[llvm] 73c2cb5 - [RISCV] Merge RV32/RV64 CHECK lines in strided vp load/store tests. NFC
Luke Lau via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 19 04:25:32 PDT 2023
Author: Luke Lau
Date: 2023-09-19T12:24:32+01:00
New Revision: 73c2cb5999132f45df5314f00cc4bf9894cf100b
URL: https://github.com/llvm/llvm-project/commit/73c2cb5999132f45df5314f00cc4bf9894cf100b
DIFF: https://github.com/llvm/llvm-project/commit/73c2cb5999132f45df5314f00cc4bf9894cf100b.diff
LOG: [RISCV] Merge RV32/RV64 CHECK lines in strided vp load/store tests. NFC
Added:
Modified:
llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll
llvm/test/CodeGen/RISCV/rvv/strided-vpstore.ll
Removed:
################################################################################
diff --git a/llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll b/llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll
index c023c6a86f8b682..d8431ad7662d923 100644
--- a/llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/strided-vpload.ll
@@ -1,23 +1,19 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+m,+d,+zfh,+v,+zvfh \
-; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK-RV32
+; RUN: -verify-machineinstrs < %s | FileCheck %s \
+; RUN: -check-prefixes=CHECK,CHECK-RV32
; RUN: llc -mtriple=riscv64 -mattr=+m,+d,+zfh,+v,+zvfh \
-; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK-RV64
+; RUN: -verify-machineinstrs < %s | FileCheck %s \
+; RUN: -check-prefixes=CHECK,CHECK-RV64
declare <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i8(ptr, i8, <vscale x 1 x i1>, i32)
define <vscale x 1 x i8> @strided_vpload_nxv1i8_i8(ptr %ptr, i8 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1i8_i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV32-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1i8_i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV64-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1i8_i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
+; CHECK-NEXT: vlse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i8(ptr %ptr, i8 %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x i8> %load
}
@@ -25,17 +21,11 @@ define <vscale x 1 x i8> @strided_vpload_nxv1i8_i8(ptr %ptr, i8 signext %stride,
declare <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i16(ptr, i16, <vscale x 1 x i1>, i32)
define <vscale x 1 x i8> @strided_vpload_nxv1i8_i16(ptr %ptr, i16 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1i8_i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV32-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1i8_i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV64-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1i8_i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
+; CHECK-NEXT: vlse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i16(ptr %ptr, i16 %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x i8> %load
}
@@ -79,33 +69,21 @@ define <vscale x 1 x i8> @strided_vpload_nxv1i8_i64_allones_mask(ptr %ptr, i64 s
declare <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)
define <vscale x 1 x i8> @strided_vpload_nxv1i8(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV32-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV64-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
+; CHECK-NEXT: vlse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x i8> %load
}
define <vscale x 1 x i8> @strided_vpload_nxv1i8_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1i8_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV32-NEXT: vlse8.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1i8_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV64-NEXT: vlse8.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1i8_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
+; CHECK-NEXT: vlse8.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 1 x i1> %a, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
%load = call <vscale x 1 x i8> @llvm.experimental.vp.strided.load.nxv1i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %b, i32 %evl)
@@ -115,17 +93,11 @@ define <vscale x 1 x i8> @strided_vpload_nxv1i8_allones_mask(ptr %ptr, i32 signe
declare <vscale x 2 x i8> @llvm.experimental.vp.strided.load.nxv2i8.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)
define <vscale x 2 x i8> @strided_vpload_nxv2i8(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf4, ta, ma
-; CHECK-RV32-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf4, ta, ma
-; CHECK-RV64-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf4, ta, ma
+; CHECK-NEXT: vlse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.experimental.vp.strided.load.nxv2i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x i8> %load
}
@@ -133,17 +105,11 @@ define <vscale x 2 x i8> @strided_vpload_nxv2i8(ptr %ptr, i32 signext %stride, <
declare <vscale x 4 x i8> @llvm.experimental.vp.strided.load.nxv4i8.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)
define <vscale x 4 x i8> @strided_vpload_nxv4i8(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf2, ta, ma
-; CHECK-RV32-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf2, ta, ma
-; CHECK-RV64-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf2, ta, ma
+; CHECK-NEXT: vlse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 4 x i8> @llvm.experimental.vp.strided.load.nxv4i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x i8> %load
}
@@ -151,33 +117,21 @@ define <vscale x 4 x i8> @strided_vpload_nxv4i8(ptr %ptr, i32 signext %stride, <
declare <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)
define <vscale x 8 x i8> @strided_vpload_nxv8i8(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, m1, ta, ma
-; CHECK-RV32-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, m1, ta, ma
-; CHECK-RV64-NEXT: vlse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, m1, ta, ma
+; CHECK-NEXT: vlse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x i8> %load
}
define <vscale x 8 x i8> @strided_vpload_nxv8i8_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8i8_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, m1, ta, ma
-; CHECK-RV32-NEXT: vlse8.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8i8_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, m1, ta, ma
-; CHECK-RV64-NEXT: vlse8.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8i8_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, m1, ta, ma
+; CHECK-NEXT: vlse8.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 8 x i1> %a, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
%load = call <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %b, i32 %evl)
@@ -187,17 +141,11 @@ define <vscale x 8 x i8> @strided_vpload_nxv8i8_allones_mask(ptr %ptr, i32 signe
declare <vscale x 1 x i16> @llvm.experimental.vp.strided.load.nxv1i16.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)
define <vscale x 1 x i16> @strided_vpload_nxv1i16(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x i16> @llvm.experimental.vp.strided.load.nxv1i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x i16> %load
}
@@ -205,33 +153,21 @@ define <vscale x 1 x i16> @strided_vpload_nxv1i16(ptr %ptr, i32 signext %stride,
declare <vscale x 2 x i16> @llvm.experimental.vp.strided.load.nxv2i16.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)
define <vscale x 2 x i16> @strided_vpload_nxv2i16(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.experimental.vp.strided.load.nxv2i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x i16> %load
}
define <vscale x 2 x i16> @strided_vpload_nxv2i16_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2i16_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2i16_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2i16_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 2 x i1> %a, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
%load = call <vscale x 2 x i16> @llvm.experimental.vp.strided.load.nxv2i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %b, i32 %evl)
@@ -241,17 +177,11 @@ define <vscale x 2 x i16> @strided_vpload_nxv2i16_allones_mask(ptr %ptr, i32 sig
declare <vscale x 4 x i16> @llvm.experimental.vp.strided.load.nxv4i16.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)
define <vscale x 4 x i16> @strided_vpload_nxv4i16(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, m1, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, m1, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, m1, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 4 x i16> @llvm.experimental.vp.strided.load.nxv4i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x i16> %load
}
@@ -259,17 +189,11 @@ define <vscale x 4 x i16> @strided_vpload_nxv4i16(ptr %ptr, i32 signext %stride,
declare <vscale x 8 x i16> @llvm.experimental.vp.strided.load.nxv8i16.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)
define <vscale x 8 x i16> @strided_vpload_nxv8i16(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, m2, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, m2, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, m2, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 8 x i16> @llvm.experimental.vp.strided.load.nxv8i16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x i16> %load
}
@@ -277,17 +201,11 @@ define <vscale x 8 x i16> @strided_vpload_nxv8i16(ptr %ptr, i32 signext %stride,
declare <vscale x 1 x i32> @llvm.experimental.vp.strided.load.nxv1i32.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)
define <vscale x 1 x i32> @strided_vpload_nxv1i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1i32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1i32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x i32> @llvm.experimental.vp.strided.load.nxv1i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x i32> %load
}
@@ -295,17 +213,11 @@ define <vscale x 1 x i32> @strided_vpload_nxv1i32(ptr %ptr, i32 signext %stride,
declare <vscale x 2 x i32> @llvm.experimental.vp.strided.load.nxv2i32.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)
define <vscale x 2 x i32> @strided_vpload_nxv2i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2i32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m1, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2i32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m1, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m1, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.experimental.vp.strided.load.nxv2i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x i32> %load
}
@@ -313,33 +225,21 @@ define <vscale x 2 x i32> @strided_vpload_nxv2i32(ptr %ptr, i32 signext %stride,
declare <vscale x 4 x i32> @llvm.experimental.vp.strided.load.nxv4i32.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)
define <vscale x 4 x i32> @strided_vpload_nxv4i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4i32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4i32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 4 x i32> @llvm.experimental.vp.strided.load.nxv4i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x i32> %load
}
define <vscale x 4 x i32> @strided_vpload_nxv4i32_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4i32_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4i32_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4i32_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 4 x i1> %a, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
%load = call <vscale x 4 x i32> @llvm.experimental.vp.strided.load.nxv4i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %b, i32 %evl)
@@ -349,17 +249,11 @@ define <vscale x 4 x i32> @strided_vpload_nxv4i32_allones_mask(ptr %ptr, i32 sig
declare <vscale x 8 x i32> @llvm.experimental.vp.strided.load.nxv8i32.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)
define <vscale x 8 x i32> @strided_vpload_nxv8i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8i32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8i32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m4, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 8 x i32> @llvm.experimental.vp.strided.load.nxv8i32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x i32> %load
}
@@ -367,33 +261,21 @@ define <vscale x 8 x i32> @strided_vpload_nxv8i32(ptr %ptr, i32 signext %stride,
declare <vscale x 1 x i64> @llvm.experimental.vp.strided.load.nxv1i64.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)
define <vscale x 1 x i64> @strided_vpload_nxv1i64(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1i64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1i64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1i64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m1, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x i64> @llvm.experimental.vp.strided.load.nxv1i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x i64> %load
}
define <vscale x 1 x i64> @strided_vpload_nxv1i64_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1i64_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1i64_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1i64_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m1, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 1 x i1> %a, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
%load = call <vscale x 1 x i64> @llvm.experimental.vp.strided.load.nxv1i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %b, i32 %evl)
@@ -403,17 +285,11 @@ define <vscale x 1 x i64> @strided_vpload_nxv1i64_allones_mask(ptr %ptr, i32 sig
declare <vscale x 2 x i64> @llvm.experimental.vp.strided.load.nxv2i64.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)
define <vscale x 2 x i64> @strided_vpload_nxv2i64(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2i64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m2, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2i64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m2, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2i64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m2, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 2 x i64> @llvm.experimental.vp.strided.load.nxv2i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x i64> %load
}
@@ -421,17 +297,11 @@ define <vscale x 2 x i64> @strided_vpload_nxv2i64(ptr %ptr, i32 signext %stride,
declare <vscale x 4 x i64> @llvm.experimental.vp.strided.load.nxv4i64.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)
define <vscale x 4 x i64> @strided_vpload_nxv4i64(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4i64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4i64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4i64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 4 x i64> @llvm.experimental.vp.strided.load.nxv4i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x i64> %load
}
@@ -439,17 +309,11 @@ define <vscale x 4 x i64> @strided_vpload_nxv4i64(ptr %ptr, i32 signext %stride,
declare <vscale x 8 x i64> @llvm.experimental.vp.strided.load.nxv8i64.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)
define <vscale x 8 x i64> @strided_vpload_nxv8i64(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8i64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8i64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8i64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 8 x i64> @llvm.experimental.vp.strided.load.nxv8i64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x i64> %load
}
@@ -457,17 +321,11 @@ define <vscale x 8 x i64> @strided_vpload_nxv8i64(ptr %ptr, i32 signext %stride,
declare <vscale x 1 x half> @llvm.experimental.vp.strided.load.nxv1f16.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)
define <vscale x 1 x half> @strided_vpload_nxv1f16(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1f16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1f16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1f16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x half> @llvm.experimental.vp.strided.load.nxv1f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x half> %load
}
@@ -475,33 +333,21 @@ define <vscale x 1 x half> @strided_vpload_nxv1f16(ptr %ptr, i32 signext %stride
declare <vscale x 2 x half> @llvm.experimental.vp.strided.load.nxv2f16.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)
define <vscale x 2 x half> @strided_vpload_nxv2f16(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2f16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2f16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2f16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 2 x half> @llvm.experimental.vp.strided.load.nxv2f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x half> %load
}
define <vscale x 2 x half> @strided_vpload_nxv2f16_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2f16_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2f16_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2f16_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 2 x i1> %a, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
%load = call <vscale x 2 x half> @llvm.experimental.vp.strided.load.nxv2f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %b, i32 %evl)
@@ -511,17 +357,11 @@ define <vscale x 2 x half> @strided_vpload_nxv2f16_allones_mask(ptr %ptr, i32 si
declare <vscale x 4 x half> @llvm.experimental.vp.strided.load.nxv4f16.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)
define <vscale x 4 x half> @strided_vpload_nxv4f16(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4f16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, m1, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4f16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, m1, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4f16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, m1, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 4 x half> @llvm.experimental.vp.strided.load.nxv4f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x half> %load
}
@@ -529,17 +369,11 @@ define <vscale x 4 x half> @strided_vpload_nxv4f16(ptr %ptr, i32 signext %stride
declare <vscale x 8 x half> @llvm.experimental.vp.strided.load.nxv8f16.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)
define <vscale x 8 x half> @strided_vpload_nxv8f16(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8f16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, m2, ta, ma
-; CHECK-RV32-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8f16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, m2, ta, ma
-; CHECK-RV64-NEXT: vlse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8f16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, m2, ta, ma
+; CHECK-NEXT: vlse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 8 x half> @llvm.experimental.vp.strided.load.nxv8f16.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x half> %load
}
@@ -547,17 +381,11 @@ define <vscale x 8 x half> @strided_vpload_nxv8f16(ptr %ptr, i32 signext %stride
declare <vscale x 1 x float> @llvm.experimental.vp.strided.load.nxv1f32.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)
define <vscale x 1 x float> @strided_vpload_nxv1f32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x float> @llvm.experimental.vp.strided.load.nxv1f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x float> %load
}
@@ -565,17 +393,11 @@ define <vscale x 1 x float> @strided_vpload_nxv1f32(ptr %ptr, i32 signext %strid
declare <vscale x 2 x float> @llvm.experimental.vp.strided.load.nxv2f32.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)
define <vscale x 2 x float> @strided_vpload_nxv2f32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m1, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m1, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m1, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 2 x float> @llvm.experimental.vp.strided.load.nxv2f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x float> %load
}
@@ -583,17 +405,11 @@ define <vscale x 2 x float> @strided_vpload_nxv2f32(ptr %ptr, i32 signext %strid
declare <vscale x 4 x float> @llvm.experimental.vp.strided.load.nxv4f32.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)
define <vscale x 4 x float> @strided_vpload_nxv4f32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 4 x float> @llvm.experimental.vp.strided.load.nxv4f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x float> %load
}
@@ -601,33 +417,21 @@ define <vscale x 4 x float> @strided_vpload_nxv4f32(ptr %ptr, i32 signext %strid
declare <vscale x 8 x float> @llvm.experimental.vp.strided.load.nxv8f32.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)
define <vscale x 8 x float> @strided_vpload_nxv8f32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m4, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 8 x float> @llvm.experimental.vp.strided.load.nxv8f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x float> %load
}
define <vscale x 8 x float> @strided_vpload_nxv8f32_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8f32_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV32-NEXT: vlse32.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8f32_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV64-NEXT: vlse32.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8f32_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m4, ta, ma
+; CHECK-NEXT: vlse32.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 8 x i1> %a, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
%load = call <vscale x 8 x float> @llvm.experimental.vp.strided.load.nxv8f32.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %b, i32 %evl)
@@ -637,17 +441,11 @@ define <vscale x 8 x float> @strided_vpload_nxv8f32_allones_mask(ptr %ptr, i32 s
declare <vscale x 1 x double> @llvm.experimental.vp.strided.load.nxv1f64.p0.i32(ptr, i32, <vscale x 1 x i1>, i32)
define <vscale x 1 x double> @strided_vpload_nxv1f64(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv1f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv1f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv1f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m1, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 1 x double> @llvm.experimental.vp.strided.load.nxv1f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x double> %load
}
@@ -655,17 +453,11 @@ define <vscale x 1 x double> @strided_vpload_nxv1f64(ptr %ptr, i32 signext %stri
declare <vscale x 2 x double> @llvm.experimental.vp.strided.load.nxv2f64.p0.i32(ptr, i32, <vscale x 2 x i1>, i32)
define <vscale x 2 x double> @strided_vpload_nxv2f64(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv2f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m2, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv2f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m2, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv2f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m2, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 2 x double> @llvm.experimental.vp.strided.load.nxv2f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x double> %load
}
@@ -673,33 +465,21 @@ define <vscale x 2 x double> @strided_vpload_nxv2f64(ptr %ptr, i32 signext %stri
declare <vscale x 4 x double> @llvm.experimental.vp.strided.load.nxv4f64.p0.i32(ptr, i32, <vscale x 4 x i1>, i32)
define <vscale x 4 x double> @strided_vpload_nxv4f64(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 4 x double> @llvm.experimental.vp.strided.load.nxv4f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x double> %load
}
define <vscale x 4 x double> @strided_vpload_nxv4f64_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv4f64_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv4f64_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv4f64_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 4 x i1> %a, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
%load = call <vscale x 4 x double> @llvm.experimental.vp.strided.load.nxv4f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 4 x i1> %b, i32 %evl)
@@ -709,50 +489,32 @@ define <vscale x 4 x double> @strided_vpload_nxv4f64_allones_mask(ptr %ptr, i32
declare <vscale x 8 x double> @llvm.experimental.vp.strided.load.nxv8f64.p0.i32(ptr, i32, <vscale x 8 x i1>, i32)
define <vscale x 8 x double> @strided_vpload_nxv8f64(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv8f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv8f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv8f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%load = call <vscale x 8 x double> @llvm.experimental.vp.strided.load.nxv8f64.p0.i32(ptr %ptr, i32 signext %stride, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x double> %load
}
; Widening
define <vscale x 3 x double> @strided_vpload_nxv3f64(ptr %ptr, i32 signext %stride, <vscale x 3 x i1> %mask, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv3f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv3f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv3f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
%v = call <vscale x 3 x double> @llvm.experimental.vp.strided.load.nxv3f64.p0.i32(ptr %ptr, i32 %stride, <vscale x 3 x i1> %mask, i32 %evl)
ret <vscale x 3 x double> %v
}
define <vscale x 3 x double> @strided_vpload_nxv3f64_allones_mask(ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpload_nxv3f64_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV32-NEXT: vlse64.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpload_nxv3f64_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV64-NEXT: vlse64.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpload_nxv3f64_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
+; CHECK-NEXT: vlse64.v v8, (a0), a1
+; CHECK-NEXT: ret
%one = insertelement <vscale x 3 x i1> poison, i1 true, i32 0
%allones = shufflevector <vscale x 3 x i1> %one, <vscale x 3 x i1> poison, <vscale x 3 x i32> zeroinitializer
%v = call <vscale x 3 x double> @llvm.experimental.vp.strided.load.nxv3f64.p0.i32(ptr %ptr, i32 %stride, <vscale x 3 x i1> %allones, i32 %evl)
diff --git a/llvm/test/CodeGen/RISCV/rvv/strided-vpstore.ll b/llvm/test/CodeGen/RISCV/rvv/strided-vpstore.ll
index 8df8a69e8027f6d..b7b9769e82d1b69 100644
--- a/llvm/test/CodeGen/RISCV/rvv/strided-vpstore.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/strided-vpstore.ll
@@ -1,23 +1,19 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+m,+d,+zfh,+v,+zvfh \
-; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK-RV32
+; RUN: -verify-machineinstrs < %s | FileCheck %s \
+; RUN: -check-prefixes=CHECK,CHECK-RV32
; RUN: llc -mtriple=riscv64 -mattr=+m,+d,+zfh,+v,+zvfh \
-; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK-RV64
+; RUN: -verify-machineinstrs < %s | FileCheck %s \
+; RUN: -check-prefixes=CHECK,CHECK-RV64
declare void @llvm.experimental.vp.strided.store.nxv1i8.p0.i8(<vscale x 1 x i8>, ptr, i8, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1i8_i8(<vscale x 1 x i8> %val, ptr %ptr, i8 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1i8_i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV32-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1i8_i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV64-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1i8_i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
+; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1i8.p0.i8(<vscale x 1 x i8> %val, ptr %ptr, i8 %stride, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -25,17 +21,11 @@ define void @strided_vpstore_nxv1i8_i8(<vscale x 1 x i8> %val, ptr %ptr, i8 sign
declare void @llvm.experimental.vp.strided.store.nxv1i8.p0.i16(<vscale x 1 x i8>, ptr, i16, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1i8_i16(<vscale x 1 x i8> %val, ptr %ptr, i16 signext %stride, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1i8_i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV32-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1i8_i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV64-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1i8_i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
+; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1i8.p0.i16(<vscale x 1 x i8> %val, ptr %ptr, i16 %stride, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -61,17 +51,11 @@ define void @strided_vpstore_nxv1i8_i64(<vscale x 1 x i8> %val, ptr %ptr, i64 si
declare void @llvm.experimental.vp.strided.store.nxv1i8.p0.i32(<vscale x 1 x i8>, ptr, i32, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1i8(<vscale x 1 x i8> %val, ptr %ptr, i32 signext %strided, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV32-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV64-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
+; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1i8.p0.i32(<vscale x 1 x i8> %val, ptr %ptr, i32 %strided, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -79,17 +63,11 @@ define void @strided_vpstore_nxv1i8(<vscale x 1 x i8> %val, ptr %ptr, i32 signex
declare void @llvm.experimental.vp.strided.store.nxv2i8.p0.i32(<vscale x 2 x i8>, ptr, i32, <vscale x 2 x i1>, i32)
define void @strided_vpstore_nxv2i8(<vscale x 2 x i8> %val, ptr %ptr, i32 signext %strided, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv2i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf4, ta, ma
-; CHECK-RV32-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv2i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf4, ta, ma
-; CHECK-RV64-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv2i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf4, ta, ma
+; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv2i8.p0.i32(<vscale x 2 x i8> %val, ptr %ptr, i32 %strided, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
@@ -97,17 +75,11 @@ define void @strided_vpstore_nxv2i8(<vscale x 2 x i8> %val, ptr %ptr, i32 signex
declare void @llvm.experimental.vp.strided.store.nxv4i8.p0.i32(<vscale x 4 x i8>, ptr, i32, <vscale x 4 x i1>, i32)
define void @strided_vpstore_nxv4i8(<vscale x 4 x i8> %val, ptr %ptr, i32 signext %strided, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv4i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf2, ta, ma
-; CHECK-RV32-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv4i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf2, ta, ma
-; CHECK-RV64-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv4i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf2, ta, ma
+; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv4i8.p0.i32(<vscale x 4 x i8> %val, ptr %ptr, i32 %strided, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
@@ -115,17 +87,11 @@ define void @strided_vpstore_nxv4i8(<vscale x 4 x i8> %val, ptr %ptr, i32 signex
declare void @llvm.experimental.vp.strided.store.nxv8i8.p0.i32(<vscale x 8 x i8>, ptr, i32, <vscale x 8 x i1>, i32)
define void @strided_vpstore_nxv8i8(<vscale x 8 x i8> %val, ptr %ptr, i32 signext %strided, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv8i8:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, m1, ta, ma
-; CHECK-RV32-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv8i8:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, m1, ta, ma
-; CHECK-RV64-NEXT: vsse8.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv8i8:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, m1, ta, ma
+; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv8i8.p0.i32(<vscale x 8 x i8> %val, ptr %ptr, i32 %strided, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
@@ -133,17 +99,11 @@ define void @strided_vpstore_nxv8i8(<vscale x 8 x i8> %val, ptr %ptr, i32 signex
declare void @llvm.experimental.vp.strided.store.nxv1i16.p0.i32(<vscale x 1 x i16>, ptr, i32, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1i16(<vscale x 1 x i16> %val, ptr %ptr, i32 signext %strided, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
-; CHECK-RV32-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
-; CHECK-RV64-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1i16.p0.i32(<vscale x 1 x i16> %val, ptr %ptr, i32 %strided, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -151,17 +111,11 @@ define void @strided_vpstore_nxv1i16(<vscale x 1 x i16> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv2i16.p0.i32(<vscale x 2 x i16>, ptr, i32, <vscale x 2 x i1>, i32)
define void @strided_vpstore_nxv2i16(<vscale x 2 x i16> %val, ptr %ptr, i32 signext %strided, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv2i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV32-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv2i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV64-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv2i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv2i16.p0.i32(<vscale x 2 x i16> %val, ptr %ptr, i32 %strided, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
@@ -169,17 +123,11 @@ define void @strided_vpstore_nxv2i16(<vscale x 2 x i16> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv4i16.p0.i32(<vscale x 4 x i16>, ptr, i32, <vscale x 4 x i1>, i32)
define void @strided_vpstore_nxv4i16(<vscale x 4 x i16> %val, ptr %ptr, i32 signext %strided, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv4i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, m1, ta, ma
-; CHECK-RV32-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv4i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, m1, ta, ma
-; CHECK-RV64-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv4i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, m1, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv4i16.p0.i32(<vscale x 4 x i16> %val, ptr %ptr, i32 %strided, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
@@ -187,17 +135,11 @@ define void @strided_vpstore_nxv4i16(<vscale x 4 x i16> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv8i16.p0.i32(<vscale x 8 x i16>, ptr, i32, <vscale x 8 x i1>, i32)
define void @strided_vpstore_nxv8i16(<vscale x 8 x i16> %val, ptr %ptr, i32 signext %strided, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv8i16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, m2, ta, ma
-; CHECK-RV32-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv8i16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, m2, ta, ma
-; CHECK-RV64-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv8i16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, m2, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv8i16.p0.i32(<vscale x 8 x i16> %val, ptr %ptr, i32 %strided, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
@@ -205,17 +147,11 @@ define void @strided_vpstore_nxv8i16(<vscale x 8 x i16> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv1i32.p0.i32(<vscale x 1 x i32>, ptr, i32, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1i32(<vscale x 1 x i32> %val, ptr %ptr, i32 signext %strided, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1i32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1i32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1i32.p0.i32(<vscale x 1 x i32> %val, ptr %ptr, i32 %strided, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -223,17 +159,11 @@ define void @strided_vpstore_nxv1i32(<vscale x 1 x i32> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv2i32.p0.i32(<vscale x 2 x i32>, ptr, i32, <vscale x 2 x i1>, i32)
define void @strided_vpstore_nxv2i32(<vscale x 2 x i32> %val, ptr %ptr, i32 signext %strided, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv2i32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m1, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv2i32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m1, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv2i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m1, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv2i32.p0.i32(<vscale x 2 x i32> %val, ptr %ptr, i32 %strided, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
@@ -241,17 +171,11 @@ define void @strided_vpstore_nxv2i32(<vscale x 2 x i32> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv4i32.p0.i32(<vscale x 4 x i32>, ptr, i32, <vscale x 4 x i1>, i32)
define void @strided_vpstore_nxv4i32(<vscale x 4 x i32> %val, ptr %ptr, i32 signext %strided, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv4i32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv4i32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv4i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv4i32.p0.i32(<vscale x 4 x i32> %val, ptr %ptr, i32 %strided, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
@@ -259,17 +183,11 @@ define void @strided_vpstore_nxv4i32(<vscale x 4 x i32> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv8i32.p0.i32(<vscale x 8 x i32>, ptr, i32, <vscale x 8 x i1>, i32)
define void @strided_vpstore_nxv8i32(<vscale x 8 x i32> %val, ptr %ptr, i32 signext %strided, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv8i32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv8i32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv8i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m4, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv8i32.p0.i32(<vscale x 8 x i32> %val, ptr %ptr, i32 %strided, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
@@ -277,17 +195,11 @@ define void @strided_vpstore_nxv8i32(<vscale x 8 x i32> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv1i64.p0.i32(<vscale x 1 x i64>, ptr, i32, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1i64(<vscale x 1 x i64> %val, ptr %ptr, i32 signext %strided, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1i64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1i64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1i64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m1, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1i64.p0.i32(<vscale x 1 x i64> %val, ptr %ptr, i32 %strided, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -295,17 +207,11 @@ define void @strided_vpstore_nxv1i64(<vscale x 1 x i64> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv2i64.p0.i32(<vscale x 2 x i64>, ptr, i32, <vscale x 2 x i1>, i32)
define void @strided_vpstore_nxv2i64(<vscale x 2 x i64> %val, ptr %ptr, i32 signext %strided, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv2i64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m2, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv2i64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m2, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv2i64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m2, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv2i64.p0.i32(<vscale x 2 x i64> %val, ptr %ptr, i32 %strided, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
@@ -313,17 +219,11 @@ define void @strided_vpstore_nxv2i64(<vscale x 2 x i64> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv4i64.p0.i32(<vscale x 4 x i64>, ptr, i32, <vscale x 4 x i1>, i32)
define void @strided_vpstore_nxv4i64(<vscale x 4 x i64> %val, ptr %ptr, i32 signext %strided, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv4i64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv4i64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv4i64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv4i64.p0.i32(<vscale x 4 x i64> %val, ptr %ptr, i32 %strided, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
@@ -331,17 +231,11 @@ define void @strided_vpstore_nxv4i64(<vscale x 4 x i64> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv8i64.p0.i32(<vscale x 8 x i64>, ptr, i32, <vscale x 8 x i1>, i32)
define void @strided_vpstore_nxv8i64(<vscale x 8 x i64> %val, ptr %ptr, i32 signext %strided, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv8i64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv8i64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv8i64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv8i64.p0.i32(<vscale x 8 x i64> %val, ptr %ptr, i32 %strided, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
@@ -349,17 +243,11 @@ define void @strided_vpstore_nxv8i64(<vscale x 8 x i64> %val, ptr %ptr, i32 sign
declare void @llvm.experimental.vp.strided.store.nxv1f16.p0.i32(<vscale x 1 x half>, ptr, i32, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1f16(<vscale x 1 x half> %val, ptr %ptr, i32 signext %strided, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1f16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
-; CHECK-RV32-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1f16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
-; CHECK-RV64-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1f16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1f16.p0.i32(<vscale x 1 x half> %val, ptr %ptr, i32 %strided, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -367,17 +255,11 @@ define void @strided_vpstore_nxv1f16(<vscale x 1 x half> %val, ptr %ptr, i32 sig
declare void @llvm.experimental.vp.strided.store.nxv2f16.p0.i32(<vscale x 2 x half>, ptr, i32, <vscale x 2 x i1>, i32)
define void @strided_vpstore_nxv2f16(<vscale x 2 x half> %val, ptr %ptr, i32 signext %strided, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv2f16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV32-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv2f16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
-; CHECK-RV64-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv2f16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv2f16.p0.i32(<vscale x 2 x half> %val, ptr %ptr, i32 %strided, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
@@ -385,17 +267,11 @@ define void @strided_vpstore_nxv2f16(<vscale x 2 x half> %val, ptr %ptr, i32 sig
declare void @llvm.experimental.vp.strided.store.nxv4f16.p0.i32(<vscale x 4 x half>, ptr, i32, <vscale x 4 x i1>, i32)
define void @strided_vpstore_nxv4f16(<vscale x 4 x half> %val, ptr %ptr, i32 signext %strided, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv4f16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, m1, ta, ma
-; CHECK-RV32-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv4f16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, m1, ta, ma
-; CHECK-RV64-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv4f16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, m1, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv4f16.p0.i32(<vscale x 4 x half> %val, ptr %ptr, i32 %strided, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
@@ -403,17 +279,11 @@ define void @strided_vpstore_nxv4f16(<vscale x 4 x half> %val, ptr %ptr, i32 sig
declare void @llvm.experimental.vp.strided.store.nxv8f16.p0.i32(<vscale x 8 x half>, ptr, i32, <vscale x 8 x i1>, i32)
define void @strided_vpstore_nxv8f16(<vscale x 8 x half> %val, ptr %ptr, i32 signext %strided, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv8f16:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e16, m2, ta, ma
-; CHECK-RV32-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv8f16:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e16, m2, ta, ma
-; CHECK-RV64-NEXT: vsse16.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv8f16:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e16, m2, ta, ma
+; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv8f16.p0.i32(<vscale x 8 x half> %val, ptr %ptr, i32 %strided, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
@@ -421,17 +291,11 @@ define void @strided_vpstore_nxv8f16(<vscale x 8 x half> %val, ptr %ptr, i32 sig
declare void @llvm.experimental.vp.strided.store.nxv1f32.p0.i32(<vscale x 1 x float>, ptr, i32, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1f32(<vscale x 1 x float> %val, ptr %ptr, i32 signext %strided, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1f32.p0.i32(<vscale x 1 x float> %val, ptr %ptr, i32 %strided, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -439,17 +303,11 @@ define void @strided_vpstore_nxv1f32(<vscale x 1 x float> %val, ptr %ptr, i32 si
declare void @llvm.experimental.vp.strided.store.nxv2f32.p0.i32(<vscale x 2 x float>, ptr, i32, <vscale x 2 x i1>, i32)
define void @strided_vpstore_nxv2f32(<vscale x 2 x float> %val, ptr %ptr, i32 signext %strided, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv2f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m1, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv2f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m1, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv2f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m1, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv2f32.p0.i32(<vscale x 2 x float> %val, ptr %ptr, i32 %strided, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
@@ -457,17 +315,11 @@ define void @strided_vpstore_nxv2f32(<vscale x 2 x float> %val, ptr %ptr, i32 si
declare void @llvm.experimental.vp.strided.store.nxv4f32.p0.i32(<vscale x 4 x float>, ptr, i32, <vscale x 4 x i1>, i32)
define void @strided_vpstore_nxv4f32(<vscale x 4 x float> %val, ptr %ptr, i32 signext %strided, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv4f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv4f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv4f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv4f32.p0.i32(<vscale x 4 x float> %val, ptr %ptr, i32 %strided, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
@@ -475,17 +327,11 @@ define void @strided_vpstore_nxv4f32(<vscale x 4 x float> %val, ptr %ptr, i32 si
declare void @llvm.experimental.vp.strided.store.nxv8f32.p0.i32(<vscale x 8 x float>, ptr, i32, <vscale x 8 x i1>, i32)
define void @strided_vpstore_nxv8f32(<vscale x 8 x float> %val, ptr %ptr, i32 signext %strided, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv8f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv8f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m4, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv8f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m4, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv8f32.p0.i32(<vscale x 8 x float> %val, ptr %ptr, i32 %strided, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
@@ -493,17 +339,11 @@ define void @strided_vpstore_nxv8f32(<vscale x 8 x float> %val, ptr %ptr, i32 si
declare void @llvm.experimental.vp.strided.store.nxv1f64.p0.i32(<vscale x 1 x double>, ptr, i32, <vscale x 1 x i1>, i32)
define void @strided_vpstore_nxv1f64(<vscale x 1 x double> %val, ptr %ptr, i32 signext %strided, <vscale x 1 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m1, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m1, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv1f64.p0.i32(<vscale x 1 x double> %val, ptr %ptr, i32 %strided, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
@@ -511,17 +351,11 @@ define void @strided_vpstore_nxv1f64(<vscale x 1 x double> %val, ptr %ptr, i32 s
declare void @llvm.experimental.vp.strided.store.nxv2f64.p0.i32(<vscale x 2 x double>, ptr, i32, <vscale x 2 x i1>, i32)
define void @strided_vpstore_nxv2f64(<vscale x 2 x double> %val, ptr %ptr, i32 signext %strided, <vscale x 2 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv2f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m2, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv2f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m2, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv2f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m2, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv2f64.p0.i32(<vscale x 2 x double> %val, ptr %ptr, i32 %strided, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
@@ -529,17 +363,11 @@ define void @strided_vpstore_nxv2f64(<vscale x 2 x double> %val, ptr %ptr, i32 s
declare void @llvm.experimental.vp.strided.store.nxv4f64.p0.i32(<vscale x 4 x double>, ptr, i32, <vscale x 4 x i1>, i32)
define void @strided_vpstore_nxv4f64(<vscale x 4 x double> %val, ptr %ptr, i32 signext %strided, <vscale x 4 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv4f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv4f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m4, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv4f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv4f64.p0.i32(<vscale x 4 x double> %val, ptr %ptr, i32 %strided, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
@@ -547,33 +375,21 @@ define void @strided_vpstore_nxv4f64(<vscale x 4 x double> %val, ptr %ptr, i32 s
declare void @llvm.experimental.vp.strided.store.nxv8f64.p0.i32(<vscale x 8 x double>, ptr, i32, <vscale x 8 x i1>, i32)
define void @strided_vpstore_nxv8f64(<vscale x 8 x double> %val, ptr %ptr, i32 signext %strided, <vscale x 8 x i1> %m, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv8f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv8f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv8f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv8f64.p0.i32(<vscale x 8 x double> %val, ptr %ptr, i32 %strided, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @strided_vpstore_nxv1i8_allones_mask(<vscale x 1 x i8> %val, ptr %ptr, i32 signext %strided, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv1i8_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV32-NEXT: vsse8.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv1i8_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
-; CHECK-RV64-NEXT: vsse8.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv1i8_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
+; CHECK-NEXT: vsse8.v v8, (a0), a1
+; CHECK-NEXT: ret
%a = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
%b = shufflevector <vscale x 1 x i1> %a, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
call void @llvm.experimental.vp.strided.store.nxv1i8.p0.i32(<vscale x 1 x i8> %val, ptr %ptr, i32 %strided, <vscale x 1 x i1> %b, i32 %evl)
@@ -582,33 +398,21 @@ define void @strided_vpstore_nxv1i8_allones_mask(<vscale x 1 x i8> %val, ptr %pt
; Widening
define void @strided_vpstore_nxv3f32(<vscale x 3 x float> %v, ptr %ptr, i32 signext %stride, <vscale x 3 x i1> %mask, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv3f32:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv3f32:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv3f32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv3f32.p0.i32(<vscale x 3 x float> %v, ptr %ptr, i32 %stride, <vscale x 3 x i1> %mask, i32 %evl)
ret void
}
define void @strided_vpstore_nxv3f32_allones_mask(<vscale x 3 x float> %v, ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_vpstore_nxv3f32_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV32-NEXT: vsse32.v v8, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_vpstore_nxv3f32_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: vsetvli zero, a2, e32, m2, ta, ma
-; CHECK-RV64-NEXT: vsse32.v v8, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_vpstore_nxv3f32_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
+; CHECK-NEXT: vsse32.v v8, (a0), a1
+; CHECK-NEXT: ret
%one = insertelement <vscale x 3 x i1> poison, i1 true, i32 0
%allones = shufflevector <vscale x 3 x i1> %one, <vscale x 3 x i1> poison, <vscale x 3 x i32> zeroinitializer
call void @llvm.experimental.vp.strided.store.nxv3f32.p0.i32(<vscale x 3 x float> %v, ptr %ptr, i32 %stride, <vscale x 3 x i1> %allones, i32 %evl)
@@ -619,95 +423,52 @@ declare void @llvm.experimental.vp.strided.store.nxv3f32.p0.i32(<vscale x 3 x fl
; Splitting
define void @strided_store_nxv16f64(<vscale x 16 x double> %v, ptr %ptr, i32 signext %stride, <vscale x 16 x i1> %mask, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_store_nxv16f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: csrr a3, vlenb
-; CHECK-RV32-NEXT: mv a4, a2
-; CHECK-RV32-NEXT: bltu a2, a3, .LBB34_2
-; CHECK-RV32-NEXT: # %bb.1:
-; CHECK-RV32-NEXT: mv a4, a3
-; CHECK-RV32-NEXT: .LBB34_2:
-; CHECK-RV32-NEXT: vsetvli zero, a4, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV32-NEXT: sub a5, a2, a3
-; CHECK-RV32-NEXT: sltu a2, a2, a5
-; CHECK-RV32-NEXT: addi a2, a2, -1
-; CHECK-RV32-NEXT: and a2, a2, a5
-; CHECK-RV32-NEXT: mul a4, a4, a1
-; CHECK-RV32-NEXT: add a0, a0, a4
-; CHECK-RV32-NEXT: srli a3, a3, 3
-; CHECK-RV32-NEXT: vsetvli a4, zero, e8, mf4, ta, ma
-; CHECK-RV32-NEXT: vslidedown.vx v0, v0, a3
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v16, (a0), a1, v0.t
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_store_nxv16f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: csrr a3, vlenb
-; CHECK-RV64-NEXT: mv a4, a2
-; CHECK-RV64-NEXT: bltu a2, a3, .LBB34_2
-; CHECK-RV64-NEXT: # %bb.1:
-; CHECK-RV64-NEXT: mv a4, a3
-; CHECK-RV64-NEXT: .LBB34_2:
-; CHECK-RV64-NEXT: vsetvli zero, a4, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1, v0.t
-; CHECK-RV64-NEXT: sub a5, a2, a3
-; CHECK-RV64-NEXT: sltu a2, a2, a5
-; CHECK-RV64-NEXT: addi a2, a2, -1
-; CHECK-RV64-NEXT: and a2, a2, a5
-; CHECK-RV64-NEXT: mul a4, a4, a1
-; CHECK-RV64-NEXT: add a0, a0, a4
-; CHECK-RV64-NEXT: srli a3, a3, 3
-; CHECK-RV64-NEXT: vsetvli a4, zero, e8, mf4, ta, ma
-; CHECK-RV64-NEXT: vslidedown.vx v0, v0, a3
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v16, (a0), a1, v0.t
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_store_nxv16f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: mv a4, a2
+; CHECK-NEXT: bltu a2, a3, .LBB34_2
+; CHECK-NEXT: # %bb.1:
+; CHECK-NEXT: mv a4, a3
+; CHECK-NEXT: .LBB34_2:
+; CHECK-NEXT: vsetvli zero, a4, e64, m8, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
+; CHECK-NEXT: sub a5, a2, a3
+; CHECK-NEXT: sltu a2, a2, a5
+; CHECK-NEXT: addi a2, a2, -1
+; CHECK-NEXT: and a2, a2, a5
+; CHECK-NEXT: mul a4, a4, a1
+; CHECK-NEXT: add a0, a0, a4
+; CHECK-NEXT: srli a3, a3, 3
+; CHECK-NEXT: vsetvli a4, zero, e8, mf4, ta, ma
+; CHECK-NEXT: vslidedown.vx v0, v0, a3
+; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT: vsse64.v v16, (a0), a1, v0.t
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv16f64.p0.i32(<vscale x 16 x double> %v, ptr %ptr, i32 %stride, <vscale x 16 x i1> %mask, i32 %evl)
ret void
}
define void @strided_store_nxv16f64_allones_mask(<vscale x 16 x double> %v, ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_store_nxv16f64_allones_mask:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: csrr a3, vlenb
-; CHECK-RV32-NEXT: mv a4, a2
-; CHECK-RV32-NEXT: bltu a2, a3, .LBB35_2
-; CHECK-RV32-NEXT: # %bb.1:
-; CHECK-RV32-NEXT: mv a4, a3
-; CHECK-RV32-NEXT: .LBB35_2:
-; CHECK-RV32-NEXT: vsetvli zero, a4, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v8, (a0), a1
-; CHECK-RV32-NEXT: sub a3, a2, a3
-; CHECK-RV32-NEXT: sltu a2, a2, a3
-; CHECK-RV32-NEXT: addi a2, a2, -1
-; CHECK-RV32-NEXT: and a2, a2, a3
-; CHECK-RV32-NEXT: mul a3, a4, a1
-; CHECK-RV32-NEXT: add a0, a0, a3
-; CHECK-RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vsse64.v v16, (a0), a1
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_store_nxv16f64_allones_mask:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: csrr a3, vlenb
-; CHECK-RV64-NEXT: mv a4, a2
-; CHECK-RV64-NEXT: bltu a2, a3, .LBB35_2
-; CHECK-RV64-NEXT: # %bb.1:
-; CHECK-RV64-NEXT: mv a4, a3
-; CHECK-RV64-NEXT: .LBB35_2:
-; CHECK-RV64-NEXT: vsetvli zero, a4, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v8, (a0), a1
-; CHECK-RV64-NEXT: sub a3, a2, a3
-; CHECK-RV64-NEXT: sltu a2, a2, a3
-; CHECK-RV64-NEXT: addi a2, a2, -1
-; CHECK-RV64-NEXT: and a2, a2, a3
-; CHECK-RV64-NEXT: mul a3, a4, a1
-; CHECK-RV64-NEXT: add a0, a0, a3
-; CHECK-RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vsse64.v v16, (a0), a1
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_store_nxv16f64_allones_mask:
+; CHECK: # %bb.0:
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: mv a4, a2
+; CHECK-NEXT: bltu a2, a3, .LBB35_2
+; CHECK-NEXT: # %bb.1:
+; CHECK-NEXT: mv a4, a3
+; CHECK-NEXT: .LBB35_2:
+; CHECK-NEXT: vsetvli zero, a4, e64, m8, ta, ma
+; CHECK-NEXT: vsse64.v v8, (a0), a1
+; CHECK-NEXT: sub a3, a2, a3
+; CHECK-NEXT: sltu a2, a2, a3
+; CHECK-NEXT: addi a2, a2, -1
+; CHECK-NEXT: and a2, a2, a3
+; CHECK-NEXT: mul a3, a4, a1
+; CHECK-NEXT: add a0, a0, a3
+; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
+; CHECK-NEXT: vsse64.v v16, (a0), a1
+; CHECK-NEXT: ret
%one = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
%allones = shufflevector <vscale x 16 x i1> %one, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
call void @llvm.experimental.vp.strided.store.nxv16f64.p0.i32(<vscale x 16 x double> %v, ptr %ptr, i32 %stride, <vscale x 16 x i1> %allones, i32 %evl)
@@ -718,127 +479,66 @@ declare void @llvm.experimental.vp.strided.store.nxv16f64.p0.i32(<vscale x 16 x
; Widening + splitting (with HiIsEmpty == true)
define void @strided_store_nxv17f64(<vscale x 17 x double> %v, ptr %ptr, i32 signext %stride, <vscale x 17 x i1> %mask, i32 zeroext %evl) {
-; CHECK-RV32-LABEL: strided_store_nxv17f64:
-; CHECK-RV32: # %bb.0:
-; CHECK-RV32-NEXT: csrr a4, vlenb
-; CHECK-RV32-NEXT: slli a6, a4, 1
-; CHECK-RV32-NEXT: vmv1r.v v24, v0
-; CHECK-RV32-NEXT: mv a5, a3
-; CHECK-RV32-NEXT: bltu a3, a6, .LBB36_2
-; CHECK-RV32-NEXT: # %bb.1:
-; CHECK-RV32-NEXT: mv a5, a6
-; CHECK-RV32-NEXT: .LBB36_2:
-; CHECK-RV32-NEXT: mv a7, a5
-; CHECK-RV32-NEXT: bltu a5, a4, .LBB36_4
-; CHECK-RV32-NEXT: # %bb.3:
-; CHECK-RV32-NEXT: mv a7, a4
-; CHECK-RV32-NEXT: .LBB36_4:
-; CHECK-RV32-NEXT: addi sp, sp, -16
-; CHECK-RV32-NEXT: .cfi_def_cfa_offset 16
-; CHECK-RV32-NEXT: csrr t0, vlenb
-; CHECK-RV32-NEXT: slli t0, t0, 3
-; CHECK-RV32-NEXT: sub sp, sp, t0
-; CHECK-RV32-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
-; CHECK-RV32-NEXT: vl8re64.v v0, (a0)
-; CHECK-RV32-NEXT: addi a0, sp, 16
-; CHECK-RV32-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
-; CHECK-RV32-NEXT: vsetvli zero, a7, e64, m8, ta, ma
-; CHECK-RV32-NEXT: vmv1r.v v0, v24
-; CHECK-RV32-NEXT: vsse64.v v8, (a1), a2, v0.t
-; CHECK-RV32-NEXT: sub a0, a5, a4
-; CHECK-RV32-NEXT: sltu t0, a5, a0
-; CHECK-RV32-NEXT: addi t0, t0, -1
-; CHECK-RV32-NEXT: and a0, t0, a0
-; CHECK-RV32-NEXT: mul a7, a7, a2
-; CHECK-RV32-NEXT: add a7, a1, a7
-; CHECK-RV32-NEXT: srli t0, a4, 3
-; CHECK-RV32-NEXT: vsetvli t1, zero, e8, mf4, ta, ma
-; CHECK-RV32-NEXT: vslidedown.vx v0, v24, t0
-; CHECK-RV32-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-RV32-NEXT: sub a0, a3, a6
-; CHECK-RV32-NEXT: sltu a3, a3, a0
-; CHECK-RV32-NEXT: addi a3, a3, -1
-; CHECK-RV32-NEXT: and a0, a3, a0
-; CHECK-RV32-NEXT: vsse64.v v16, (a7), a2, v0.t
-; CHECK-RV32-NEXT: bltu a0, a4, .LBB36_6
-; CHECK-RV32-NEXT: # %bb.5:
-; CHECK-RV32-NEXT: mv a0, a4
-; CHECK-RV32-NEXT: .LBB36_6:
-; CHECK-RV32-NEXT: mul a3, a5, a2
-; CHECK-RV32-NEXT: add a1, a1, a3
-; CHECK-RV32-NEXT: srli a4, a4, 2
-; CHECK-RV32-NEXT: vsetvli a3, zero, e8, mf2, ta, ma
-; CHECK-RV32-NEXT: vslidedown.vx v0, v24, a4
-; CHECK-RV32-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-RV32-NEXT: addi a0, sp, 16
-; CHECK-RV32-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-RV32-NEXT: vsse64.v v8, (a1), a2, v0.t
-; CHECK-RV32-NEXT: csrr a0, vlenb
-; CHECK-RV32-NEXT: slli a0, a0, 3
-; CHECK-RV32-NEXT: add sp, sp, a0
-; CHECK-RV32-NEXT: addi sp, sp, 16
-; CHECK-RV32-NEXT: ret
-;
-; CHECK-RV64-LABEL: strided_store_nxv17f64:
-; CHECK-RV64: # %bb.0:
-; CHECK-RV64-NEXT: csrr a4, vlenb
-; CHECK-RV64-NEXT: slli a6, a4, 1
-; CHECK-RV64-NEXT: vmv1r.v v24, v0
-; CHECK-RV64-NEXT: mv a5, a3
-; CHECK-RV64-NEXT: bltu a3, a6, .LBB36_2
-; CHECK-RV64-NEXT: # %bb.1:
-; CHECK-RV64-NEXT: mv a5, a6
-; CHECK-RV64-NEXT: .LBB36_2:
-; CHECK-RV64-NEXT: mv a7, a5
-; CHECK-RV64-NEXT: bltu a5, a4, .LBB36_4
-; CHECK-RV64-NEXT: # %bb.3:
-; CHECK-RV64-NEXT: mv a7, a4
-; CHECK-RV64-NEXT: .LBB36_4:
-; CHECK-RV64-NEXT: addi sp, sp, -16
-; CHECK-RV64-NEXT: .cfi_def_cfa_offset 16
-; CHECK-RV64-NEXT: csrr t0, vlenb
-; CHECK-RV64-NEXT: slli t0, t0, 3
-; CHECK-RV64-NEXT: sub sp, sp, t0
-; CHECK-RV64-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
-; CHECK-RV64-NEXT: vl8re64.v v0, (a0)
-; CHECK-RV64-NEXT: addi a0, sp, 16
-; CHECK-RV64-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
-; CHECK-RV64-NEXT: vsetvli zero, a7, e64, m8, ta, ma
-; CHECK-RV64-NEXT: vmv1r.v v0, v24
-; CHECK-RV64-NEXT: vsse64.v v8, (a1), a2, v0.t
-; CHECK-RV64-NEXT: sub a0, a5, a4
-; CHECK-RV64-NEXT: sltu t0, a5, a0
-; CHECK-RV64-NEXT: addi t0, t0, -1
-; CHECK-RV64-NEXT: and a0, t0, a0
-; CHECK-RV64-NEXT: mul a7, a7, a2
-; CHECK-RV64-NEXT: add a7, a1, a7
-; CHECK-RV64-NEXT: srli t0, a4, 3
-; CHECK-RV64-NEXT: vsetvli t1, zero, e8, mf4, ta, ma
-; CHECK-RV64-NEXT: vslidedown.vx v0, v24, t0
-; CHECK-RV64-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-RV64-NEXT: sub a0, a3, a6
-; CHECK-RV64-NEXT: sltu a3, a3, a0
-; CHECK-RV64-NEXT: addi a3, a3, -1
-; CHECK-RV64-NEXT: and a0, a3, a0
-; CHECK-RV64-NEXT: vsse64.v v16, (a7), a2, v0.t
-; CHECK-RV64-NEXT: bltu a0, a4, .LBB36_6
-; CHECK-RV64-NEXT: # %bb.5:
-; CHECK-RV64-NEXT: mv a0, a4
-; CHECK-RV64-NEXT: .LBB36_6:
-; CHECK-RV64-NEXT: mul a3, a5, a2
-; CHECK-RV64-NEXT: add a1, a1, a3
-; CHECK-RV64-NEXT: srli a4, a4, 2
-; CHECK-RV64-NEXT: vsetvli a3, zero, e8, mf2, ta, ma
-; CHECK-RV64-NEXT: vslidedown.vx v0, v24, a4
-; CHECK-RV64-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-RV64-NEXT: addi a0, sp, 16
-; CHECK-RV64-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-RV64-NEXT: vsse64.v v8, (a1), a2, v0.t
-; CHECK-RV64-NEXT: csrr a0, vlenb
-; CHECK-RV64-NEXT: slli a0, a0, 3
-; CHECK-RV64-NEXT: add sp, sp, a0
-; CHECK-RV64-NEXT: addi sp, sp, 16
-; CHECK-RV64-NEXT: ret
+; CHECK-LABEL: strided_store_nxv17f64:
+; CHECK: # %bb.0:
+; CHECK-NEXT: csrr a4, vlenb
+; CHECK-NEXT: slli a6, a4, 1
+; CHECK-NEXT: vmv1r.v v24, v0
+; CHECK-NEXT: mv a5, a3
+; CHECK-NEXT: bltu a3, a6, .LBB36_2
+; CHECK-NEXT: # %bb.1:
+; CHECK-NEXT: mv a5, a6
+; CHECK-NEXT: .LBB36_2:
+; CHECK-NEXT: mv a7, a5
+; CHECK-NEXT: bltu a5, a4, .LBB36_4
+; CHECK-NEXT: # %bb.3:
+; CHECK-NEXT: mv a7, a4
+; CHECK-NEXT: .LBB36_4:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: .cfi_def_cfa_offset 16
+; CHECK-NEXT: csrr t0, vlenb
+; CHECK-NEXT: slli t0, t0, 3
+; CHECK-NEXT: sub sp, sp, t0
+; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; CHECK-NEXT: vl8re64.v v0, (a0)
+; CHECK-NEXT: addi a0, sp, 16
+; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vsetvli zero, a7, e64, m8, ta, ma
+; CHECK-NEXT: vmv1r.v v0, v24
+; CHECK-NEXT: vsse64.v v8, (a1), a2, v0.t
+; CHECK-NEXT: sub a0, a5, a4
+; CHECK-NEXT: sltu t0, a5, a0
+; CHECK-NEXT: addi t0, t0, -1
+; CHECK-NEXT: and a0, t0, a0
+; CHECK-NEXT: mul a7, a7, a2
+; CHECK-NEXT: add a7, a1, a7
+; CHECK-NEXT: srli t0, a4, 3
+; CHECK-NEXT: vsetvli t1, zero, e8, mf4, ta, ma
+; CHECK-NEXT: vslidedown.vx v0, v24, t0
+; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT: sub a0, a3, a6
+; CHECK-NEXT: sltu a3, a3, a0
+; CHECK-NEXT: addi a3, a3, -1
+; CHECK-NEXT: and a0, a3, a0
+; CHECK-NEXT: vsse64.v v16, (a7), a2, v0.t
+; CHECK-NEXT: bltu a0, a4, .LBB36_6
+; CHECK-NEXT: # %bb.5:
+; CHECK-NEXT: mv a0, a4
+; CHECK-NEXT: .LBB36_6:
+; CHECK-NEXT: mul a3, a5, a2
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: srli a4, a4, 2
+; CHECK-NEXT: vsetvli a3, zero, e8, mf2, ta, ma
+; CHECK-NEXT: vslidedown.vx v0, v24, a4
+; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT: addi a0, sp, 16
+; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vsse64.v v8, (a1), a2, v0.t
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
call void @llvm.experimental.vp.strided.store.nxv17f64.p0.i32(<vscale x 17 x double> %v, ptr %ptr, i32 %stride, <vscale x 17 x i1> %mask, i32 %evl)
ret void
}
More information about the llvm-commits
mailing list