[llvm] [RISCV][CostModel] cost of vector cttz/ctlz under ZVBB (PR #115800)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 11 18:04:59 PST 2024
https://github.com/LiqinWeng created https://github.com/llvm/llvm-project/pull/115800
None
>From b2efe619a7eb8ff72de56b9a37d73f7501599cd1 Mon Sep 17 00:00:00 2001
From: LiqinWeng <liqin.weng at spacemit.com>
Date: Mon, 11 Nov 2024 19:02:29 +0800
Subject: [PATCH] [RISCV][CostModel] cost of vector cttz/ctlz under ZVBB
---
.../Target/RISCV/RISCVTargetTransformInfo.cpp | 2 +
.../Analysis/CostModel/RISCV/int-bit-manip.ll | 334 ++++++++++++++++++
2 files changed, 336 insertions(+)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 046f63fe1617c5..9fa6624aae89f8 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1035,6 +1035,8 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
return LT.first;
break;
}
+ case Intrinsic::cttz:
+ case Intrinsic::ctlz:
case Intrinsic::ctpop: {
auto LT = getTypeLegalizationCost(RetTy);
if (ST->hasVInstructions() && ST->hasStdExtZvbb() && LT.second.isVector())
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
index ea05464b084086..911993caba4d65 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
@@ -157,6 +157,260 @@ define void @bitreverse() {
ret void
}
+define void @ctlz() {
+; NOZVBB-LABEL: 'ctlz'
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 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 2 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 2 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 2 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 2 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 2 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 2 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 2 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 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %10 = call <vscale x 32 x i8> @llvm.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost 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 2 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 2 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 2 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 2 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 2 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 2 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 2 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 2 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 2 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost 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 2 for instruction: %22 = call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %23 = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <16 x i32> @llvm.ctlz.v16i32(<16 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = 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 2 for instruction: %27 = 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 2 for instruction: %28 = 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 2 for instruction: %29 = 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 2 for instruction: %30 = 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 2 for instruction: %31 = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %32 = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <8 x i64> @llvm.ctlz.v8i64(<8 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <16 x i64> @llvm.ctlz.v16i64(<16 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %35 = 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 2 for instruction: %36 = 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 2 for instruction: %37 = 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 2 for instruction: %38 = 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 4 for instruction: %39 = 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: '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 1 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 1 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 1 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 1 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 1 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 1 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 1 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 i32> @llvm.ctlz.v2i32(<2 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = 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: %26 = 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: %27 = 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 1 for instruction: %28 = 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 1 for instruction: %29 = 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 1 for instruction: %30 = 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: %31 = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <8 x i64> @llvm.ctlz.v8i64(<8 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = 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: %35 = 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 1 for instruction: %36 = 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 1 for instruction: %37 = 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 1 for instruction: %38 = 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 2 for instruction: %39 = 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.ctlz.v2i8(<2 x i8> undef, i1 false)
+ call <4 x i8> @llvm.ctlz.v4i8(<4 x i8> undef, i1 false)
+ call <8 x i8> @llvm.ctlz.v8i8(<8 x i8> undef, i1 false)
+ call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> undef, i1 false)
+ call <vscale x 1 x i8> @llvm.ctlz.nxv1i8(<vscale x 1 x i8> undef, i1 false)
+ call <vscale x 2 x i8> @llvm.ctlz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+ call <vscale x 4 x i8> @llvm.ctlz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+ call <vscale x 8 x i8> @llvm.ctlz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+ call <vscale x 16 x i8> @llvm.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+ call <vscale x 32 x i8> @llvm.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+ call <vscale x 64 x i8> @llvm.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+ call <2 x i16> @llvm.ctlz.v2i16(<2 x i16> undef, i1 false)
+ call <4 x i16> @llvm.ctlz.v4i16(<4 x i16> undef, i1 false)
+ call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> undef, i1 false)
+ call <16 x i16> @llvm.ctlz.v16i16(<16 x i16> undef, i1 false)
+ call <vscale x 1 x i16> @llvm.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+ call <vscale x 2 x i16> @llvm.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+ call <vscale x 4 x i16> @llvm.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+ call <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+ call <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+ call <vscale x 32 x i16> @llvm.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+ call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> undef, i1 false)
+ call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> undef, i1 false)
+ call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> undef, i1 false)
+ call <16 x i32> @llvm.ctlz.v16i32(<16 x i32> undef, i1 false)
+ call <vscale x 1 x i32> @llvm.ctlz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
+ call <vscale x 2 x i32> @llvm.ctlz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
+ call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+ call <vscale x 8 x i32> @llvm.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+ call <vscale x 16 x i32> @llvm.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+ call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> undef, i1 false)
+ call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> undef, i1 false)
+ call <8 x i64> @llvm.ctlz.v8i64(<8 x i64> undef, i1 false)
+ call <16 x i64> @llvm.ctlz.v16i64(<16 x i64> undef, i1 false)
+ call <vscale x 1 x i64> @llvm.ctlz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
+ call <vscale x 2 x i64> @llvm.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+ call <vscale x 4 x i64> @llvm.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+ call <vscale x 8 x i64> @llvm.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+ call <vscale x 16 x i64> @llvm.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+ ret void
+}
+
+define void @cttz() {
+; NOZVBB-LABEL: 'cttz'
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 22 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 44 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 88 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 176 for instruction: %4 = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %5 = call <vscale x 1 x i8> @llvm.cttz.nxv1i8(<vscale x 1 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x i8> @llvm.cttz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x i8> @llvm.cttz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x i8> @llvm.cttz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x i8> @llvm.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %10 = call <vscale x 32 x i8> @llvm.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost 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 22 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 44 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 88 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 191 for instruction: %15 = call <16 x i16> @llvm.cttz.v16i16(<16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x i16> @llvm.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i16> @llvm.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x i16> @llvm.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %20 = call <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost 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 22 for instruction: %22 = call <2 x i32> @llvm.cttz.v2i32(<2 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %23 = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 95 for instruction: %24 = call <8 x i32> @llvm.cttz.v8i32(<8 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 191 for instruction: %25 = call <16 x i32> @llvm.cttz.v16i32(<16 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %26 = call <vscale x 1 x i32> @llvm.cttz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %27 = call <vscale x 2 x i32> @llvm.cttz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %28 = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %29 = call <vscale x 8 x i32> @llvm.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %30 = 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 22 for instruction: %31 = call <2 x i64> @llvm.cttz.v2i64(<2 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %32 = call <4 x i64> @llvm.cttz.v4i64(<4 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 95 for instruction: %33 = call <8 x i64> @llvm.cttz.v8i64(<8 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 191 for instruction: %34 = call <16 x i64> @llvm.cttz.v16i64(<16 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %35 = call <vscale x 1 x i64> @llvm.cttz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %36 = call <vscale x 2 x i64> @llvm.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %37 = call <vscale x 4 x i64> @llvm.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %38 = call <vscale x 8 x i64> @llvm.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; NOZVBB-NEXT: Cost Model: Invalid cost for instruction: %39 = 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: '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 1 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 1 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 1 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 1 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 1 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 1 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 1 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 i32> @llvm.cttz.v2i32(<2 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.cttz.v8i32(<8 x i32> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = 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: %26 = 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: %27 = 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 1 for instruction: %28 = 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 1 for instruction: %29 = 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 1 for instruction: %30 = 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: %31 = call <2 x i64> @llvm.cttz.v2i64(<2 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <4 x i64> @llvm.cttz.v4i64(<4 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <8 x i64> @llvm.cttz.v8i64(<8 x i64> undef, i1 false)
+; ZVBB-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = 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: %35 = 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 1 for instruction: %36 = 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 1 for instruction: %37 = 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 1 for instruction: %38 = 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 2 for instruction: %39 = 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.cttz.v2i8(<2 x i8> undef, i1 false)
+ call <4 x i8> @llvm.cttz.v4i8(<4 x i8> undef, i1 false)
+ call <8 x i8> @llvm.cttz.v8i8(<8 x i8> undef, i1 false)
+ call <16 x i8> @llvm.cttz.v16i8(<16 x i8> undef, i1 false)
+ call <vscale x 1 x i8> @llvm.cttz.nxv1i8(<vscale x 1 x i8> undef, i1 false)
+ call <vscale x 2 x i8> @llvm.cttz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+ call <vscale x 4 x i8> @llvm.cttz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+ call <vscale x 8 x i8> @llvm.cttz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+ call <vscale x 16 x i8> @llvm.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+ call <vscale x 32 x i8> @llvm.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+ call <vscale x 64 x i8> @llvm.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+ call <2 x i16> @llvm.cttz.v2i16(<2 x i16> undef, i1 false)
+ call <4 x i16> @llvm.cttz.v4i16(<4 x i16> undef, i1 false)
+ call <8 x i16> @llvm.cttz.v8i16(<8 x i16> undef, i1 false)
+ call <16 x i16> @llvm.cttz.v16i16(<16 x i16> undef, i1 false)
+ call <vscale x 1 x i16> @llvm.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
+ call <vscale x 2 x i16> @llvm.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
+ call <vscale x 4 x i16> @llvm.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
+ call <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+ call <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+ call <vscale x 32 x i16> @llvm.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+ call <2 x i32> @llvm.cttz.v2i32(<2 x i32> undef, i1 false)
+ call <4 x i32> @llvm.cttz.v4i32(<4 x i32> undef, i1 false)
+ call <8 x i32> @llvm.cttz.v8i32(<8 x i32> undef, i1 false)
+ call <16 x i32> @llvm.cttz.v16i32(<16 x i32> undef, i1 false)
+ call <vscale x 1 x i32> @llvm.cttz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
+ call <vscale x 2 x i32> @llvm.cttz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
+ call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+ call <vscale x 8 x i32> @llvm.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+ call <vscale x 16 x i32> @llvm.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+ call <2 x i64> @llvm.cttz.v2i64(<2 x i64> undef, i1 false)
+ call <4 x i64> @llvm.cttz.v4i64(<4 x i64> undef, i1 false)
+ call <8 x i64> @llvm.cttz.v8i64(<8 x i64> undef, i1 false)
+ call <16 x i64> @llvm.cttz.v16i64(<16 x i64> undef, i1 false)
+ call <vscale x 1 x i64> @llvm.cttz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
+ call <vscale x 2 x i64> @llvm.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+ call <vscale x 4 x i64> @llvm.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+ call <vscale x 8 x i64> @llvm.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+ call <vscale x 16 x i64> @llvm.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+ ret void
+}
+
define void @ctpop() {
; NOZVBB-LABEL: 'ctpop'
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %1 = call i8 @llvm.ctpop.i8(i8 undef)
@@ -778,6 +1032,86 @@ declare <vscale x 4 x i64> @llvm.vp.bswap.nxv4i64(<vscale x 4 x i64>, <vscale x
declare <vscale x 8 x i64> @llvm.vp.bswap.nxv8i64(<vscale x 8 x i64>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i64> @llvm.vp.bswap.nxv16i64(<vscale x 16 x i64>, <vscale x 16 x i1>, i32)
+declare <2 x i8> @llvm.ctlz.v2i8(<2 x i8>, i1)
+declare <4 x i8> @llvm.ctlz.v4i8(<4 x i8>, i1)
+declare <8 x i8> @llvm.ctlz.v8i8(<8 x i8>, i1)
+declare <16 x i8> @llvm.ctlz.v16i8(<16 x i8>, i1)
+declare <vscale x 1 x i8> @llvm.ctlz.nxv1i8(<vscale x 1 x i8>, i1)
+declare <vscale x 2 x i8> @llvm.ctlz.nxv2i8(<vscale x 2 x i8>, i1)
+declare <vscale x 4 x i8> @llvm.ctlz.nxv4i8(<vscale x 4 x i8>, i1)
+declare <vscale x 8 x i8> @llvm.ctlz.nxv8i8(<vscale x 8 x i8>, i1)
+declare <vscale x 16 x i8> @llvm.ctlz.nxv16i8(<vscale x 16 x i8>, i1)
+declare <vscale x 32 x i8> @llvm.ctlz.nxv32i8(<vscale x 32 x i8>, i1)
+declare <vscale x 64 x i8> @llvm.ctlz.nxv64i8(<vscale x 64 x i8>, i1)
+declare <2 x i16> @llvm.ctlz.v2i16(<2 x i16>, i1)
+declare <4 x i16> @llvm.ctlz.v4i16(<4 x i16>, i1)
+declare <8 x i16> @llvm.ctlz.v8i16(<8 x i16>, i1)
+declare <16 x i16> @llvm.ctlz.v16i16(<16 x i16>, i1)
+declare <vscale x 1 x i16> @llvm.ctlz.nxv1i16(<vscale x 1 x i16>, i1)
+declare <vscale x 2 x i16> @llvm.ctlz.nxv2i16(<vscale x 2 x i16>, i1)
+declare <vscale x 4 x i16> @llvm.ctlz.nxv4i16(<vscale x 4 x i16>, i1)
+declare <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16>, i1)
+declare <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16>, i1)
+declare <vscale x 32 x i16> @llvm.ctlz.nxv32i16(<vscale x 32 x i16>, i1)
+declare <2 x i32> @llvm.ctlz.v2i32(<2 x i32>, i1)
+declare <4 x i32> @llvm.ctlz.v4i32(<4 x i32>, i1)
+declare <8 x i32> @llvm.ctlz.v8i32(<8 x i32>, i1)
+declare <16 x i32> @llvm.ctlz.v16i32(<16 x i32>, i1)
+declare <vscale x 1 x i32> @llvm.ctlz.nxv1i32(<vscale x 1 x i32>, i1)
+declare <vscale x 2 x i32> @llvm.ctlz.nxv2i32(<vscale x 2 x i32>, i1)
+declare <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32>, i1)
+declare <vscale x 8 x i32> @llvm.ctlz.nxv8i32(<vscale x 8 x i32>, i1)
+declare <vscale x 16 x i32> @llvm.ctlz.nxv16i32(<vscale x 16 x i32>, i1)
+declare <2 x i64> @llvm.ctlz.v2i64(<2 x i64>, i1)
+declare <4 x i64> @llvm.ctlz.v4i64(<4 x i64>, i1)
+declare <8 x i64> @llvm.ctlz.v8i64(<8 x i64>, i1)
+declare <16 x i64> @llvm.ctlz.v16i64(<16 x i64>, i1)
+declare <vscale x 1 x i64> @llvm.ctlz.nxv1i64(<vscale x 1 x i64>, i1)
+declare <vscale x 2 x i64> @llvm.ctlz.nxv2i64(<vscale x 2 x i64>, i1)
+declare <vscale x 4 x i64> @llvm.ctlz.nxv4i64(<vscale x 4 x i64>, i1)
+declare <vscale x 8 x i64> @llvm.ctlz.nxv8i64(<vscale x 8 x i64>, i1)
+declare <vscale x 16 x i64> @llvm.ctlz.nxv16i64(<vscale x 16 x i64>, i1)
+
+declare <2 x i8> @llvm.cttz.v2i8(<2 x i8>, i1)
+declare <4 x i8> @llvm.cttz.v4i8(<4 x i8>, i1)
+declare <8 x i8> @llvm.cttz.v8i8(<8 x i8>, i1)
+declare <16 x i8> @llvm.cttz.v16i8(<16 x i8>, i1)
+declare <vscale x 1 x i8> @llvm.cttz.nxv1i8(<vscale x 1 x i8>, i1)
+declare <vscale x 2 x i8> @llvm.cttz.nxv2i8(<vscale x 2 x i8>, i1)
+declare <vscale x 4 x i8> @llvm.cttz.nxv4i8(<vscale x 4 x i8>, i1)
+declare <vscale x 8 x i8> @llvm.cttz.nxv8i8(<vscale x 8 x i8>, i1)
+declare <vscale x 16 x i8> @llvm.cttz.nxv16i8(<vscale x 16 x i8>, i1)
+declare <vscale x 32 x i8> @llvm.cttz.nxv32i8(<vscale x 32 x i8>, i1)
+declare <vscale x 64 x i8> @llvm.cttz.nxv64i8(<vscale x 64 x i8>, i1)
+declare <2 x i16> @llvm.cttz.v2i16(<2 x i16>, i1)
+declare <4 x i16> @llvm.cttz.v4i16(<4 x i16>, i1)
+declare <8 x i16> @llvm.cttz.v8i16(<8 x i16>, i1)
+declare <16 x i16> @llvm.cttz.v16i16(<16 x i16>, i1)
+declare <vscale x 1 x i16> @llvm.cttz.nxv1i16(<vscale x 1 x i16>, i1)
+declare <vscale x 2 x i16> @llvm.cttz.nxv2i16(<vscale x 2 x i16>, i1)
+declare <vscale x 4 x i16> @llvm.cttz.nxv4i16(<vscale x 4 x i16>, i1)
+declare <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16>, i1)
+declare <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16>, i1)
+declare <vscale x 32 x i16> @llvm.cttz.nxv32i16(<vscale x 32 x i16>, i1)
+declare <2 x i32> @llvm.cttz.v2i32(<2 x i32>, i1)
+declare <4 x i32> @llvm.cttz.v4i32(<4 x i32>, i1)
+declare <8 x i32> @llvm.cttz.v8i32(<8 x i32>, i1)
+declare <16 x i32> @llvm.cttz.v16i32(<16 x i32>, i1)
+declare <vscale x 1 x i32> @llvm.cttz.nxv1i32(<vscale x 1 x i32>, i1)
+declare <vscale x 2 x i32> @llvm.cttz.nxv2i32(<vscale x 2 x i32>, i1)
+declare <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32>, i1)
+declare <vscale x 8 x i32> @llvm.cttz.nxv8i32(<vscale x 8 x i32>, i1)
+declare <vscale x 16 x i32> @llvm.cttz.nxv16i32(<vscale x 16 x i32>, i1)
+declare <2 x i64> @llvm.cttz.v2i64(<2 x i64>, i1)
+declare <4 x i64> @llvm.cttz.v4i64(<4 x i64>, i1)
+declare <8 x i64> @llvm.cttz.v8i64(<8 x i64>, i1)
+declare <16 x i64> @llvm.cttz.v16i64(<16 x i64>, i1)
+declare <vscale x 1 x i64> @llvm.cttz.nxv1i64(<vscale x 1 x i64>, i1)
+declare <vscale x 2 x i64> @llvm.cttz.nxv2i64(<vscale x 2 x i64>, i1)
+declare <vscale x 4 x i64> @llvm.cttz.nxv4i64(<vscale x 4 x i64>, i1)
+declare <vscale x 8 x i64> @llvm.cttz.nxv8i64(<vscale x 8 x i64>, i1)
+declare <vscale x 16 x i64> @llvm.cttz.nxv16i64(<vscale x 16 x i64>, i1)
+
declare <2 x i8> @llvm.vp.ctpop.v2i8(<2 x i8>, <2 x i1>, i32)
declare <4 x i8> @llvm.vp.ctpop.v4i8(<4 x i8>, <4 x i1>, i32)
declare <8 x i8> @llvm.vp.ctpop.v8i8(<8 x i8>, <8 x i1>, i32)
More information about the llvm-commits
mailing list