[FX]], i32 0, <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[TMP1:%.*]] = select <4 x i1> [[MASK]], <4 x i32> [[X]], <4 x i32> [[Y]]
+; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP3:%.*]] = sub <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP4:%.*]] = mul <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP5:%.*]] = ashr <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP6:%.*]] = lshr <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP7:%.*]] = shl <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP8:%.*]] = or <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP9:%.*]] = and <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP10:%.*]] = xor <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP11:%.*]] = call <4 x i32> @llvm.abs.v4i32(<4 x i32> [[X]], i1 false)
+; CHECK-NEXT: [[TMP12:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]])
+; CHECK-NEXT: [[TMP13:%.*]] = call <4 x i32> @llvm.smin.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]])
+; CHECK-NEXT: [[TMP14:%.*]] = call <4 x i32> @llvm.umax.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]])
+; CHECK-NEXT: [[TMP15:%.*]] = call <4 x i32> @llvm.umin.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]])
+; CHECK-NEXT: [[TMP16:%.*]] = call <4 x float> @llvm.copysign.v4f32(<4 x float> [[FX]], <4 x float> [[FY]])
+; CHECK-NEXT: [[TMP17:%.*]] = call <4 x float> @llvm.minnum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]])
+; CHECK-NEXT: [[TMP18:%.*]] = call <4 x float> @llvm.maxnum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]])
+; CHECK-NEXT: [[TMP19:%.*]] = call <4 x float> @llvm.minimum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]])
+; CHECK-NEXT: [[TMP20:%.*]] = call <4 x float> @llvm.maximum.v4f32(<4 x float> [[FX]], <4 x float> [[FY]])
+; CHECK-NEXT: [[TMP21:%.*]] = fadd <4 x float> [[FX]], [[FY]]
+; CHECK-NEXT: [[TMP22:%.*]] = fsub <4 x float> [[FX]], [[FY]]
+; CHECK-NEXT: [[TMP23:%.*]] = fmul <4 x float> [[FX]], [[FY]]
+; CHECK-NEXT: [[TMP24:%.*]] = fdiv <4 x float> [[FX]], [[FY]]
+; CHECK-NEXT: [[TMP25:%.*]] = frem <4 x float> [[FX]], [[FY]]
+; CHECK-NEXT: [[TMP26:%.*]] = fneg <4 x float> [[FX]]
+; CHECK-NEXT: [[TMP27:%.*]] = call <4 x float> @llvm.fabs.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP28:%.*]] = call <4 x float> @llvm.sqrt.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP29:%.*]] = call <4 x float> @llvm.fma.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x float> [[FZ]])
+; CHECK-NEXT: [[TMP30:%.*]] = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> [[FX]], <4 x float> [[FY]], <4 x float> [[FZ]])
+; CHECK-NEXT: [[TMP31:%.*]] = trunc <4 x i32> [[X]] to <4 x i16>
+; CHECK-NEXT: [[TMP32:%.*]] = zext <4 x i32> [[X]] to <4 x i64>
+; CHECK-NEXT: [[TMP33:%.*]] = sext <4 x i32> [[X]] to <4 x i64>
+; CHECK-NEXT: [[TMP34:%.*]] = fptrunc <4 x float> [[FX]] to <4 x half>
+; CHECK-NEXT: [[TMP35:%.*]] = fpext <4 x float> [[FX]] to <4 x double>
+; CHECK-NEXT: [[TMP36:%.*]] = fptoui <4 x float> [[FX]] to <4 x i32>
+; CHECK-NEXT: [[TMP37:%.*]] = fptosi <4 x float> [[FX]] to <4 x i32>
+; CHECK-NEXT: [[TMP38:%.*]] = uitofp <4 x i32> [[X]] to <4 x float>
+; CHECK-NEXT: [[TMP39:%.*]] = sitofp <4 x i32> [[X]] to <4 x float>
+; CHECK-NEXT: [[TMP40:%.*]] = ptrtoint <4 x ptr> [[PX]] to <4 x i32>
+; CHECK-NEXT: [[TMP41:%.*]] = inttoptr <4 x i32> [[X]] to <4 x ptr>
+; CHECK-NEXT: [[TMP42:%.*]] = fcmp oeq <4 x float> [[FX]], [[FY]]
+; CHECK-NEXT: [[TMP43:%.*]] = icmp eq <4 x i32> [[X]], [[Y]]
+; CHECK-NEXT: [[TMP44:%.*]] = call <4 x float> @llvm.ceil.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP45:%.*]] = call <4 x float> @llvm.floor.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP46:%.*]] = call <4 x float> @llvm.rint.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP47:%.*]] = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP48:%.*]] = call <4 x float> @llvm.round.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP49:%.*]] = call <4 x float> @llvm.roundeven.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP50:%.*]] = call <4 x float> @llvm.trunc.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP51:%.*]] = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP52:%.*]] = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> [[FX]])
+; CHECK-NEXT: [[TMP53:%.*]] = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> [[X]])
+; CHECK-NEXT: [[TMP54:%.*]] = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> [[X]])
+; CHECK-NEXT: [[TMP55:%.*]] = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> [[X]])
+; CHECK-NEXT: [[TMP56:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[X]], i1 false)
+; CHECK-NEXT: [[TMP57:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[X]], i1 false)
+; CHECK-NEXT: [[TMP58:%.*]] = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]])
+; CHECK-NEXT: [[TMP59:%.*]] = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]])
+; CHECK-NEXT: [[TMP60:%.*]] = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]])
+; CHECK-NEXT: [[TMP61:%.*]] = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]])
+; CHECK-NEXT: [[TMP62:%.*]] = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i32> [[Z]])
+; CHECK-NEXT: [[TMP63:%.*]] = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> [[X]], <4 x i32> [[Y]], <4 x i32> [[Z]])
+; CHECK-NEXT: [[TMP64:%.*]] = call <4 x i1> @llvm.is.fpclass.v4f32(<4 x float> [[FX]], /* (none) */ i32 0)
; CHECK-NEXT: ret void
;
call <4 x i32> @llvm.vp.select(<4 x i1> %mask, <4 x i32> %x, <4 x i32> %y, i32 %evl)
@@ -140,7 +140,7 @@ define void @f(<4 x i32> %x, <4 x i32> %y, <4 x i32> %z, <4 x float> %fx, <4 x f
define <4 x float> @fmfs(<4 x float> %x, <4 x float> %y, <4 x i1> %mask, i32 %evl) {
; CHECK-LABEL: define <4 x float> @fmfs(
; CHECK-SAME: <4 x float> [[X:%.*]], <4 x float> [[Y:%.*]], <4 x i1> [[MASK:%.*]], i32 [[EVL:%.*]]) {
-; CHECK-NEXT: [[RES:%.*]] = call fast <4 x float> @llvm.vp.fadd.v4f32(<4 x float> [[X]], <4 x float> [[Y]], <4 x i1> [[MASK]], i32 [[EVL]])
+; CHECK-NEXT: [[RES:%.*]] = fadd fast <4 x float> [[X]], [[Y]]
; CHECK-NEXT: ret <4 x float> [[RES]]
;
%res = call fast <4 x float> @llvm.vp.fadd(<4 x float> %x, <4 x float> %y, <4 x i1> %mask, i32 %evl)
diff --git a/llvm/test/CodeGen/VE/Packed/vp_add.ll b/llvm/test/CodeGen/VE/Packed/vp_add.ll
index 3e64d6fe9b1db..e4d0951b8aa32 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_add.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_add.ll
@@ -6,11 +6,9 @@ declare <512 x i32> @llvm.vp.add.v512i32(<512 x i32>, <512 x i32>, <512 x i1>, i
define fastcc <512 x i32> @test_vp_add_v512i32_vv(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_add_v512i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvaddu %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvaddu %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.add.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -20,14 +18,12 @@ define fastcc <512 x i32> @test_vp_add_v512i32_rv(i32 %s0, <512 x i32> %i1, <512
; CHECK-LABEL: test_vp_add_v512i32_rv:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvaddu %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvaddu %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x i32> undef, i32 %s0, i32 0
%i0 = shufflevector <512 x i32> %xins, <512 x i32> undef, <512 x i32> zeroinitializer
@@ -39,14 +35,12 @@ define fastcc <512 x i32> @test_vp_add_v512i32_vr(<512 x i32> %i0, i32 %s1, <512
; CHECK-LABEL: test_vp_add_v512i32_vr:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvaddu %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvaddu %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x i32> undef, i32 %s1, i32 0
%i1 = shufflevector <512 x i32> %yins, <512 x i32> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_and.ll b/llvm/test/CodeGen/VE/Packed/vp_and.ll
index 2c9aa57001e08..4a7fe76b8babc 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_and.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_and.ll
@@ -6,11 +6,9 @@ declare <512 x i32> @llvm.vp.and.v512i32(<512 x i32>, <512 x i32>, <512 x i1>, i
define fastcc <512 x i32> @test_vp_and_v512i32_vv(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_and_v512i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvand %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvand %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.and.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -20,14 +18,12 @@ define fastcc <512 x i32> @test_vp_and_v512i32_rv(i32 %s0, <512 x i32> %i1, <512
; CHECK-LABEL: test_vp_and_v512i32_rv:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvand %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvand %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x i32> undef, i32 %s0, i32 0
%i0 = shufflevector <512 x i32> %xins, <512 x i32> undef, <512 x i32> zeroinitializer
@@ -39,14 +35,12 @@ define fastcc <512 x i32> @test_vp_and_v512i32_vr(<512 x i32> %i0, i32 %s1, <512
; CHECK-LABEL: test_vp_and_v512i32_vr:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvand %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvand %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x i32> undef, i32 %s1, i32 0
%i1 = shufflevector <512 x i32> %yins, <512 x i32> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_fadd.ll b/llvm/test/CodeGen/VE/Packed/vp_fadd.ll
index be201ed461a98..8ccaab7d40e8d 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_fadd.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_fadd.ll
@@ -6,11 +6,9 @@ declare <512 x float> @llvm.vp.fadd.v512f32(<512 x float>, <512 x float>, <512 x
define fastcc <512 x float> @test_vp_fadd_v512f32_vv(<512 x float> %i0, <512 x float> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v512f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvfadd %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvfadd %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x float> @llvm.vp.fadd.v512f32(<512 x float> %i0, <512 x float> %i1, <512 x i1> %m, i32 %n)
ret <512 x float> %r0
@@ -19,14 +17,12 @@ define fastcc <512 x float> @test_vp_fadd_v512f32_vv(<512 x float> %i0, <512 x f
define fastcc <512 x float> @test_vp_fadd_v512f32_rv(float %s0, <512 x float> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v512f32_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s2, %s0, (32)1
+; CHECK-NEXT: and %s1, %s0, (32)1
; CHECK-NEXT: srl %s0, %s0, 32
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfadd %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvfadd %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x float> undef, float %s0, i32 0
%i0 = shufflevector <512 x float> %xins, <512 x float> undef, <512 x i32> zeroinitializer
@@ -37,14 +33,12 @@ define fastcc <512 x float> @test_vp_fadd_v512f32_rv(float %s0, <512 x float> %i
define fastcc <512 x float> @test_vp_fadd_v512f32_vr(<512 x float> %i0, float %s1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v512f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s2, %s0, (32)1
+; CHECK-NEXT: and %s1, %s0, (32)1
; CHECK-NEXT: srl %s0, %s0, 32
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfadd %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvfadd %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x float> undef, float %s1, i32 0
%i1 = shufflevector <512 x float> %yins, <512 x float> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_fdiv.ll b/llvm/test/CodeGen/VE/Packed/vp_fdiv.ll
index dac6fc7296d28..f31f6c5a55258 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_fdiv.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_fdiv.ll
@@ -6,18 +6,13 @@ declare <512 x float> @llvm.vp.fdiv.v512f32(<512 x float>, <512 x float>, <512 x
define fastcc <512 x float> @test_vp_fdiv_v512f32_vv(<512 x float> %i0, <512 x float> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v512f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s0, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
-; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vshf %v2, %v1, %v1, 4
-; CHECK-NEXT: vshf %v3, %v0, %v0, 4
-; CHECK-NEXT: vfdiv.s %v2, %v3, %v2, %vm3
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfdiv.s %v0, %v0, %v1, %vm2
-; CHECK-NEXT: vshf %v0, %v2, %v0, 8
+; CHECK-NEXT: vfdiv.s %v2, %v0, %v1, %vm0
+; CHECK-NEXT: vshf %v1, %v1, %v1, 4
+; CHECK-NEXT: vshf %v0, %v0, %v0, 4
+; CHECK-NEXT: vfdiv.s %v0, %v0, %v1, %vm0
+; CHECK-NEXT: vshf %v0, %v0, %v2, 8
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x float> @llvm.vp.fdiv.v512f32(<512 x float> %i0, <512 x float> %i1, <512 x i1> %m, i32 %n)
ret <512 x float> %r0
@@ -26,24 +21,16 @@ define fastcc <512 x float> @test_vp_fdiv_v512f32_vv(<512 x float> %i0, <512 x f
define fastcc <512 x float> @test_vp_fdiv_v512f32_rv(float %s0, <512 x float> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v512f32_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s2, %s0, (32)1
+; CHECK-NEXT: and %s1, %s0, (32)1
; CHECK-NEXT: srl %s0, %s0, 32
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
-; CHECK-NEXT: vbrd %v1, %s0
-; CHECK-NEXT: adds.w.sx %s0, 1, %s1
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
-; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfdiv.s %v2, %v1, %v0, %vm2
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
+; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: vfdiv.s %v2, %v1, %v0, %vm0
; CHECK-NEXT: vshf %v1, %v1, %v1, 4
; CHECK-NEXT: vshf %v0, %v0, %v0, 4
-; CHECK-NEXT: vfdiv.s %v0, %v1, %v0, %vm3
-; CHECK-NEXT: lvl %s0
+; CHECK-NEXT: vfdiv.s %v0, %v1, %v0, %vm0
; CHECK-NEXT: vshf %v0, %v0, %v2, 8
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x float> undef, float %s0, i32 0
@@ -55,24 +42,16 @@ define fastcc <512 x float> @test_vp_fdiv_v512f32_rv(float %s0, <512 x float> %i
define fastcc <512 x float> @test_vp_fdiv_v512f32_vr(<512 x float> %i0, float %s1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v512f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s2, %s0, (32)1
+; CHECK-NEXT: and %s1, %s0, (32)1
; CHECK-NEXT: srl %s0, %s0, 32
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
-; CHECK-NEXT: vbrd %v1, %s0
-; CHECK-NEXT: adds.w.sx %s0, 1, %s1
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
-; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfdiv.s %v2, %v0, %v1, %vm2
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
+; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: vfdiv.s %v2, %v0, %v1, %vm0
; CHECK-NEXT: vshf %v1, %v1, %v1, 4
; CHECK-NEXT: vshf %v0, %v0, %v0, 4
-; CHECK-NEXT: vfdiv.s %v0, %v0, %v1, %vm3
-; CHECK-NEXT: lvl %s0
+; CHECK-NEXT: vfdiv.s %v0, %v0, %v1, %vm0
; CHECK-NEXT: vshf %v0, %v0, %v2, 8
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x float> undef, float %s1, i32 0
diff --git a/llvm/test/CodeGen/VE/Packed/vp_fmul.ll b/llvm/test/CodeGen/VE/Packed/vp_fmul.ll
index 853b0ee9a84e9..45809967099ce 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_fmul.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_fmul.ll
@@ -6,11 +6,9 @@ declare <512 x float> @llvm.vp.fmul.v512f32(<512 x float>, <512 x float>, <512 x
define fastcc <512 x float> @test_vp_fmul_v512f32_vv(<512 x float> %i0, <512 x float> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v512f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvfmul %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvfmul %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x float> @llvm.vp.fmul.v512f32(<512 x float> %i0, <512 x float> %i1, <512 x i1> %m, i32 %n)
ret <512 x float> %r0
@@ -19,14 +17,12 @@ define fastcc <512 x float> @test_vp_fmul_v512f32_vv(<512 x float> %i0, <512 x f
define fastcc <512 x float> @test_vp_fmul_v512f32_rv(float %s0, <512 x float> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v512f32_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s2, %s0, (32)1
+; CHECK-NEXT: and %s1, %s0, (32)1
; CHECK-NEXT: srl %s0, %s0, 32
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfmul %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvfmul %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x float> undef, float %s0, i32 0
%i0 = shufflevector <512 x float> %xins, <512 x float> undef, <512 x i32> zeroinitializer
@@ -37,14 +33,12 @@ define fastcc <512 x float> @test_vp_fmul_v512f32_rv(float %s0, <512 x float> %i
define fastcc <512 x float> @test_vp_fmul_v512f32_vr(<512 x float> %i0, float %s1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v512f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s2, %s0, (32)1
+; CHECK-NEXT: and %s1, %s0, (32)1
; CHECK-NEXT: srl %s0, %s0, 32
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfmul %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvfmul %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x float> undef, float %s1, i32 0
%i1 = shufflevector <512 x float> %yins, <512 x float> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_fsub.ll b/llvm/test/CodeGen/VE/Packed/vp_fsub.ll
index e5fd8bd7456c6..4460cb1567235 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_fsub.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_fsub.ll
@@ -6,11 +6,9 @@ declare <512 x float> @llvm.vp.fsub.v512f32(<512 x float>, <512 x float>, <512 x
define fastcc <512 x float> @test_vp_fsub_v512f32_vv(<512 x float> %i0, <512 x float> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v512f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvfsub %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvfsub %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x float> @llvm.vp.fsub.v512f32(<512 x float> %i0, <512 x float> %i1, <512 x i1> %m, i32 %n)
ret <512 x float> %r0
@@ -19,14 +17,12 @@ define fastcc <512 x float> @test_vp_fsub_v512f32_vv(<512 x float> %i0, <512 x f
define fastcc <512 x float> @test_vp_fsub_v512f32_rv(float %s0, <512 x float> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v512f32_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s2, %s0, (32)1
+; CHECK-NEXT: and %s1, %s0, (32)1
; CHECK-NEXT: srl %s0, %s0, 32
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfsub %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvfsub %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x float> undef, float %s0, i32 0
%i0 = shufflevector <512 x float> %xins, <512 x float> undef, <512 x i32> zeroinitializer
@@ -37,17 +33,13 @@ define fastcc <512 x float> @test_vp_fsub_v512f32_rv(float %s0, <512 x float> %i
define fastcc <512 x float> @test_vp_fsub_v512f32_vr(<512 x float> %i0, float %s1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v512f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s2, %s0, (32)1
+; CHECK-NEXT: and %s1, %s0, (32)1
; CHECK-NEXT: srl %s0, %s0, 32
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
+; CHECK-NEXT: lvl %s1
; CHECK-NEXT: vbrd %v1, %s0
-; CHECK-NEXT: adds.w.sx %s0, 1, %s1
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
-; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvfsub %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvfsub %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x float> undef, float %s1, i32 0
%i1 = shufflevector <512 x float> %yins, <512 x float> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_mul.ll b/llvm/test/CodeGen/VE/Packed/vp_mul.ll
index 32c1eb92795eb..e738cc5f1736c 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_mul.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_mul.ll
@@ -6,19 +6,13 @@ declare <512 x i32> @llvm.vp.mul.v512i32(<512 x i32>, <512 x i32>, <512 x i1>, i
define fastcc <512 x i32> @test_vp_v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v512i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s1, 1, %s0
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
-; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vshf %v2, %v1, %v1, 0
-; CHECK-NEXT: vshf %v3, %v0, %v0, 0
-; CHECK-NEXT: vmuls.w.sx %v2, %v3, %v2, %vm2
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vmuls.w.sx %v0, %v0, %v1, %vm3
-; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vshf %v0, %v0, %v2, 13
+; CHECK-NEXT: vmuls.w.sx %v2, %v0, %v1, %vm0
+; CHECK-NEXT: vshf %v1, %v1, %v1, 0
+; CHECK-NEXT: vshf %v0, %v0, %v0, 0
+; CHECK-NEXT: vmuls.w.sx %v0, %v0, %v1, %vm0
+; CHECK-NEXT: vshf %v0, %v2, %v0, 13
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.mul.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -27,19 +21,13 @@ define fastcc <512 x i32> @test_vp_v512i32(<512 x i32> %i0, <512 x i32> %i1, <51
define fastcc <512 x i32> @test_vp_v512i32_vmp0(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v512i32_vmp0:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s1, 1, %s0
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
-; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vshf %v2, %v1, %v1, 0
-; CHECK-NEXT: vshf %v3, %v0, %v0, 0
-; CHECK-NEXT: vmuls.w.sx %v2, %v3, %v2, %vm0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
+; CHECK-NEXT: vmuls.w.sx %v2, %v0, %v1, %vm0
+; CHECK-NEXT: vshf %v1, %v1, %v1, 0
+; CHECK-NEXT: vshf %v0, %v0, %v0, 0
; CHECK-NEXT: vmuls.w.sx %v0, %v0, %v1, %vm0
-; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vshf %v0, %v0, %v2, 13
+; CHECK-NEXT: vshf %v0, %v2, %v0, 13
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.mul.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> splat (i1 true), i32 %n)
ret <512 x i32> %r0
diff --git a/llvm/test/CodeGen/VE/Packed/vp_or.ll b/llvm/test/CodeGen/VE/Packed/vp_or.ll
index db46aa2d86e54..cbd47969e301f 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_or.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_or.ll
@@ -6,11 +6,9 @@ declare <512 x i32> @llvm.vp.or.v512i32(<512 x i32>, <512 x i32>, <512 x i1>, i3
define fastcc <512 x i32> @test_vp_or_v512i32_vv(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_or_v512i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvor %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvor %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.or.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -20,14 +18,12 @@ define fastcc <512 x i32> @test_vp_or_v512i32_rv(i32 %s0, <512 x i32> %i1, <512
; CHECK-LABEL: test_vp_or_v512i32_rv:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvor %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvor %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x i32> undef, i32 %s0, i32 0
%i0 = shufflevector <512 x i32> %xins, <512 x i32> undef, <512 x i32> zeroinitializer
@@ -39,14 +35,12 @@ define fastcc <512 x i32> @test_vp_or_v512i32_vr(<512 x i32> %i0, i32 %s1, <512
; CHECK-LABEL: test_vp_or_v512i32_vr:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvor %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvor %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x i32> undef, i32 %s1, i32 0
%i1 = shufflevector <512 x i32> %yins, <512 x i32> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_shl.ll b/llvm/test/CodeGen/VE/Packed/vp_shl.ll
index 3697c6ec92b38..90ce8aec931bf 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_shl.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_shl.ll
@@ -6,11 +6,9 @@ declare <512 x i32> @llvm.vp.shl.v512i32(<512 x i32>, <512 x i32>, <512 x i1>, i
define fastcc <512 x i32> @test_vp_shl_v512i32_vv(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_shl_v512i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsll %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvsll %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.shl.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -20,17 +18,13 @@ define fastcc <512 x i32> @test_vp_shl_v512i32_rv(i32 %s0, <512 x i32> %i1, <512
; CHECK-LABEL: test_vp_shl_v512i32_rv:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
+; CHECK-NEXT: lvl %s1
; CHECK-NEXT: vbrd %v1, %s0
-; CHECK-NEXT: adds.w.sx %s0, 1, %s1
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
-; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsll %v0, %v1, %v0, %vm2
+; CHECK-NEXT: pvsll %v0, %v1, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x i32> undef, i32 %s0, i32 0
%i0 = shufflevector <512 x i32> %xins, <512 x i32> undef, <512 x i32> zeroinitializer
@@ -42,14 +36,12 @@ define fastcc <512 x i32> @test_vp_shl_v512i32_vr(<512 x i32> %i0, i32 %s1, <512
; CHECK-LABEL: test_vp_shl_v512i32_vr:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvsll %v0, %v0, %s0, %vm2
+; CHECK-NEXT: pvsll %v0, %v0, %s0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x i32> undef, i32 %s1, i32 0
%i1 = shufflevector <512 x i32> %yins, <512 x i32> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_sra.ll b/llvm/test/CodeGen/VE/Packed/vp_sra.ll
index 3fe690c97d600..724d44f8d1e15 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_sra.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_sra.ll
@@ -6,11 +6,9 @@ declare <512 x i32> @llvm.vp.ashr.v512i32(<512 x i32>, <512 x i32>, <512 x i1>,
define fastcc <512 x i32> @test_vp_ashr_v512i32_vv(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_ashr_v512i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsra %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvsra %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.ashr.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -20,17 +18,13 @@ define fastcc <512 x i32> @test_vp_ashr_v512i32_rv(i32 %s0, <512 x i32> %i1, <51
; CHECK-LABEL: test_vp_ashr_v512i32_rv:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
+; CHECK-NEXT: lvl %s1
; CHECK-NEXT: vbrd %v1, %s0
-; CHECK-NEXT: adds.w.sx %s0, 1, %s1
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
-; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsra %v0, %v1, %v0, %vm2
+; CHECK-NEXT: pvsra %v0, %v1, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x i32> undef, i32 %s0, i32 0
%i0 = shufflevector <512 x i32> %xins, <512 x i32> undef, <512 x i32> zeroinitializer
@@ -42,14 +36,12 @@ define fastcc <512 x i32> @test_vp_ashr_v512i32_vr(<512 x i32> %i0, i32 %s1, <51
; CHECK-LABEL: test_vp_ashr_v512i32_vr:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvsra %v0, %v0, %s0, %vm2
+; CHECK-NEXT: pvsra %v0, %v0, %s0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x i32> undef, i32 %s1, i32 0
%i1 = shufflevector <512 x i32> %yins, <512 x i32> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_srl.ll b/llvm/test/CodeGen/VE/Packed/vp_srl.ll
index f835549afc9c9..8932364eb4cc9 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_srl.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_srl.ll
@@ -6,11 +6,9 @@ declare <512 x i32> @llvm.vp.lshr.v512i32(<512 x i32>, <512 x i32>, <512 x i1>,
define fastcc <512 x i32> @test_vp_lshr_v512i32_vv(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_lshr_v512i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsrl %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvsrl %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.lshr.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -20,17 +18,13 @@ define fastcc <512 x i32> @test_vp_lshr_v512i32_rv(i32 %s0, <512 x i32> %i1, <51
; CHECK-LABEL: test_vp_lshr_v512i32_rv:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
+; CHECK-NEXT: lvl %s1
; CHECK-NEXT: vbrd %v1, %s0
-; CHECK-NEXT: adds.w.sx %s0, 1, %s1
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
-; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsrl %v0, %v1, %v0, %vm2
+; CHECK-NEXT: pvsrl %v0, %v1, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x i32> undef, i32 %s0, i32 0
%i0 = shufflevector <512 x i32> %xins, <512 x i32> undef, <512 x i32> zeroinitializer
@@ -42,14 +36,12 @@ define fastcc <512 x i32> @test_vp_lshr_v512i32_vr(<512 x i32> %i0, i32 %s1, <51
; CHECK-LABEL: test_vp_lshr_v512i32_vr:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvsrl %v0, %v0, %s0, %vm2
+; CHECK-NEXT: pvsrl %v0, %v0, %s0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x i32> undef, i32 %s1, i32 0
%i1 = shufflevector <512 x i32> %yins, <512 x i32> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_sub.ll b/llvm/test/CodeGen/VE/Packed/vp_sub.ll
index 8ebf8ef8b3c26..f1fecc79d6177 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_sub.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_sub.ll
@@ -6,11 +6,9 @@ declare <512 x i32> @llvm.vp.sub.v512i32(<512 x i32>, <512 x i32>, <512 x i1>, i
define fastcc <512 x i32> @test_vp_sub_v512i32_vv(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_sub_v512i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsubu %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvsubu %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.sub.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -20,14 +18,12 @@ define fastcc <512 x i32> @test_vp_sub_v512i32_rv(i32 %s0, <512 x i32> %i1, <512
; CHECK-LABEL: test_vp_sub_v512i32_rv:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvsubu %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvsubu %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x i32> undef, i32 %s0, i32 0
%i0 = shufflevector <512 x i32> %xins, <512 x i32> undef, <512 x i32> zeroinitializer
@@ -39,17 +35,13 @@ define fastcc <512 x i32> @test_vp_sub_v512i32_vr(<512 x i32> %i0, i32 %s1, <512
; CHECK-LABEL: test_vp_sub_v512i32_vr:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
+; CHECK-NEXT: lvl %s1
; CHECK-NEXT: vbrd %v1, %s0
-; CHECK-NEXT: adds.w.sx %s0, 1, %s1
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
-; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsubu %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvsubu %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x i32> undef, i32 %s1, i32 0
%i1 = shufflevector <512 x i32> %yins, <512 x i32> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Packed/vp_xor.ll b/llvm/test/CodeGen/VE/Packed/vp_xor.ll
index 51b1b7f5bfa7a..600634d5ed792 100644
--- a/llvm/test/CodeGen/VE/Packed/vp_xor.ll
+++ b/llvm/test/CodeGen/VE/Packed/vp_xor.ll
@@ -6,11 +6,9 @@ declare <512 x i32> @llvm.vp.xor.v512i32(<512 x i32>, <512 x i32>, <512 x i1>, i
define fastcc <512 x i32> @test_vp_xor_v512i32_vv(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_xor_v512i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: adds.w.sx %s0, 1, %s0
-; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: srl %s0, %s0, 1
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvxor %v0, %v0, %v1, %vm2
+; CHECK-NEXT: pvxor %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <512 x i32> @llvm.vp.xor.v512i32(<512 x i32> %i0, <512 x i32> %i1, <512 x i1> %m, i32 %n)
ret <512 x i32> %r0
@@ -20,14 +18,12 @@ define fastcc <512 x i32> @test_vp_xor_v512i32_rv(i32 %s0, <512 x i32> %i1, <512
; CHECK-LABEL: test_vp_xor_v512i32_rv:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvxor %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvxor %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <512 x i32> undef, i32 %s0, i32 0
%i0 = shufflevector <512 x i32> %xins, <512 x i32> undef, <512 x i32> zeroinitializer
@@ -39,14 +35,12 @@ define fastcc <512 x i32> @test_vp_xor_v512i32_vr(<512 x i32> %i0, i32 %s1, <512
; CHECK-LABEL: test_vp_xor_v512i32_vr:
; CHECK: # %bb.0:
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: sll %s2, %s0, 32
+; CHECK-NEXT: sll %s1, %s0, 32
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: or %s0, %s0, %s2
-; CHECK-NEXT: adds.w.sx %s1, 1, %s1
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: srl %s1, %s1, 1
+; CHECK-NEXT: or %s0, %s0, %s1
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvxor %v0, %s0, %v0, %vm2
+; CHECK-NEXT: pvxor %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <512 x i32> undef, i32 %s1, i32 0
%i1 = shufflevector <512 x i32> %yins, <512 x i32> undef, <512 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Vector/vp_add.ll b/llvm/test/CodeGen/VE/Vector/vp_add.ll
index bd6f25bdacbca..259f65c382f29 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_add.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_add.ll
@@ -5,9 +5,9 @@ declare <256 x i32> @llvm.vp.add.v256i32(<256 x i32>, <256 x i32>, <256 x i1>, i
define fastcc <256 x i32> @test_vp_add_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_add_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vadds.w.sx %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vadds.w.sx %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.add.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -19,9 +19,9 @@ declare <256 x i64> @llvm.vp.add.v256i64(<256 x i64>, <256 x i64>, <256 x i1>, i
define fastcc <256 x i64> @test_vp_int_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_int_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vadds.l %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vadds.l %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.add.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_and.ll b/llvm/test/CodeGen/VE/Vector/vp_and.ll
index b28c486527825..cb3bd715271b0 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_and.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_and.ll
@@ -5,9 +5,9 @@ declare <256 x i32> @llvm.vp.and.v256i32(<256 x i32>, <256 x i32>, <256 x i1>, i
define fastcc <256 x i32> @test_vp_and_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_and_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvand.lo %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvand.lo %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.and.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -19,9 +19,9 @@ declare <256 x i64> @llvm.vp.and.v256i64(<256 x i64>, <256 x i64>, <256 x i1>, i
define fastcc <256 x i64> @test_vp_int_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_int_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vand %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vand %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.and.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_ashr.ll b/llvm/test/CodeGen/VE/Vector/vp_ashr.ll
index fe7ad8d1b5a96..ae8d948e6682d 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_ashr.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_ashr.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.ashr.v256i32(<256 x i32>, <256 x i32>, <256 x i1>,
define fastcc <256 x i32> @test_vp_int(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_int:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsra.lo %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvsra.lo %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.ashr.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.ashr.v256i64(<256 x i64>, <256 x i64>, <256 x i1>,
define fastcc <256 x i64> @test_vp_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vsra.l %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vsra.l %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.ashr.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_fadd.ll b/llvm/test/CodeGen/VE/Vector/vp_fadd.ll
index 9de2b26074e0e..c850e25bdf8cf 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_fadd.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_fadd.ll
@@ -6,9 +6,9 @@ declare <256 x float> @llvm.vp.fadd.v256f32(<256 x float>, <256 x float>, <256 x
define fastcc <256 x float> @test_vp_fadd_v256f32_vv(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v256f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvfadd.up %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvfadd.up %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x float> @llvm.vp.fadd.v256f32(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %n)
ret <256 x float> %r0
@@ -17,9 +17,9 @@ define fastcc <256 x float> @test_vp_fadd_v256f32_vv(<256 x float> %i0, <256 x f
define fastcc <256 x float> @test_vp_fadd_v256f32_rv(float %s0, <256 x float> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v256f32_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfadd.up %v0, %s0, %v0, %vm1
+; CHECK-NEXT: pvfadd.up %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x float> undef, float %s0, i32 0
%i0 = shufflevector <256 x float> %xins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -30,9 +30,9 @@ define fastcc <256 x float> @test_vp_fadd_v256f32_rv(float %s0, <256 x float> %i
define fastcc <256 x float> @test_vp_fadd_v256f32_vr(<256 x float> %i0, float %s1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v256f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfadd.up %v0, %s0, %v0, %vm1
+; CHECK-NEXT: pvfadd.up %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x float> undef, float %s1, i32 0
%i1 = shufflevector <256 x float> %yins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -46,9 +46,9 @@ declare <256 x double> @llvm.vp.fadd.v256f64(<256 x double>, <256 x double>, <25
define fastcc <256 x double> @test_vp_fadd_v256f64_vv(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v256f64_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfadd.d %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vfadd.d %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x double> @llvm.vp.fadd.v256f64(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %n)
ret <256 x double> %r0
@@ -57,9 +57,9 @@ define fastcc <256 x double> @test_vp_fadd_v256f64_vv(<256 x double> %i0, <256 x
define fastcc <256 x double> @test_vp_fadd_v256f64_rv(double %s0, <256 x double> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v256f64_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfadd.d %v0, %s0, %v0, %vm1
+; CHECK-NEXT: vfadd.d %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x double> undef, double %s0, i32 0
%i0 = shufflevector <256 x double> %xins, <256 x double> undef, <256 x i32> zeroinitializer
@@ -70,9 +70,9 @@ define fastcc <256 x double> @test_vp_fadd_v256f64_rv(double %s0, <256 x double>
define fastcc <256 x double> @test_vp_fadd_v256f64_vr(<256 x double> %i0, double %s1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fadd_v256f64_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfadd.d %v0, %s0, %v0, %vm1
+; CHECK-NEXT: vfadd.d %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x double> undef, double %s1, i32 0
%i1 = shufflevector <256 x double> %yins, <256 x double> undef, <256 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Vector/vp_fdiv.ll b/llvm/test/CodeGen/VE/Vector/vp_fdiv.ll
index 40e065a5fe59e..d409d0e089bb7 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_fdiv.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_fdiv.ll
@@ -6,9 +6,9 @@ declare <256 x float> @llvm.vp.fdiv.v256f32(<256 x float>, <256 x float>, <256 x
define fastcc <256 x float> @test_vp_fdiv_v256f32_vv(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v256f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfdiv.s %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vfdiv.s %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x float> @llvm.vp.fdiv.v256f32(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %n)
ret <256 x float> %r0
@@ -17,9 +17,9 @@ define fastcc <256 x float> @test_vp_fdiv_v256f32_vv(<256 x float> %i0, <256 x f
define fastcc <256 x float> @test_vp_fdiv_v256f32_rv(float %s0, <256 x float> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v256f32_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfdiv.s %v0, %s0, %v0, %vm1
+; CHECK-NEXT: vfdiv.s %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x float> undef, float %s0, i32 0
%i0 = shufflevector <256 x float> %xins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -30,9 +30,9 @@ define fastcc <256 x float> @test_vp_fdiv_v256f32_rv(float %s0, <256 x float> %i
define fastcc <256 x float> @test_vp_fdiv_v256f32_vr(<256 x float> %i0, float %s1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v256f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfdiv.s %v0, %v0, %s0, %vm1
+; CHECK-NEXT: vfdiv.s %v0, %v0, %s0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x float> undef, float %s1, i32 0
%i1 = shufflevector <256 x float> %yins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -46,9 +46,9 @@ declare <256 x double> @llvm.vp.fdiv.v256f64(<256 x double>, <256 x double>, <25
define fastcc <256 x double> @test_vp_fdiv_v256f64_vv(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v256f64_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfdiv.d %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vfdiv.d %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x double> @llvm.vp.fdiv.v256f64(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %n)
ret <256 x double> %r0
@@ -57,9 +57,9 @@ define fastcc <256 x double> @test_vp_fdiv_v256f64_vv(<256 x double> %i0, <256 x
define fastcc <256 x double> @test_vp_fdiv_v256f64_rv(double %s0, <256 x double> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v256f64_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfdiv.d %v0, %s0, %v0, %vm1
+; CHECK-NEXT: vfdiv.d %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x double> undef, double %s0, i32 0
%i0 = shufflevector <256 x double> %xins, <256 x double> undef, <256 x i32> zeroinitializer
@@ -70,9 +70,9 @@ define fastcc <256 x double> @test_vp_fdiv_v256f64_rv(double %s0, <256 x double>
define fastcc <256 x double> @test_vp_fdiv_v256f64_vr(<256 x double> %i0, double %s1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fdiv_v256f64_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfdiv.d %v0, %v0, %s0, %vm1
+; CHECK-NEXT: vfdiv.d %v0, %v0, %s0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x double> undef, double %s1, i32 0
%i1 = shufflevector <256 x double> %yins, <256 x double> undef, <256 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Vector/vp_fma.ll b/llvm/test/CodeGen/VE/Vector/vp_fma.ll
index cb61cb0236a3d..50ce95a3eb39f 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_fma.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_fma.ll
@@ -6,9 +6,9 @@ declare <256 x float> @llvm.vp.fma.v256f32(<256 x float>, <256 x float>, <256 x
define fastcc <256 x float> @test_vp_fma_v256f32_vvv(<256 x float> %i0, <256 x float> %i1, <256 x float> %i2, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fma_v256f32_vvv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfmad.s %v0, %v2, %v0, %v1, %vm1
+; CHECK-NEXT: vfmad.s %v0, %v2, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x float> @llvm.vp.fma.v256f32(<256 x float> %i0, <256 x float> %i1, <256 x float> %i2, <256 x i1> %m, i32 %n)
ret <256 x float> %r0
@@ -17,9 +17,9 @@ define fastcc <256 x float> @test_vp_fma_v256f32_vvv(<256 x float> %i0, <256 x f
define fastcc <256 x float> @test_vp_fma_v256f32_rvv(float %s0, <256 x float> %i1, <256 x float> %i2, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fma_v256f32_rvv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfmad.s %v0, %v1, %s0, %v0, %vm1
+; CHECK-NEXT: vfmad.s %v0, %v1, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x float> undef, float %s0, i32 0
%i0 = shufflevector <256 x float> %xins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -30,9 +30,9 @@ define fastcc <256 x float> @test_vp_fma_v256f32_rvv(float %s0, <256 x float> %i
define fastcc <256 x float> @test_vp_fma_v256f32_vrv(<256 x float> %i0, float %s1, <256 x float> %i2, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fma_v256f32_vrv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfmad.s %v0, %v1, %s0, %v0, %vm1
+; CHECK-NEXT: vfmad.s %v0, %v1, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x float> undef, float %s1, i32 0
%i1 = shufflevector <256 x float> %yins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -43,9 +43,9 @@ define fastcc <256 x float> @test_vp_fma_v256f32_vrv(<256 x float> %i0, float %s
define fastcc <256 x float> @test_vp_fma_v256f32_vvr(<256 x float> %i0, <256 x float> %i1, float %s2, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fma_v256f32_vvr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfmad.s %v0, %s0, %v0, %v1, %vm1
+; CHECK-NEXT: vfmad.s %v0, %s0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%zins = insertelement <256 x float> undef, float %s2, i32 0
%i2 = shufflevector <256 x float> %zins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -58,9 +58,9 @@ declare <256 x double> @llvm.vp.fma.v256f64(<256 x double>, <256 x double>, <256
define fastcc <256 x double> @test_vp_fma_v256f64_vvv(<256 x double> %i0, <256 x double> %i1, <256 x double> %i2, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fma_v256f64_vvv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfmad.d %v0, %v2, %v0, %v1, %vm1
+; CHECK-NEXT: vfmad.d %v0, %v2, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x double> @llvm.vp.fma.v256f64(<256 x double> %i0, <256 x double> %i1, <256 x double> %i2, <256 x i1> %m, i32 %n)
ret <256 x double> %r0
@@ -69,9 +69,9 @@ define fastcc <256 x double> @test_vp_fma_v256f64_vvv(<256 x double> %i0, <256 x
define fastcc <256 x double> @test_vp_fma_v256f64_rvv(double %s0, <256 x double> %i1, <256 x double> %i2, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fma_v256f64_rvv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfmad.d %v0, %v1, %s0, %v0, %vm1
+; CHECK-NEXT: vfmad.d %v0, %v1, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x double> undef, double %s0, i32 0
%i0 = shufflevector <256 x double> %xins, <256 x double> undef, <256 x i32> zeroinitializer
@@ -82,9 +82,9 @@ define fastcc <256 x double> @test_vp_fma_v256f64_rvv(double %s0, <256 x double>
define fastcc <256 x double> @test_vp_fma_v256f64_vrv(<256 x double> %i0, double %s1, <256 x double> %i2, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fma_v256f64_vrv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfmad.d %v0, %v1, %s0, %v0, %vm1
+; CHECK-NEXT: vfmad.d %v0, %v1, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x double> undef, double %s1, i32 0
%i1 = shufflevector <256 x double> %yins, <256 x double> undef, <256 x i32> zeroinitializer
@@ -95,9 +95,9 @@ define fastcc <256 x double> @test_vp_fma_v256f64_vrv(<256 x double> %i0, double
define fastcc <256 x double> @test_vp_fma_v256f64_vvr(<256 x double> %i0, <256 x double> %i1, double %s2, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fma_v256f64_vvr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfmad.d %v0, %s0, %v0, %v1, %vm1
+; CHECK-NEXT: vfmad.d %v0, %s0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%zins = insertelement <256 x double> undef, double %s2, i32 0
%i2 = shufflevector <256 x double> %zins, <256 x double> undef, <256 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Vector/vp_fmul.ll b/llvm/test/CodeGen/VE/Vector/vp_fmul.ll
index 739573e0b3e39..51b816bbc28c0 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_fmul.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_fmul.ll
@@ -6,9 +6,9 @@ declare <256 x float> @llvm.vp.fmul.v256f32(<256 x float>, <256 x float>, <256 x
define fastcc <256 x float> @test_vp_fmul_v256f32_vv(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v256f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvfmul.up %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvfmul.up %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x float> @llvm.vp.fmul.v256f32(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %n)
ret <256 x float> %r0
@@ -17,9 +17,9 @@ define fastcc <256 x float> @test_vp_fmul_v256f32_vv(<256 x float> %i0, <256 x f
define fastcc <256 x float> @test_vp_fmul_v256f32_rv(float %s0, <256 x float> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v256f32_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfmul.up %v0, %s0, %v0, %vm1
+; CHECK-NEXT: pvfmul.up %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x float> undef, float %s0, i32 0
%i0 = shufflevector <256 x float> %xins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -30,9 +30,9 @@ define fastcc <256 x float> @test_vp_fmul_v256f32_rv(float %s0, <256 x float> %i
define fastcc <256 x float> @test_vp_fmul_v256f32_vr(<256 x float> %i0, float %s1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v256f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfmul.up %v0, %s0, %v0, %vm1
+; CHECK-NEXT: pvfmul.up %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x float> undef, float %s1, i32 0
%i1 = shufflevector <256 x float> %yins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -46,9 +46,9 @@ declare <256 x double> @llvm.vp.fmul.v256f64(<256 x double>, <256 x double>, <25
define fastcc <256 x double> @test_vp_fmul_v256f64_vv(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v256f64_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfmul.d %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vfmul.d %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x double> @llvm.vp.fmul.v256f64(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %n)
ret <256 x double> %r0
@@ -57,9 +57,9 @@ define fastcc <256 x double> @test_vp_fmul_v256f64_vv(<256 x double> %i0, <256 x
define fastcc <256 x double> @test_vp_fmul_v256f64_rv(double %s0, <256 x double> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v256f64_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfmul.d %v0, %s0, %v0, %vm1
+; CHECK-NEXT: vfmul.d %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x double> undef, double %s0, i32 0
%i0 = shufflevector <256 x double> %xins, <256 x double> undef, <256 x i32> zeroinitializer
@@ -70,9 +70,9 @@ define fastcc <256 x double> @test_vp_fmul_v256f64_rv(double %s0, <256 x double>
define fastcc <256 x double> @test_vp_fmul_v256f64_vr(<256 x double> %i0, double %s1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fmul_v256f64_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfmul.d %v0, %s0, %v0, %vm1
+; CHECK-NEXT: vfmul.d %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x double> undef, double %s1, i32 0
%i1 = shufflevector <256 x double> %yins, <256 x double> undef, <256 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Vector/vp_fsub.ll b/llvm/test/CodeGen/VE/Vector/vp_fsub.ll
index dcfc499cbd67c..f893d52a05c95 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_fsub.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_fsub.ll
@@ -6,9 +6,9 @@ declare <256 x float> @llvm.vp.fsub.v256f32(<256 x float>, <256 x float>, <256 x
define fastcc <256 x float> @test_vp_fsub_v256f32_vv(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v256f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvfsub.up %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvfsub.up %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x float> @llvm.vp.fsub.v256f32(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %n)
ret <256 x float> %r0
@@ -17,9 +17,9 @@ define fastcc <256 x float> @test_vp_fsub_v256f32_vv(<256 x float> %i0, <256 x f
define fastcc <256 x float> @test_vp_fsub_v256f32_rv(float %s0, <256 x float> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v256f32_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfsub.up %v0, %s0, %v0, %vm1
+; CHECK-NEXT: pvfsub.up %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x float> undef, float %s0, i32 0
%i0 = shufflevector <256 x float> %xins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -30,12 +30,10 @@ define fastcc <256 x float> @test_vp_fsub_v256f32_rv(float %s0, <256 x float> %i
define fastcc <256 x float> @test_vp_fsub_v256f32_vr(<256 x float> %i0, float %s1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v256f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
-; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: pvfsub.up %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: pvfsub.up %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x float> undef, float %s1, i32 0
%i1 = shufflevector <256 x float> %yins, <256 x float> undef, <256 x i32> zeroinitializer
@@ -49,9 +47,9 @@ declare <256 x double> @llvm.vp.fsub.v256f64(<256 x double>, <256 x double>, <25
define fastcc <256 x double> @test_vp_fsub_v256f64_vv(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v256f64_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vfsub.d %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vfsub.d %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x double> @llvm.vp.fsub.v256f64(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %n)
ret <256 x double> %r0
@@ -60,9 +58,9 @@ define fastcc <256 x double> @test_vp_fsub_v256f64_vv(<256 x double> %i0, <256 x
define fastcc <256 x double> @test_vp_fsub_v256f64_rv(double %s0, <256 x double> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v256f64_rv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfsub.d %v0, %s0, %v0, %vm1
+; CHECK-NEXT: vfsub.d %v0, %s0, %v0
; CHECK-NEXT: b.l.t (, %s10)
%xins = insertelement <256 x double> undef, double %s0, i32 0
%i0 = shufflevector <256 x double> %xins, <256 x double> undef, <256 x i32> zeroinitializer
@@ -73,12 +71,10 @@ define fastcc <256 x double> @test_vp_fsub_v256f64_rv(double %s0, <256 x double>
define fastcc <256 x double> @test_vp_fsub_v256f64_vr(<256 x double> %i0, double %s1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_fsub_v256f64_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
-; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
-; CHECK-NEXT: vfsub.d %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: vfsub.d %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%yins = insertelement <256 x double> undef, double %s1, i32 0
%i1 = shufflevector <256 x double> %yins, <256 x double> undef, <256 x i32> zeroinitializer
diff --git a/llvm/test/CodeGen/VE/Vector/vp_lshr.ll b/llvm/test/CodeGen/VE/Vector/vp_lshr.ll
index 4ea6c76e866c4..ab024d971ed83 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_lshr.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_lshr.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.lshr.v256i32(<256 x i32>, <256 x i32>, <256 x i1>,
define fastcc <256 x i32> @test_vp_int(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_int:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsrl.lo %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvsrl.lo %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.lshr.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.lshr.v256i64(<256 x i64>, <256 x i64>, <256 x i1>,
define fastcc <256 x i64> @test_vp_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vsrl %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vsrl %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.lshr.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_mul.ll b/llvm/test/CodeGen/VE/Vector/vp_mul.ll
index 631f676a668de..20eca0e36a930 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_mul.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_mul.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.mul.v256i32(<256 x i32>, <256 x i32>, <256 x i1>, i
define fastcc <256 x i32> @test_vp_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vmuls.w.sx %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vmuls.w.sx %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.mul.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.mul.v256i64(<256 x i64>, <256 x i64>, <256 x i1>, i
define fastcc <256 x i64> @test_vp_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vmuls.l %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vmuls.l %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.mul.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_or.ll b/llvm/test/CodeGen/VE/Vector/vp_or.ll
index 1ae6eb5c0a3ad..53d0009eee0e4 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_or.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_or.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.or.v256i32(<256 x i32>, <256 x i32>, <256 x i1>, i3
define fastcc <256 x i32> @test_vp_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvor.lo %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvor.lo %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.or.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.or.v256i64(<256 x i64>, <256 x i64>, <256 x i1>, i3
define fastcc <256 x i64> @test_vp_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vor %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vor %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.or.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_select.ll b/llvm/test/CodeGen/VE/Vector/vp_select.ll
index 3858af7ad5017..9b340b9799981 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_select.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_select.ll
@@ -6,7 +6,7 @@ declare <256 x i32> @llvm.vp.select.v256i32(<256 x i1>, <256 x i32>, <256 x i32>
define fastcc <256 x i32> @test_vp_select_v256i32_vv(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %pivot) {
; CHECK-LABEL: test_vp_select_v256i32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
; CHECK-NEXT: vmrg %v1, %v1, %v0, %vm1
; CHECK-NEXT: lea %s16, 256
@@ -20,12 +20,10 @@ define fastcc <256 x i32> @test_vp_select_v256i32_vv(<256 x i32> %i0, <256 x i32
define fastcc <256 x i32> @test_vp_select_v256i32_vr(<256 x i32> %i0, i32 %s1, <256 x i1> %m, i32 %pivot) {
; CHECK-LABEL: test_vp_select_v256i32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
; CHECK-NEXT: and %s0, %s0, (32)0
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
-; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
+; CHECK-NEXT: vbrd %v1, %s0
; CHECK-NEXT: vmrg %v1, %v1, %v0, %vm1
; CHECK-NEXT: lea %s16, 256
; CHECK-NEXT: lvl %s16
@@ -42,7 +40,7 @@ declare <256 x float> @llvm.vp.select.v256f32(<256 x i1>, <256 x float>, <256 x
define fastcc <256 x float> @test_vp_select_v256f32_vv(<256 x float> %i0, <256 x float> %i1, <256 x i1> %m, i32 %pivot) {
; CHECK-LABEL: test_vp_select_v256f32_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
; CHECK-NEXT: vmrg %v1, %v1, %v0, %vm1
; CHECK-NEXT: lea %s16, 256
@@ -56,11 +54,9 @@ define fastcc <256 x float> @test_vp_select_v256f32_vv(<256 x float> %i0, <256 x
define fastcc <256 x float> @test_vp_select_v256f32_vr(<256 x float> %i0, float %s1, <256 x i1> %m, i32 %pivot) {
; CHECK-LABEL: test_vp_select_v256f32_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
-; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
+; CHECK-NEXT: vbrd %v1, %s0
; CHECK-NEXT: vmrg %v1, %v1, %v0, %vm1
; CHECK-NEXT: lea %s16, 256
; CHECK-NEXT: lvl %s16
@@ -77,7 +73,7 @@ declare <256 x double> @llvm.vp.select.v256f64(<256 x i1>, <256 x double>, <256
define fastcc <256 x double> @test_vp_select_v256f64_vv(<256 x double> %i0, <256 x double> %i1, <256 x i1> %m, i32 %pivot) {
; CHECK-LABEL: test_vp_select_v256f64_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
; CHECK-NEXT: vmrg %v1, %v1, %v0, %vm1
; CHECK-NEXT: lea %s16, 256
@@ -91,11 +87,9 @@ define fastcc <256 x double> @test_vp_select_v256f64_vv(<256 x double> %i0, <256
define fastcc <256 x double> @test_vp_select_v256f64_vr(<256 x double> %i0, double %s1, <256 x i1> %m, i32 %pivot) {
; CHECK-LABEL: test_vp_select_v256f64_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
-; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
+; CHECK-NEXT: vbrd %v1, %s0
; CHECK-NEXT: vmrg %v1, %v1, %v0, %vm1
; CHECK-NEXT: lea %s16, 256
; CHECK-NEXT: lvl %s16
@@ -112,7 +106,7 @@ declare <256 x i64> @llvm.vp.select.v256i64(<256 x i1>, <256 x i64>, <256 x i64>
define fastcc <256 x i64> @test_vp_select_v256i64_vv(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %pivot) {
; CHECK-LABEL: test_vp_select_v256i64_vv:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
; CHECK-NEXT: vmrg %v1, %v1, %v0, %vm1
; CHECK-NEXT: lea %s16, 256
@@ -126,11 +120,9 @@ define fastcc <256 x i64> @test_vp_select_v256i64_vv(<256 x i64> %i0, <256 x i64
define fastcc <256 x i64> @test_vp_select_v256i64_vr(<256 x i64> %i0, i64 %s1, <256 x i1> %m, i32 %pivot) {
; CHECK-LABEL: test_vp_select_v256i64_vr:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s1, %s1, (32)0
-; CHECK-NEXT: lea %s2, 256
-; CHECK-NEXT: lvl %s2
-; CHECK-NEXT: vbrd %v1, %s0
+; CHECK-NEXT: lea %s1, 256
; CHECK-NEXT: lvl %s1
+; CHECK-NEXT: vbrd %v1, %s0
; CHECK-NEXT: vmrg %v1, %v1, %v0, %vm1
; CHECK-NEXT: lea %s16, 256
; CHECK-NEXT: lvl %s16
diff --git a/llvm/test/CodeGen/VE/Vector/vp_shl.ll b/llvm/test/CodeGen/VE/Vector/vp_shl.ll
index 5929e00bcb158..867931708bd11 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_shl.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_shl.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.shl.v256i32(<256 x i32>, <256 x i32>, <256 x i1>, i
define fastcc <256 x i32> @test_vp_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsll.lo %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvsll.lo %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.shl.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.shl.v256i64(<256 x i64>, <256 x i64>, <256 x i1>, i
define fastcc <256 x i64> @test_vp_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vsll %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vsll %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.shl.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_sra.ll b/llvm/test/CodeGen/VE/Vector/vp_sra.ll
index a45d694e5334d..4ac8965176eef 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_sra.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_sra.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.ashr.v256i32(<256 x i32>, <256 x i32>, <256 x i1>,
define fastcc <256 x i32> @test_vp_ashr_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_ashr_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsra.lo %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvsra.lo %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.ashr.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.ashr.v256i64(<256 x i64>, <256 x i64>, <256 x i1>,
define fastcc <256 x i64> @test_vp_int_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_int_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vsra.l %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vsra.l %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.ashr.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_srl.ll b/llvm/test/CodeGen/VE/Vector/vp_srl.ll
index f00688d8a2bf9..6c1484f6b29c7 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_srl.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_srl.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.lshr.v256i32(<256 x i32>, <256 x i32>, <256 x i1>,
define fastcc <256 x i32> @test_vp_lshr_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_lshr_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvsrl.lo %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvsrl.lo %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.lshr.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.lshr.v256i64(<256 x i64>, <256 x i64>, <256 x i1>,
define fastcc <256 x i64> @test_vp_int_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_int_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vsrl %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vsrl %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.lshr.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_sub.ll b/llvm/test/CodeGen/VE/Vector/vp_sub.ll
index b0f4726c23ebb..13e75abca7431 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_sub.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_sub.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.sub.v256i32(<256 x i32>, <256 x i32>, <256 x i1>, i
define fastcc <256 x i32> @test_vp_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vsubs.w.sx %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vsubs.w.sx %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.sub.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.sub.v256i64(<256 x i64>, <256 x i64>, <256 x i1>, i
define fastcc <256 x i64> @test_vp_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vsubs.l %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vsubs.l %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.sub.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/CodeGen/VE/Vector/vp_xor.ll b/llvm/test/CodeGen/VE/Vector/vp_xor.ll
index ae6b0f8033309..d380687614894 100644
--- a/llvm/test/CodeGen/VE/Vector/vp_xor.ll
+++ b/llvm/test/CodeGen/VE/Vector/vp_xor.ll
@@ -6,9 +6,9 @@ declare <256 x i32> @llvm.vp.xor.v256i32(<256 x i32>, <256 x i32>, <256 x i1>, i
define fastcc <256 x i32> @test_vp_v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: pvxor.lo %v0, %v0, %v1, %vm1
+; CHECK-NEXT: pvxor.lo %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i32> @llvm.vp.xor.v256i32(<256 x i32> %i0, <256 x i32> %i1, <256 x i1> %m, i32 %n)
ret <256 x i32> %r0
@@ -20,9 +20,9 @@ declare <256 x i64> @llvm.vp.xor.v256i64(<256 x i64>, <256 x i64>, <256 x i1>, i
define fastcc <256 x i64> @test_vp_v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n) {
; CHECK-LABEL: test_vp_v256i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: and %s0, %s0, (32)0
+; CHECK-NEXT: lea %s0, 256
; CHECK-NEXT: lvl %s0
-; CHECK-NEXT: vxor %v0, %v0, %v1, %vm1
+; CHECK-NEXT: vxor %v0, %v0, %v1
; CHECK-NEXT: b.l.t (, %s10)
%r0 = call <256 x i64> @llvm.vp.xor.v256i64(<256 x i64> %i0, <256 x i64> %i1, <256 x i1> %m, i32 %n)
ret <256 x i64> %r0
diff --git a/llvm/test/Transforms/DeadStoreElimination/dead-vp.store.ll b/llvm/test/Transforms/DeadStoreElimination/dead-vp.store.ll
index 7ba1354d8cd0b..4fc4a8e9f6fae 100644
--- a/llvm/test/Transforms/DeadStoreElimination/dead-vp.store.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/dead-vp.store.ll
@@ -6,8 +6,8 @@
define void @test1(ptr %a, i32 %vl, <vscale x 8 x i32> %v1, <vscale x 8 x i32> %v2) {
;
; CHECK-LABEL: @test1(
-; CHECK-NEXT: [[VP_OP:%.*]] = call <vscale x 8 x i32> @llvm.vp.add.nxv8i32(<vscale x 8 x i32> [[V1:%.*]], <vscale x 8 x i32> [[V2:%.*]], <vscale x 8 x i1> splat (i1 true), i32 [[VL:%.*]])
-; CHECK-NEXT: call void @llvm.vp.store.nxv8i32.p0(<vscale x 8 x i32> [[VP_OP]], ptr nonnull [[A:%.*]], <vscale x 8 x i1> splat (i1 true), i32 [[VL]])
+; CHECK-NEXT: [[VP_OP:%.*]] = add <vscale x 8 x i32> [[V1:%.*]], [[V2:%.*]]
+; CHECK-NEXT: call void @llvm.vp.store.nxv8i32.p0(<vscale x 8 x i32> [[VP_OP]], ptr nonnull [[A:%.*]], <vscale x 8 x i1> splat (i1 true), i32 [[VL:%.*]])
; CHECK-NEXT: ret void
;
call void @llvm.vp.store.nxv8i32.p0(<vscale x 8 x i32> %v1, ptr nonnull %a, <vscale x 8 x i1> splat (i1 true), i32 %vl)
diff --git a/llvm/test/Transforms/GVN/vp_gather_scatter.ll b/llvm/test/Transforms/GVN/vp_gather_scatter.ll
index cfa9e1e9f1bf7..23b496333e630 100644
--- a/llvm/test/Transforms/GVN/vp_gather_scatter.ll
+++ b/llvm/test/Transforms/GVN/vp_gather_scatter.ll
@@ -5,7 +5,7 @@
define <vscale x 8 x i32> @foo(<vscale x 8 x ptr> %p, <vscale x 8 x i32> %x, <vscale x 8 x i1> %mask, i32 %vl) {
; CHECK-LABEL: @foo(
; CHECK-NEXT: [[A:%.*]] = call <vscale x 8 x i32> @llvm.vp.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> [[P:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i32 [[VL:%.*]])
-; CHECK-NEXT: [[B:%.*]] = call <vscale x 8 x i32> @llvm.vp.add.nxv8i32(<vscale x 8 x i32> [[A]], <vscale x 8 x i32> [[X:%.*]], <vscale x 8 x i1> [[MASK]], i32 [[VL]])
+; CHECK-NEXT: [[B:%.*]] = add <vscale x 8 x i32> [[A]], [[X:%.*]]
; CHECK-NEXT: call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> [[B]], <vscale x 8 x ptr> [[P]], <vscale x 8 x i1> [[MASK]], i32 [[VL]])
; CHECK-NEXT: [[C:%.*]] = call <vscale x 8 x i32> @llvm.vp.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> [[P]], <vscale x 8 x i1> [[MASK]], i32 [[VL]])
; CHECK-NEXT: ret <vscale x 8 x i32> [[C]]
diff --git a/llvm/test/Transforms/InstCombine/fabs.ll b/llvm/test/Transforms/InstCombine/fabs.ll
index 52a9ce7aab2bd..86456b8b4c02d 100644
--- a/llvm/test/Transforms/InstCombine/fabs.ll
+++ b/llvm/test/Transforms/InstCombine/fabs.ll
@@ -1682,8 +1682,7 @@ define i32 @test_fabs_nsz_used_by_fptoui_sat(float %x) {
define <2 x i1> @test_fabs_used_vp_is_fpclass_zero_or_pinf(<2 x float> %x, <2 x i1> %mask, i32 %evl) {
; CHECK-LABEL: @test_fabs_used_vp_is_fpclass_zero_or_pinf(
-; CHECK-NEXT: [[SEL:%.*]] = call <2 x float> @llvm.fabs.v2f32(<2 x float> [[X:%.*]])
-; CHECK-NEXT: [[IS_FPCLASS:%.*]] = call <2 x i1> @llvm.vp.is.fpclass.v2f32(<2 x float> [[SEL]], i32 608, <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
+; CHECK-NEXT: [[IS_FPCLASS:%.*]] = call <2 x i1> @llvm.is.fpclass.v2f32(<2 x float> [[X:%.*]], /* (inf zero) */ i32 612)
; CHECK-NEXT: ret <2 x i1> [[IS_FPCLASS]]
;
%cmp = fcmp oge <2 x float> %x, zeroinitializer
diff --git a/llvm/test/Transforms/InstSimplify/add_vp.ll b/llvm/test/Transforms/InstSimplify/add_vp.ll
index 320f3fbb30379..2b9c19a4e7f5c 100644
--- a/llvm/test/Transforms/InstSimplify/add_vp.ll
+++ b/llvm/test/Transforms/InstSimplify/add_vp.ll
@@ -10,8 +10,7 @@ declare <2 x i8> @llvm.vp.sub.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)
; Constant folding should just work.
define <2 x i32> @constant_vp_add(<2 x i1> %mask, i32 %evl) {
; CHECK-LABEL: @constant_vp_add(
-; CHECK-NEXT: [[Q:%.*]] = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> splat (i32 3), <2 x i32> splat (i32 7), <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; CHECK-NEXT: ret <2 x i32> [[Q]]
+; CHECK-NEXT: ret <2 x i32> splat (i32 10)
;
%Q = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> <i32 3, i32 3>, <2 x i32> <i32 7, i32 7>, <2 x i1> %mask, i32 %evl)
ret <2 x i32> %Q
@@ -20,9 +19,7 @@ define <2 x i32> @constant_vp_add(<2 x i1> %mask, i32 %evl) {
; Simplifying pure VP intrinsic patterns.
define <2 x i32> @common_sub_operand(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl) {
; CHECK-LABEL: @common_sub_operand(
-; CHECK-NEXT: [[Z:%.*]] = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; CHECK-NEXT: [[Q:%.*]] = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> [[Z]], <2 x i32> [[Y]], <2 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: ret <2 x i32> [[Q]]
+; CHECK-NEXT: ret <2 x i32> [[Q:%.*]]
;
; %Z = sub i32 %X, %Y, vp(%mask, %evl)
%Z = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl)
@@ -34,9 +31,7 @@ define <2 x i32> @common_sub_operand(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask,
; Mixing regular SIMD with vp intrinsics (vp add match root).
define <2 x i32> @common_sub_operand_vproot(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl) {
; CHECK-LABEL: @common_sub_operand_vproot(
-; CHECK-NEXT: [[Z:%.*]] = sub <2 x i32> [[X:%.*]], [[Y:%.*]]
-; CHECK-NEXT: [[Q:%.*]] = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> [[Z]], <2 x i32> [[Y]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; CHECK-NEXT: ret <2 x i32> [[Q]]
+; CHECK-NEXT: ret <2 x i32> [[Q:%.*]]
;
%Z = sub <2 x i32> %X, %Y
; %Q = add i32 %Z, %Y, vp(%mask, %evl)
@@ -47,9 +42,7 @@ define <2 x i32> @common_sub_operand_vproot(<2 x i32> %X, <2 x i32> %Y, <2 x i1>
; Mixing regular SIMD with vp intrinsics (vp inside pattern, regular instruction root).
define <2 x i32> @common_sub_operand_vpinner(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl) {
; CHECK-LABEL: @common_sub_operand_vpinner(
-; CHECK-NEXT: [[Z:%.*]] = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; CHECK-NEXT: [[Q:%.*]] = add <2 x i32> [[Z]], [[Y]]
-; CHECK-NEXT: ret <2 x i32> [[Q]]
+; CHECK-NEXT: ret <2 x i32> [[Q:%.*]]
;
; %Z = sub i32 %X, %Y, vp(%mask, %evl)
%Z = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> %X, <2 x i32> %Y, <2 x i1> %mask, i32 %evl)
@@ -59,9 +52,7 @@ define <2 x i32> @common_sub_operand_vpinner(<2 x i32> %X, <2 x i32> %Y, <2 x i1
define <2 x i32> @negated_operand(<2 x i32> %x, <2 x i1> %mask, i32 %evl) {
; CHECK-LABEL: @negated_operand(
-; CHECK-NEXT: [[NEGX:%.*]] = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> zeroinitializer, <2 x i32> [[X:%.*]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; CHECK-NEXT: [[R:%.*]] = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> [[NEGX]], <2 x i32> [[X]], <2 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: ret <2 x i32> [[R]]
+; CHECK-NEXT: ret <2 x i32> zeroinitializer
;
; %negx = sub i32 0, %x
%negx = call <2 x i32> @llvm.vp.sub.v2i32(<2 x i32> zeroinitializer, <2 x i32> %x, <2 x i1> %mask, i32 %evl)
@@ -77,10 +68,7 @@ define <2 x i8> @knownnegation(<2 x i8> %x, <2 x i8> %y, <2 x i1> %mask, i32 %ev
;
; %xy = sub i8 %x, %y
; CHECK-LABEL: @knownnegation(
-; CHECK-NEXT: [[XY:%.*]] = call <2 x i8> @llvm.vp.sub.v2i8(<2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; CHECK-NEXT: [[YX:%.*]] = call <2 x i8> @llvm.vp.sub.v2i8(<2 x i8> [[Y]], <2 x i8> [[X]], <2 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: [[R:%.*]] = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> [[XY]], <2 x i8> [[YX]], <2 x i1> [[MASK]], i32 [[EVL]])
-; CHECK-NEXT: ret <2 x i8> [[R]]
+; CHECK-NEXT: ret <2 x i8> zeroinitializer
;
%xy = call <2 x i8> @llvm.vp.sub.v2i8(<2 x i8> %x, <2 x i8> %y, <2 x i1> %mask, i32 %evl)
; %yx = sub i8 %y, %x
diff --git a/llvm/test/Transforms/LICM/vector-intrinsics.ll b/llvm/test/Transforms/LICM/vector-intrinsics.ll
index 351773e63de9d..d08520aadcc74 100644
--- a/llvm/test/Transforms/LICM/vector-intrinsics.ll
+++ b/llvm/test/Transforms/LICM/vector-intrinsics.ll
@@ -38,7 +38,7 @@ define i32 @vp_umax(<2 x i32> %inv.l, <2 x i32> %inv.r, i1 %c) {
; CHECK-LABEL: define i32 @vp_umax(
; CHECK-SAME: <2 x i32> [[INV_L:%.*]], <2 x i32> [[INV_R:%.*]], i1 [[C:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*]]:
-; CHECK-NEXT: [[VP_UMAX:%.*]] = call <2 x i32> @llvm.vp.umax.v2i32(<2 x i32> [[INV_L]], <2 x i32> [[INV_R]], <2 x i1> splat (i1 true), i32 2)
+; CHECK-NEXT: [[VP_UMAX:%.*]] = call <2 x i32> @llvm.umax.v2i32(<2 x i32> [[INV_L]], <2 x i32> [[INV_R]])
; CHECK-NEXT: [[EXTRACT:%.*]] = extractelement <2 x i32> [[VP_UMAX]], i32 0
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
diff --git a/llvm/test/Transforms/PreISelIntrinsicLowering/expand-vp.ll b/llvm/test/Transforms/PreISelIntrinsicLowering/expand-vp.ll
index bc85a1fd7ff96..442422e3d9254 100644
--- a/llvm/test/Transforms/PreISelIntrinsicLowering/expand-vp.ll
+++ b/llvm/test/Transforms/PreISelIntrinsicLowering/expand-vp.ll
@@ -350,47 +350,47 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; All legal - don't transform anything.
; LEGAL_LEGAL: define void @test_vp_int_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x i32> %i2, <8 x i32> %f3, <8 x i1> %m, i32 %n) {
-; LEGAL_LEGAL-NEXT: %r0 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r1 = call <8 x i32> @llvm.vp.sub.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r2 = call <8 x i32> @llvm.vp.mul.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
+; LEGAL_LEGAL-NEXT: %r0 = add <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %r1 = sub <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %r2 = mul <8 x i32> %i0, %i1
; LEGAL_LEGAL-NEXT: %r3 = call <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r4 = call <8 x i32> @llvm.vp.srem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r5 = call <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r6 = call <8 x i32> @llvm.vp.urem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r7 = call <8 x i32> @llvm.vp.smax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r8 = call <8 x i32> @llvm.vp.smin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r9 = call <8 x i32> @llvm.vp.umax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rA = call <8 x i32> @llvm.vp.umin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rB = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rC = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rD = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rE = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rF = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r10 = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
+; LEGAL_LEGAL-NEXT: %r7 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> %i0, <8 x i32> %i1)
+; LEGAL_LEGAL-NEXT: %r8 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> %i0, <8 x i32> %i1)
+; LEGAL_LEGAL-NEXT: %r9 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> %i0, <8 x i32> %i1)
+; LEGAL_LEGAL-NEXT: %rA = call <8 x i32> @llvm.umin.v8i32(<8 x i32> %i0, <8 x i32> %i1)
+; LEGAL_LEGAL-NEXT: %rB = and <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %rC = or <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %rD = xor <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %rE = ashr <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %rF = lshr <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %r10 = shl <8 x i32> %i0, %i1
; LEGAL_LEGAL-NEXT: %r11 = call <8 x i32> @llvm.vp.merge.v8i32(<8 x i1> %m, <8 x i32> %i0, <8 x i32> %i1, i32 %n)
-; LEGAL_LEGAL-NEXT: %r12 = call <8 x i32> @llvm.vp.select.v8i32(<8 x i1> %m, <8 x i32> %i0, <8 x i32> %i1, i32 %n)
+; LEGAL_LEGAL-NEXT: %r12 = select <8 x i1> %m, <8 x i32> %i0, <8 x i32> %i1
; LEGAL_LEGAL-NEXT: ret void
; LEGAL_LEGAL:define void @test_vp_int_vscale(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i32> %i2, <vscale x 4 x i32> %f3, <vscale x 4 x i1> %m, i32 %n) {
-; LEGAL_LEGAL-NEXT: %r0 = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r1 = call <vscale x 4 x i32> @llvm.vp.sub.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r2 = call <vscale x 4 x i32> @llvm.vp.mul.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
+; LEGAL_LEGAL-NEXT: %r0 = add <vscale x 4 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %r1 = sub <vscale x 4 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %r2 = mul <vscale x 4 x i32> %i0, %i1
; LEGAL_LEGAL-NEXT: %r3 = call <vscale x 4 x i32> @llvm.vp.sdiv.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r4 = call <vscale x 4 x i32> @llvm.vp.srem.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r5 = call <vscale x 4 x i32> @llvm.vp.udiv.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
; LEGAL_LEGAL-NEXT: %r6 = call <vscale x 4 x i32> @llvm.vp.urem.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r7 = call <vscale x 4 x i32> @llvm.vp.smax.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r8 = call <vscale x 4 x i32> @llvm.vp.smin.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r9 = call <vscale x 4 x i32> @llvm.vp.umax.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rA = call <vscale x 4 x i32> @llvm.vp.umin.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rB = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rC = call <vscale x 4 x i32> @llvm.vp.or.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rD = call <vscale x 4 x i32> @llvm.vp.xor.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rE = call <vscale x 4 x i32> @llvm.vp.ashr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %rF = call <vscale x 4 x i32> @llvm.vp.lshr.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r10 = call <vscale x 4 x i32> @llvm.vp.shl.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %n)
+; LEGAL_LEGAL-NEXT: %r7 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1)
+; LEGAL_LEGAL-NEXT: %r8 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1)
+; LEGAL_LEGAL-NEXT: %r9 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1)
+; LEGAL_LEGAL-NEXT: %rA = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1)
+; LEGAL_LEGAL-NEXT: %rB = and <vscale x 4 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %rC = or <vscale x 4 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %rD = xor <vscale x 4 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %rE = ashr <vscale x 4 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %rF = lshr <vscale x 4 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %r10 = shl <vscale x 4 x i32> %i0, %i1
; LEGAL_LEGAL-NEXT: %r11 = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> %m, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, i32 %n)
-; LEGAL_LEGAL-NEXT: %r12 = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> %m, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, i32 %n)
+; LEGAL_LEGAL-NEXT: %r12 = select <vscale x 4 x i1> %m, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1
; LEGAL_LEGAL-NEXT: ret void
; LEGAL_LEGAL: define void @test_vp_reduce_int_v4(i32 %start, <4 x i32> %vi, <4 x i1> %m, i32 %n) {
@@ -425,10 +425,10 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; LEGAL_LEGAL-NEXT: ret void
; LEGAL_LEGAL: define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x float> %f1, <8 x i1> %m, i32 %n) {
-; LEGAL_LEGAL-NEXT: %r0 = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"eq", <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r1 = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"slt", <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r2 = call <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float> %f0, <8 x float> %f1, metadata !"oeq", <8 x i1> %m, i32 %n)
-; LEGAL_LEGAL-NEXT: %r3 = call <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float> %f0, <8 x float> %f1, metadata !"ult", <8 x i1> %m, i32 %n)
+; LEGAL_LEGAL-NEXT: %r0 = icmp eq <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %r1 = icmp slt <8 x i32> %i0, %i1
+; LEGAL_LEGAL-NEXT: %r2 = fcmp oeq <8 x float> %f0, %f1
+; LEGAL_LEGAL-NEXT: %r3 = fcmp ult <8 x float> %f0, %f1
; LEGAL_LEGAL-NEXT: ret void
; Drop %evl where possible else fold %evl into %mask (%evl Discard, %mask Legal)
@@ -443,9 +443,9 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; (4) All VP intrinsics have an ineffective %evl parameter.
; DISCARD_LEGAL: define void @test_vp_int_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x i32> %i2, <8 x i32> %f3, <8 x i1> %m, i32 %n) {
-; DISCARD_LEGAL-NEXT: %r0 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %r1 = call <8 x i32> @llvm.vp.sub.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %r2 = call <8 x i32> @llvm.vp.mul.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
+; DISCARD_LEGAL-NEXT: %r0 = add <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %r1 = sub <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %r2 = mul <8 x i32> %i0, %i1
; DISCARD_LEGAL-NEXT: [[NSPLATINS:%.+]] = insertelement <8 x i32> poison, i32 %n, i64 0
; DISCARD_LEGAL-NEXT: [[NSPLAT:%.+]] = shufflevector <8 x i32> [[NSPLATINS]], <8 x i32> poison, <8 x i32> zeroinitializer
; DISCARD_LEGAL-NEXT: [[EVLMASK:%.+]] = icmp ult <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, [[NSPLAT]]
@@ -454,22 +454,22 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; DISCARD_LEGAL-NOT: %r4 = call <8 x i32> @llvm.vp.srem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NOT: %r5 = call <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; DISCARD_LEGAL-NOT: %r6 = call <8 x i32> @llvm.vp.urem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL: %r7 = call <8 x i32> @llvm.vp.smax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL: %r8 = call <8 x i32> @llvm.vp.smin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL: %r9 = call <8 x i32> @llvm.vp.umax.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL: %rA = call <8 x i32> @llvm.vp.umin.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %rB = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %rC = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %rD = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %rE = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %rF = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %r10 = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
+; DISCARD_LEGAL: %r7 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> %i0, <8 x i32> %i1)
+; DISCARD_LEGAL: %r8 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> %i0, <8 x i32> %i1)
+; DISCARD_LEGAL: %r9 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> %i0, <8 x i32> %i1)
+; DISCARD_LEGAL: %rA = call <8 x i32> @llvm.umin.v8i32(<8 x i32> %i0, <8 x i32> %i1)
+; DISCARD_LEGAL-NEXT: %rB = and <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %rC = or <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %rD = xor <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %rE = ashr <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %rF = lshr <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %r10 = shl <8 x i32> %i0, %i1
; DISCARD_LEGAL-NEXT: [[NSPLATINS2:%.+]] = insertelement <8 x i32> poison, i32 %n, i64 0
; DISCARD_LEGAL-NEXT: [[NSPLAT2:%.+]] = shufflevector <8 x i32> [[NSPLATINS2]], <8 x i32> poison, <8 x i32> zeroinitializer
; DISCARD_LEGAL-NEXT: [[EVLMASK2:%.+]] = icmp ult <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, [[NSPLAT2]]
; DISCARD_LEGAL-NEXT: [[NEWMASK2:%.+]] = and <8 x i1> [[EVLMASK2]], %m
; DISCARD_LEGAL-NEXT: %r11 = call <8 x i32> @llvm.vp.merge.v8i32(<8 x i1> [[NEWMASK2]], <8 x i32> %i0, <8 x i32> %i1, i32 8)
-; DISCARD_LEGAL-NEXT: %r12 = call <8 x i32> @llvm.vp.select.v8i32(<8 x i1> %m, <8 x i32> %i0, <8 x i32> %i1, i32 8)
+; DISCARD_LEGAL-NEXT: %r12 = select <8 x i1> %m, <8 x i32> %i0, <8 x i32> %i1
; DISCARD_LEGAL-NEXT: ret void
; TODO compute vscale only once and use caching.
@@ -477,17 +477,17 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; intrinsic and skip over it for all others.
; DISCARD_LEGAL: define void @test_vp_int_vscale(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i32> %i2, <vscale x 4 x i32> %f3, <vscale x 4 x i1> %m, i32 %n) {
+; DISCARD_LEGAL-NEXT: %r0 = add <vscale x 4 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %r1 = sub <vscale x 4 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %r2 = mul <vscale x 4 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: [[EVLM:%.+]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 0, i32 %n)
+; DISCARD_LEGAL-NEXT: [[NEWM:%.+]] = and <vscale x 4 x i1> [[EVLM]], %m
; DISCARD_LEGAL-NEXT: %vscale = call i32 @llvm.vscale.i32()
; DISCARD_LEGAL-NEXT: %scalable_size = mul nuw i32 %vscale, 4
-; DISCARD_LEGAL-NEXT: %r0 = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %scalable_size)
-; DISCARD_LEGAL: %r1 = call <vscale x 4 x i32> @llvm.vp.sub.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %scalable_size{{.*}})
-; DISCARD_LEGAL: %r2 = call <vscale x 4 x i32> @llvm.vp.mul.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> %m, i32 %scalable_size{{.*}})
-; DISCARD_LEGAL: [[EVLM:%.+]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 0, i32 %n)
-; DISCARD_LEGAL: [[NEWM:%.+]] = and <vscale x 4 x i1> [[EVLM]], %m
-; DISCARD_LEGAL: %r3 = call <vscale x 4 x i32> @llvm.vp.sdiv.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> [[NEWM]], i32 %scalable_size{{.*}})
+; DISCARD_LEGAL-NEXT: %r3 = call <vscale x 4 x i32> @llvm.vp.sdiv.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> [[NEWM]], i32 %scalable_size)
; DISCARD_LEGAL-NOT: %{{.+}} = call <vscale x 4 x i32> @llvm.vp.{{.*}}, i32 %n)
; DISCARD_LEGAL: %r11 = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> %{{.*}}, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, i32 %scalable_size{{.*}})
-; DISCARD_LEGAL: %r12 = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> %m, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, i32 %scalable_size{{.*}})
+; DISCARD_LEGAL: %r12 = select <vscale x 4 x i1> %m, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1
; DISCARD_LEGAL-NEXT: ret void
; DISCARD_LEGAL: define void @test_vp_reduce_int_v4(i32 %start, <4 x i32> %vi, <4 x i1> %m, i32 %n) {
@@ -530,10 +530,10 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; DISCARD_LEGAL: ret void
; DISCARD_LEGAL: define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x float> %f1, <8 x i1> %m, i32 %n) {
-; DISCARD_LEGAL-NEXT: %r0 = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"eq", <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %r1 = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"slt", <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %r2 = call <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float> %f0, <8 x float> %f1, metadata !"oeq", <8 x i1> %m, i32 8)
-; DISCARD_LEGAL-NEXT: %r3 = call <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float> %f0, <8 x float> %f1, metadata !"ult", <8 x i1> %m, i32 8)
+; DISCARD_LEGAL-NEXT: %r0 = icmp eq <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %r1 = icmp slt <8 x i32> %i0, %i1
+; DISCARD_LEGAL-NEXT: %r2 = fcmp oeq <8 x float> %f0, %f1
+; DISCARD_LEGAL-NEXT: %r3 = fcmp ult <8 x float> %f0, %f1
; Convert %evl into %mask everywhere (%evl Convert, %mask Legal)
;
@@ -543,11 +543,11 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; (3) All VP intrinsics have an ineffective %evl parameter.
;
; CONVERT_LEGAL: define void @test_vp_int_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x i32> %i2, <8 x i32> %f3, <8 x i1> %m, i32 %n) {
-; CONVERT_LEGAL-NEXT: [[NINS:%.+]] = insertelement <8 x i32> poison, i32 %n, i64 0
+; CONVERT-LEGAL: %{{.+}} = add <8 x i32> %i0, %i1
+; CONVERT_LEGAL: [[NINS:%.+]] = insertelement <8 x i32> poison, i32 %n, i64 0
; CONVERT_LEGAL-NEXT: [[NSPLAT:%.+]] = shufflevector <8 x i32> [[NINS]], <8 x i32> poison, <8 x i32> zeroinitializer
; CONVERT_LEGAL-NEXT: [[EVLM:%.+]] = icmp ult <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, [[NSPLAT]]
; CONVERT_LEGAL-NEXT: [[NEWM:%.+]] = and <8 x i1> [[EVLM]], %m
-; CONVERT_LEGAL-NEXT: %{{.+}} = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> [[NEWM]], i32 8)
; CONVERT_LEGAL-NOT: %{{.+}} = call <8 x i32> @llvm.vp.sub.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; CONVERT_LEGAL-NOT: %{{.+}} = call <8 x i32> @llvm.vp.mul.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; CONVERT_LEGAL-NOT: %{{.+}} = call <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
@@ -561,19 +561,19 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; CONVERT_LEGAL-NOT: %{{.+}} = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; CONVERT_LEGAL-NOT: %{{.+}} = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 8)
; CONVERT_LEGAL: %r11 = call <8 x i32> @llvm.vp.merge.v8i32(<8 x i1> %{{.*}}, <8 x i32> %i0, <8 x i32> %i1, i32 8)
-; CONVERT_LEGAL: %r12 = call <8 x i32> @llvm.vp.select.v8i32(<8 x i1> %{{.*}}, <8 x i32> %i0, <8 x i32> %i1, i32 8)
+; CONVERT_LEGAL: %r12 = select <8 x i1> %{{.*}}, <8 x i32> %i0, <8 x i32> %i1
; CONVERT_LEGAL: ret void
; Similar to %evl discard, %mask legal but make sure the first VP intrinsic has a legal expansion
; CONVERT_LEGAL: define void @test_vp_int_vscale(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i32> %i2, <vscale x 4 x i32> %f3, <vscale x 4 x i1> %m, i32 %n) {
-; CONVERT_LEGAL-NEXT: [[EVLM:%.+]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 0, i32 %n)
+; CONVERT_LEGAL-NEXT: %r0 = add <vscale x 4 x i32> %i0, %i1
+; CONVERT_LEGAL: [[EVLM:%.+]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 0, i32 %n)
; CONVERT_LEGAL-NEXT: [[NEWM:%.+]] = and <vscale x 4 x i1> [[EVLM]], %m
; CONVERT_LEGAL-NEXT: %vscale = call i32 @llvm.vscale.i32()
; CONVERT_LEGAL-NEXT: %scalable_size = mul nuw i32 %vscale, 4
-; CONVERT_LEGAL-NEXT: %r0 = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, <vscale x 4 x i1> [[NEWM]], i32 %scalable_size)
; CONVERT_LEGAL-NOT: %{{.*}} = call <vscale x 4 x i32> @llvm.vp.{{.*}}, i32 %n)
; CONVERT_LEGAL: %r11 = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> %{{.*}}, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, i32 %scalable_size{{.*}})
-; CONVERT_LEGAL: %r12 = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> %{{.*}}, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1, i32 %scalable_size{{.*}})
+; CONVERT_LEGAL: %r12 = select <vscale x 4 x i1> %{{.*}}, <vscale x 4 x i32> %i0, <vscale x 4 x i32> %i1
; CONVERT_LEGAL: ret void
; CONVERT_LEGAL: define void @test_vp_reduce_int_v4(i32 %start, <4 x i32> %vi, <4 x i1> %m, i32 %n) {
@@ -616,11 +616,7 @@ define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x
; CONVERT_LEGAL: ret void
; CONVERT_LEGAL: define void @test_vp_cmp_v8(<8 x i32> %i0, <8 x i32> %i1, <8 x float> %f0, <8 x float> %f1, <8 x i1> %m, i32 %n) {
-; CONVERT_LEGAL-NEXT: [[NINS:%.+]] = insertelement <8 x i32> poison, i32 %n, i64 0
-; CONVERT_LEGAL-NEXT: [[NSPLAT:%.+]] = shufflevector <8 x i32> [[NINS]], <8 x i32> poison, <8 x i32> zeroinitializer
-; CONVERT_LEGAL-NEXT: [[EVLM:%.+]] = icmp ult <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, [[NSPLAT]]
-; CONVERT_LEGAL-NEXT: [[NEWM:%.+]] = and <8 x i1> [[EVLM]], %m
-; CONVERT_LEGAL-NEXT: %{{.+}} = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"eq", <8 x i1> [[NEWM]], i32 8)
+; CONVERT_LEGAL-NEXT: %{{.+}} = icmp eq <8 x i32> %i0, %i1
; CONVERT_LEGAL-NOT: %{{.+}} = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"eq", <8 x i1> %m, i32 %n)
; CONVERT_LEGAL-NOT: %{{.+}} = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"slt", <8 x i1> %m, i32 %n
; CONVERT_LEGAL-NOT: %{{.+}} = call <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float> %f0, <8 x float> %f1, metadata !"oeq", <8 x i1> %m, i32 %n)
diff --git a/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization-shufflevector-splat.ll b/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization-shufflevector-splat.ll
index 1736ce46c1a77..d5549c7bfb1a1 100644
--- a/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization-shufflevector-splat.ll
+++ b/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization-shufflevector-splat.ll
@@ -5,9 +5,9 @@ declare <4 x i64> @llvm.vp.add.v4i64(<4 x i64>, <4 x i64>, <4 x i1>, i32)
define <4 x i64> @add_v4i64_allonesmask(<4 x i64> %x) {
; CHECK-LABEL: define <4 x i64> @add_v4i64_allonesmask(
-; CHECK-SAME: <4 x i64> [[X:%.*]]) #[[ATTR1:[0-9]+]] {
+; CHECK-SAME: <4 x i64> [[X:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i64> [[X]], <4 x i64> zeroinitializer, <4 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP2:%.*]] = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> [[TMP1]], <4 x i64> zeroinitializer, <4 x i1> splat (i1 true), i32 0)
+; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i64> [[TMP1]], zeroinitializer
; CHECK-NEXT: ret <4 x i64> [[TMP2]]
;
%1 = shufflevector <4 x i64> %x, <4 x i64> zeroinitializer, <4 x i32> zeroinitializer
diff --git a/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll b/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
index 2373ff877c1db..7af17174e6df3 100644
--- a/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
+++ b/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
@@ -37,32 +37,14 @@ declare <1 x i64> @llvm.vp.mul.v1i64(<1 x i64>, <1 x i64>, <1 x i1>, i32)
declare <4 x i64> @llvm.vp.mul.v4i64(<4 x i64>, <4 x i64>, <4 x i1>, i32)
define <vscale x 1 x i64> @add_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @add_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = add i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @add_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.add.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @add_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.add.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @add_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = add <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -77,8 +59,8 @@ define <vscale x 1 x i64> @add_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
; ALL-LABEL: @add_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.add.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = add <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -89,32 +71,14 @@ define <vscale x 1 x i64> @add_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
}
define <vscale x 1 x i64> @sub_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @sub_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = sub i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @sub_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sub.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @sub_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sub.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @sub_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = sub <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -129,8 +93,8 @@ define <vscale x 1 x i64> @sub_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
; ALL-LABEL: @sub_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sub.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = sub <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -141,32 +105,14 @@ define <vscale x 1 x i64> @sub_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
}
define <vscale x 1 x i64> @mul_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @mul_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = mul i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @mul_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @mul_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @mul_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = mul <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -181,8 +127,8 @@ define <vscale x 1 x i64> @mul_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
; ALL-LABEL: @mul_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = mul <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -194,12 +140,10 @@ define <vscale x 1 x i64> @mul_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
define <vscale x 1 x i64> @sdiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
; VEC-COMBINE-64-LABEL: @sdiv_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = sdiv i64 [[Y:%.*]], 42
; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP2]]
; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
;
; NO-VEC-COMBINE-LABEL: @sdiv_nxv1i64_allonesmask(
@@ -208,7 +152,7 @@ define <vscale x 1 x i64> @sdiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sdiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
; VEC-COMBINE-32-LABEL: @sdiv_nxv1i64_allonesmask(
@@ -217,7 +161,7 @@ define <vscale x 1 x i64> @sdiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sdiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
@@ -234,7 +178,7 @@ define <vscale x 1 x i64> @sdiv_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sdiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -267,12 +211,10 @@ define <vscale x 1 x i64> @sdiv_nxv1i64_unspeculatable(i64 %x, i64 %y, i32 zeroe
define <vscale x 1 x i64> @udiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
; VEC-COMBINE-64-LABEL: @udiv_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = udiv i64 [[Y:%.*]], 42
; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP2]]
; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
;
; NO-VEC-COMBINE-LABEL: @udiv_nxv1i64_allonesmask(
@@ -281,7 +223,7 @@ define <vscale x 1 x i64> @udiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.udiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
; VEC-COMBINE-32-LABEL: @udiv_nxv1i64_allonesmask(
@@ -290,7 +232,7 @@ define <vscale x 1 x i64> @udiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.udiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
@@ -307,7 +249,7 @@ define <vscale x 1 x i64> @udiv_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.udiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -340,12 +282,10 @@ define <vscale x 1 x i64> @udiv_nxv1i64_unspeculatable(i64 %x, i64 %y, i32 zeroe
define <vscale x 1 x i64> @srem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
; VEC-COMBINE-64-LABEL: @srem_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = srem i64 [[Y:%.*]], 42
; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP2]]
; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
;
; NO-VEC-COMBINE-LABEL: @srem_nxv1i64_allonesmask(
@@ -354,7 +294,7 @@ define <vscale x 1 x i64> @srem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.srem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
; VEC-COMBINE-32-LABEL: @srem_nxv1i64_allonesmask(
@@ -363,7 +303,7 @@ define <vscale x 1 x i64> @srem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.srem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
@@ -380,7 +320,7 @@ define <vscale x 1 x i64> @srem_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.srem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -413,12 +353,10 @@ define <vscale x 1 x i64> @srem_nxv1i64_unspeculatable(i64 %x, i64 %y, i32 zeroe
define <vscale x 1 x i64> @urem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
; VEC-COMBINE-64-LABEL: @urem_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = urem i64 [[Y:%.*]], 42
; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP2]]
; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
;
; NO-VEC-COMBINE-LABEL: @urem_nxv1i64_allonesmask(
@@ -427,7 +365,7 @@ define <vscale x 1 x i64> @urem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.urem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
; VEC-COMBINE-32-LABEL: @urem_nxv1i64_allonesmask(
@@ -436,7 +374,7 @@ define <vscale x 1 x i64> @urem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.urem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
@@ -453,7 +391,7 @@ define <vscale x 1 x i64> @urem_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.urem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -649,32 +587,14 @@ define <vscale x 1 x i64> @urem_nxv1i64_anymask_knownvl(i64 %x, i64 %y, <vscale
}
define <vscale x 1 x i64> @ashr_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @ashr_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = ashr i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @ashr_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.ashr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @ashr_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.ashr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @ashr_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = ashr <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -689,8 +609,8 @@ define <vscale x 1 x i64> @ashr_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-LABEL: @ashr_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.ashr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = ashr <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -701,32 +621,14 @@ define <vscale x 1 x i64> @ashr_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
}
define <vscale x 1 x i64> @lshr_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @lshr_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = lshr i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @lshr_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.lshr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @lshr_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.lshr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @lshr_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = lshr <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -741,8 +643,8 @@ define <vscale x 1 x i64> @lshr_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-LABEL: @lshr_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.lshr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = lshr <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -753,32 +655,14 @@ define <vscale x 1 x i64> @lshr_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
}
define <vscale x 1 x i64> @shl_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @shl_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = shl i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @shl_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.shl.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @shl_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.shl.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @shl_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = shl <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -793,8 +677,8 @@ define <vscale x 1 x i64> @shl_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
; ALL-LABEL: @shl_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.shl.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = shl <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -805,32 +689,14 @@ define <vscale x 1 x i64> @shl_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
}
define <vscale x 1 x i64> @or_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @or_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = or i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @or_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.or.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @or_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.or.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @or_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = or <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -845,8 +711,8 @@ define <vscale x 1 x i64> @or_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <vs
; ALL-LABEL: @or_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.or.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = or <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -857,32 +723,14 @@ define <vscale x 1 x i64> @or_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <vs
}
define <vscale x 1 x i64> @and_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @and_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = and i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @and_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.and.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @and_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.and.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @and_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = and <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -897,8 +745,8 @@ define <vscale x 1 x i64> @and_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
; ALL-LABEL: @and_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.and.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = and <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -909,32 +757,14 @@ define <vscale x 1 x i64> @and_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
}
define <vscale x 1 x i64> @xor_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @xor_nxv1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = xor i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @xor_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.xor.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @xor_nxv1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.xor.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @xor_nxv1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = xor <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -949,8 +779,8 @@ define <vscale x 1 x i64> @xor_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
; ALL-LABEL: @xor_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.xor.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = xor <vscale x 1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -966,8 +796,8 @@ define <vscale x 1 x i64> @smin_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.smin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.smin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42))
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
@@ -983,8 +813,8 @@ define <vscale x 1 x i64> @smin_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-LABEL: @smin_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.smin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.smin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42))
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -1000,8 +830,8 @@ define <vscale x 1 x i64> @smax_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.smax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.smax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42))
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
@@ -1017,8 +847,8 @@ define <vscale x 1 x i64> @smax_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-LABEL: @smax_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.smax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.smax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42))
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -1034,8 +864,8 @@ define <vscale x 1 x i64> @umin_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.umin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.umin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42))
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
@@ -1053,8 +883,8 @@ define <vscale x 1 x i64> @umax_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.umax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.umax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42))
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
@@ -1070,8 +900,8 @@ define <vscale x 1 x i64> @umax_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
; ALL-LABEL: @umax_nxv1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.umax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.umax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> splat (i64 42))
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x i64> [[TMP4]]
;
%1 = insertelement <vscale x 1 x i64> poison, i64 %y, i64 0
@@ -1082,23 +912,14 @@ define <vscale x 1 x i64> @umax_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
}
define <vscale x 1 x float> @fadd_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @fadd_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = fadd float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fadd_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @fadd_nxv1f32_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = fadd <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1113,8 +934,8 @@ define <vscale x 1 x float> @fadd_nxv1f32_anymask(<vscale x 1 x float> %x, float
; ALL-LABEL: @fadd_nxv1f32_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = fadd <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1125,23 +946,14 @@ define <vscale x 1 x float> @fadd_nxv1f32_anymask(<vscale x 1 x float> %x, float
}
define <vscale x 1 x float> @fsub_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @fsub_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = fsub float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fsub_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fsub.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @fsub_nxv1f32_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = fsub <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1156,8 +968,8 @@ define <vscale x 1 x float> @fsub_nxv1f32_anymask(<vscale x 1 x float> %x, float
; ALL-LABEL: @fsub_nxv1f32_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fsub.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = fsub <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1168,23 +980,14 @@ define <vscale x 1 x float> @fsub_nxv1f32_anymask(<vscale x 1 x float> %x, float
}
define <vscale x 1 x float> @fdiv_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @fdiv_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = fdiv float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fdiv_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @fdiv_nxv1f32_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = fdiv <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1199,8 +1002,8 @@ define <vscale x 1 x float> @fdiv_nxv1f32_anymask(<vscale x 1 x float> %x, float
; ALL-LABEL: @fdiv_nxv1f32_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = fdiv <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1211,23 +1014,14 @@ define <vscale x 1 x float> @fdiv_nxv1f32_anymask(<vscale x 1 x float> %x, float
}
define <vscale x 1 x float> @frem_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @frem_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = frem float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @frem_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.frem.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @frem_nxv1f32_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = frem <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1242,8 +1036,8 @@ define <vscale x 1 x float> @frem_nxv1f32_allonesmask(<vscale x 1 x float> %x, f
; ALL-LABEL: @frem_nxv1f32_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.frem.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = frem <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1254,23 +1048,14 @@ define <vscale x 1 x float> @frem_nxv1f32_allonesmask(<vscale x 1 x float> %x, f
}
define <vscale x 1 x float> @fdiv_nxv1f32_allonesmask_knownvl(<vscale x 1 x float> %x, float %y) {
-; VEC-COMBINE-LABEL: @fdiv_nxv1f32_allonesmask_knownvl(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = fdiv float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 4)
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fdiv_nxv1f32_allonesmask_knownvl(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 4)
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 4)
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @fdiv_nxv1f32_allonesmask_knownvl(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = fdiv <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1285,8 +1070,8 @@ define <vscale x 1 x float> @fdiv_nxv1f32_anymask_knownvl(<vscale x 1 x float> %
; ALL-LABEL: @fdiv_nxv1f32_anymask_knownvl(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 4)
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 4)
+; ALL-NEXT: [[TMP3:%.*]] = fdiv <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1297,23 +1082,14 @@ define <vscale x 1 x float> @fdiv_nxv1f32_anymask_knownvl(<vscale x 1 x float> %
}
define <vscale x 1 x float> @frem_nxv1f32_allonesmask_knownvl(<vscale x 1 x float> %x, float %y) {
-; VEC-COMBINE-LABEL: @frem_nxv1f32_allonesmask_knownvl(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = frem float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 4)
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @frem_nxv1f32_allonesmask_knownvl(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.frem.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 4)
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 4)
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @frem_nxv1f32_allonesmask_knownvl(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = frem <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1328,8 +1104,8 @@ define <vscale x 1 x float> @frem_nxv1f32_allonesmask_knownvl(<vscale x 1 x floa
; ALL-LABEL: @frem_nxv1f32_anymask_knownvl(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.frem.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 4)
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 4)
+; ALL-NEXT: [[TMP3:%.*]] = frem <vscale x 1 x float> [[TMP2]], splat (float 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1340,23 +1116,14 @@ define <vscale x 1 x float> @frem_nxv1f32_allonesmask_knownvl(<vscale x 1 x floa
}
define <vscale x 1 x float> @copysign_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @copysign_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = call float @llvm.copysign.f32(float [[Y:%.*]], float 4.200000e+01)
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @copysign_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.copysign.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @copysign_nxv1f32_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.copysign.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01))
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1371,8 +1138,8 @@ define <vscale x 1 x float> @copysign_nxv1f32_anymask(<vscale x 1 x float> %x, f
; ALL-LABEL: @copysign_nxv1f32_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.copysign.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.copysign.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01))
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1383,23 +1150,14 @@ define <vscale x 1 x float> @copysign_nxv1f32_anymask(<vscale x 1 x float> %x, f
}
define <vscale x 1 x float> @minnum_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @minnum_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = call float @llvm.minnum.f32(float [[Y:%.*]], float 4.200000e+01)
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @minnum_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.minnum.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @minnum_nxv1f32_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.minnum.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01))
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1414,8 +1172,8 @@ define <vscale x 1 x float> @minnum_nxv1f32_anymask(<vscale x 1 x float> %x, flo
; ALL-LABEL: @minnum_nxv1f32_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.minnum.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.minnum.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01))
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1426,23 +1184,14 @@ define <vscale x 1 x float> @minnum_nxv1f32_anymask(<vscale x 1 x float> %x, flo
}
define <vscale x 1 x float> @maxnum_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @maxnum_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = call float @llvm.maxnum.f32(float [[Y:%.*]], float 4.200000e+01)
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @maxnum_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.maxnum.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @maxnum_nxv1f32_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.maxnum.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01))
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1457,8 +1206,8 @@ define <vscale x 1 x float> @maxnum_nxv1f32_anymask(<vscale x 1 x float> %x, flo
; ALL-LABEL: @maxnum_nxv1f32_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.maxnum.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01), <vscale x 1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.maxnum.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> splat (float 4.200000e+01))
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 1 x float> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 1 x float> [[TMP4]]
;
%1 = insertelement <vscale x 1 x float> poison, float %y, i64 0
@@ -1469,23 +1218,14 @@ define <vscale x 1 x float> @maxnum_nxv1f32_anymask(<vscale x 1 x float> %x, flo
}
define <vscale x 8 x i8> @add_nxv8i8_allonesmask(<vscale x 8 x i8> %x, i8 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @add_nxv8i8_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 8 x i1> [[SPLAT]], <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = add i8 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i8> poison, i8 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 8 x i8> [[DOTSPLATINSERT]], <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 8 x i8> @llvm.vp.mul.nxv8i8(<vscale x 8 x i8> [[X:%.*]], <vscale x 8 x i8> [[TMP2]], <vscale x 8 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 8 x i8> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @add_nxv8i8_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 8 x i1> [[SPLAT]], <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 8 x i8> poison, i8 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 8 x i8> [[TMP1]], <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> [[TMP2]], <vscale x 8 x i8> splat (i8 42), <vscale x 8 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 8 x i8> @llvm.vp.mul.nxv8i8(<vscale x 8 x i8> [[X:%.*]], <vscale x 8 x i8> [[TMP3]], <vscale x 8 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 8 x i8> [[TMP4]]
+; ALL-LABEL: @add_nxv8i8_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 8 x i1> [[SPLAT]], <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 8 x i8> poison, i8 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 8 x i8> [[TMP1]], <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = add <vscale x 8 x i8> [[TMP2]], splat (i8 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 8 x i8> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 8 x i8> [[TMP4]]
;
%splat = insertelement <vscale x 8 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 8 x i1> %splat, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
@@ -1500,8 +1240,8 @@ define <vscale x 8 x i8> @add_nxv8i8_anymask(<vscale x 8 x i8> %x, i8 %y, <vscal
; ALL-LABEL: @add_nxv8i8_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 8 x i8> poison, i8 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 8 x i8> [[TMP1]], <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> [[TMP2]], <vscale x 8 x i8> splat (i8 42), <vscale x 8 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 8 x i8> @llvm.vp.mul.nxv8i8(<vscale x 8 x i8> [[X:%.*]], <vscale x 8 x i8> [[TMP3]], <vscale x 8 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = add <vscale x 8 x i8> [[TMP2]], splat (i8 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <vscale x 8 x i8> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 8 x i8> [[TMP4]]
;
%1 = insertelement <vscale x 8 x i8> poison, i8 %y, i64 0
@@ -1512,23 +1252,14 @@ define <vscale x 8 x i8> @add_nxv8i8_anymask(<vscale x 8 x i8> %x, i8 %y, <vscal
}
define <vscale x 8 x half> @fadd_nxv1f16_allonesmask(<vscale x 8 x half> %x, half %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @fadd_nxv1f16_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 8 x i1> [[SPLAT]], <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = fadd half [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.vp.fadd.nxv8f16(<vscale x 8 x half> [[X:%.*]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <vscale x 8 x half> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fadd_nxv1f16_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <vscale x 8 x i1> [[SPLAT]], <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <vscale x 8 x half> poison, half [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.vp.fadd.nxv8f16(<vscale x 8 x half> [[TMP2]], <vscale x 8 x half> splat (half 4.200000e+01), <vscale x 8 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <vscale x 8 x half> @llvm.vp.fadd.nxv8f16(<vscale x 8 x half> [[X:%.*]], <vscale x 8 x half> [[TMP3]], <vscale x 8 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <vscale x 8 x half> [[TMP4]]
+; ALL-LABEL: @fadd_nxv1f16_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <vscale x 8 x i1> [[SPLAT]], <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 8 x half> poison, half [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = fadd <vscale x 8 x half> [[TMP2]], splat (half 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 8 x half> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <vscale x 8 x half> [[TMP4]]
;
%splat = insertelement <vscale x 8 x i1> poison, i1 -1, i32 0
%mask = shufflevector <vscale x 8 x i1> %splat, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
@@ -1543,8 +1274,8 @@ define <vscale x 8 x half> @fadd_nxv8f16_anymask(<vscale x 8 x half> %x, half %y
; ALL-LABEL: @fadd_nxv8f16_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <vscale x 8 x half> poison, half [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.vp.fadd.nxv8f16(<vscale x 8 x half> [[TMP2]], <vscale x 8 x half> splat (half 4.200000e+01), <vscale x 8 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <vscale x 8 x half> @llvm.vp.fadd.nxv8f16(<vscale x 8 x half> [[X:%.*]], <vscale x 8 x half> [[TMP3]], <vscale x 8 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = fadd <vscale x 8 x half> [[TMP2]], splat (half 4.200000e+01)
+; ALL-NEXT: [[TMP4:%.*]] = fadd <vscale x 8 x half> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <vscale x 8 x half> [[TMP4]]
;
%1 = insertelement <vscale x 8 x half> poison, half %y, i64 0
@@ -1555,31 +1286,14 @@ define <vscale x 8 x half> @fadd_nxv8f16_anymask(<vscale x 8 x half> %x, half %y
}
define <1 x i64> @add_v1i64_allonesmask(<1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-64-LABEL: @add_v1i64_allonesmask(
-; VEC-COMBINE-64-NEXT: [[SPLAT:%.*]] = insertelement <1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-64-NEXT: [[MASK:%.*]] = shufflevector <1 x i1> [[SPLAT]], <1 x i1> poison, <1 x i32> zeroinitializer
-; VEC-COMBINE-64-NEXT: [[TMP1:%.*]] = add i64 [[Y:%.*]], 42
-; VEC-COMBINE-64-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-64-NEXT: [[TMP3:%.*]] = call <1 x i64> @llvm.vp.mul.v1i64(<1 x i64> [[X:%.*]], <1 x i64> [[DOTSPLATINSERT]], <1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-64-NEXT: ret <1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @add_v1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <1 x i1> [[SPLAT]], <1 x i1> poison, <1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <1 x i64> [[TMP1]], <1 x i64> poison, <1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <1 x i64> @llvm.vp.add.v1i64(<1 x i64> [[TMP2]], <1 x i64> splat (i64 42), <1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <1 x i64> @llvm.vp.mul.v1i64(<1 x i64> [[X:%.*]], <1 x i64> [[TMP3]], <1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <1 x i64> [[TMP4]]
-;
-; VEC-COMBINE-32-LABEL: @add_v1i64_allonesmask(
-; VEC-COMBINE-32-NEXT: [[SPLAT:%.*]] = insertelement <1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-32-NEXT: [[MASK:%.*]] = shufflevector <1 x i1> [[SPLAT]], <1 x i1> poison, <1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP1:%.*]] = insertelement <1 x i64> poison, i64 [[Y:%.*]], i64 0
-; VEC-COMBINE-32-NEXT: [[TMP2:%.*]] = shufflevector <1 x i64> [[TMP1]], <1 x i64> poison, <1 x i32> zeroinitializer
-; VEC-COMBINE-32-NEXT: [[TMP3:%.*]] = call <1 x i64> @llvm.vp.add.v1i64(<1 x i64> [[TMP2]], <1 x i64> splat (i64 42), <1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-32-NEXT: [[TMP4:%.*]] = call <1 x i64> @llvm.vp.mul.v1i64(<1 x i64> [[X:%.*]], <1 x i64> [[TMP3]], <1 x i1> [[MASK]], i32 [[EVL]])
-; VEC-COMBINE-32-NEXT: ret <1 x i64> [[TMP4]]
+; ALL-LABEL: @add_v1i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <1 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <1 x i1> [[SPLAT]], <1 x i1> poison, <1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <1 x i64> [[TMP1]], <1 x i64> poison, <1 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = add <1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <1 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <1 x i64> [[TMP4]]
;
%splat = insertelement <1 x i1> poison, i1 -1, i32 0
%mask = shufflevector <1 x i1> %splat, <1 x i1> poison, <1 x i32> zeroinitializer
@@ -1594,8 +1308,8 @@ define <1 x i64> @add_v1i64_anymask(<1 x i64> %x, i64 %y, <1 x i1> %mask, i32 ze
; ALL-LABEL: @add_v1i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <1 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <1 x i64> [[TMP1]], <1 x i64> poison, <1 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <1 x i64> @llvm.vp.add.v1i64(<1 x i64> [[TMP2]], <1 x i64> splat (i64 42), <1 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <1 x i64> @llvm.vp.mul.v1i64(<1 x i64> [[X:%.*]], <1 x i64> [[TMP3]], <1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = add <1 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <1 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <1 x i64> [[TMP4]]
;
%1 = insertelement <1 x i64> poison, i64 %y, i64 0
@@ -1606,23 +1320,14 @@ define <1 x i64> @add_v1i64_anymask(<1 x i64> %x, i64 %y, <1 x i1> %mask, i32 ze
}
define <4 x i64> @add_v4i64_allonesmask(<4 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @add_v4i64_allonesmask(
-; VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <4 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <4 x i1> [[SPLAT]], <4 x i1> poison, <4 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP1:%.*]] = add i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <4 x i64> [[DOTSPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
-; VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <4 x i64> @llvm.vp.mul.v4i64(<4 x i64> [[X:%.*]], <4 x i64> [[TMP2]], <4 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT: ret <4 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @add_v4i64_allonesmask(
-; NO-VEC-COMBINE-NEXT: [[SPLAT:%.*]] = insertelement <4 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT: [[MASK:%.*]] = shufflevector <4 x i1> [[SPLAT]], <4 x i1> poison, <4 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT: [[TMP2:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT: [[TMP3:%.*]] = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> [[TMP2]], <4 x i64> splat (i64 42), <4 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT: [[TMP4:%.*]] = call <4 x i64> @llvm.vp.mul.v4i64(<4 x i64> [[X:%.*]], <4 x i64> [[TMP3]], <4 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT: ret <4 x i64> [[TMP4]]
+; ALL-LABEL: @add_v4i64_allonesmask(
+; ALL-NEXT: [[SPLAT:%.*]] = insertelement <4 x i1> poison, i1 true, i32 0
+; ALL-NEXT: [[MASK:%.*]] = shufflevector <4 x i1> [[SPLAT]], <4 x i1> poison, <4 x i32> zeroinitializer
+; ALL-NEXT: [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT: [[TMP2:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
+; ALL-NEXT: [[TMP3:%.*]] = add <4 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <4 x i64> [[X:%.*]], [[TMP3]]
+; ALL-NEXT: ret <4 x i64> [[TMP4]]
;
%splat = insertelement <4 x i1> poison, i1 -1, i32 0
%mask = shufflevector <4 x i1> %splat, <4 x i1> poison, <4 x i32> zeroinitializer
@@ -1637,8 +1342,8 @@ define <4 x i64> @add_v4i64_anymask(<4 x i64> %x, i64 %y, <4 x i1> %mask, i32 ze
; ALL-LABEL: @add_v4i64_anymask(
; ALL-NEXT: [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[Y:%.*]], i64 0
; ALL-NEXT: [[TMP2:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
-; ALL-NEXT: [[TMP3:%.*]] = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> [[TMP2]], <4 x i64> splat (i64 42), <4 x i1> [[MASK:%.*]], i32 [[EVL:%.*]])
-; ALL-NEXT: [[TMP4:%.*]] = call <4 x i64> @llvm.vp.mul.v4i64(<4 x i64> [[X:%.*]], <4 x i64> [[TMP3]], <4 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT: [[TMP3:%.*]] = add <4 x i64> [[TMP2]], splat (i64 42)
+; ALL-NEXT: [[TMP4:%.*]] = mul <4 x i64> [[X:%.*]], [[TMP3]]
; ALL-NEXT: ret <4 x i64> [[TMP4]]
;
%1 = insertelement <4 x i64> poison, i64 %y, i64 0
More information about the llvm-commits
mailing list