[llvm] [X86] X86FixupVectorConstantsPass - use VPMOVSX/ZX extensions for PS/PD domain moves (PR #122601)
via llvm-commits
llvm-commits at lists.llvm.org
Sat Jan 11 08:45:10 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
Author: Simon Pilgrim (RKSimon)
<details>
<summary>Changes</summary>
For targets with free domain moves, or AVX512 support, allow the use of VPMOVSX/ZX extension loads to reduce the load sizes.
I've limited this to extension to i32/i64 types as we're mostly interested in shuffle mask loading here, but we could include i16 types as well just as easily.
Inspired by a regression on #<!-- -->122485
---
Patch is 393.79 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/122601.diff
56 Files Affected:
- (modified) llvm/lib/Target/X86/X86FixupVectorConstants.cpp (+90-29)
- (modified) llvm/test/CodeGen/X86/avx512-build-vector.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/avx512-mask-op.ll (+2-2)
- (modified) llvm/test/CodeGen/X86/avx512-shuffles/partial_permute.ll (+105-110)
- (modified) llvm/test/CodeGen/X86/avx512-shuffles/permute.ll (+72-72)
- (modified) llvm/test/CodeGen/X86/avx512vl-intrinsics.ll (+6-6)
- (modified) llvm/test/CodeGen/X86/combine-or.ll (+10-5)
- (modified) llvm/test/CodeGen/X86/combine-sub-usat.ll (+28-8)
- (modified) llvm/test/CodeGen/X86/expand-vp-cast-intrinsics.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/extract-concat.ll (+2-2)
- (modified) llvm/test/CodeGen/X86/insert-into-constant-vector.ll (+2-2)
- (modified) llvm/test/CodeGen/X86/isel-buildvector-avx.ll (+9-4)
- (modified) llvm/test/CodeGen/X86/matrix-multiply.ll (+4-4)
- (modified) llvm/test/CodeGen/X86/nontemporal-4.ll (+16-16)
- (modified) llvm/test/CodeGen/X86/pr29112.ll (+10-10)
- (modified) llvm/test/CodeGen/X86/pr46532.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/pr78109.ll (+2-6)
- (modified) llvm/test/CodeGen/X86/pr97968.ll (+1-2)
- (modified) llvm/test/CodeGen/X86/sse41-intrinsics-x86.ll (+6-6)
- (modified) llvm/test/CodeGen/X86/vec_fp_to_int.ll (+126-56)
- (modified) llvm/test/CodeGen/X86/vec_minmax_sint.ll (+224-64)
- (modified) llvm/test/CodeGen/X86/vec_minmax_uint.ll (+224-64)
- (modified) llvm/test/CodeGen/X86/vector-compress.ll (+14-4)
- (modified) llvm/test/CodeGen/X86/vector-half-conversions.ll (+2-2)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-load-i32-stride-6.ll (+16-16)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-load-i64-stride-3.ll (+4-4)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-load-i64-stride-4.ll (+4-4)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-2.ll (+16-16)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-3.ll (+16-16)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-4.ll (+12-12)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-5.ll (+8-8)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-6.ll (+8-8)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-2.ll (+8-8)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-3.ll (+8-8)
- (modified) llvm/test/CodeGen/X86/vector-lzcnt-128.ll (+60-20)
- (modified) llvm/test/CodeGen/X86/vector-lzcnt-256.ll (+96-16)
- (modified) llvm/test/CodeGen/X86/vector-popcnt-128.ll (+32-12)
- (modified) llvm/test/CodeGen/X86/vector-popcnt-256.ll (+68-8)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll (+2-2)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll (+10-10)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll (+340-172)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-512-v16.ll (+12-12)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-512-v64.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-512-v8.ll (+324-708)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-avx512.ll (+13-14)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll (+13-14)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll (+32-15)
- (modified) llvm/test/CodeGen/X86/vector-shuffle-combining-avx512f.ll (+40-66)
- (modified) llvm/test/CodeGen/X86/vector-tzcnt-128.ll (+92-32)
- (modified) llvm/test/CodeGen/X86/vector-tzcnt-256.ll (+152-20)
- (modified) llvm/test/CodeGen/X86/vselect-avx.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/widen_fadd.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/widen_fdiv.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/widen_fmul.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/widen_fsub.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/x86-interleaved-access.ll (+2-2)
``````````diff
diff --git a/llvm/lib/Target/X86/X86FixupVectorConstants.cpp b/llvm/lib/Target/X86/X86FixupVectorConstants.cpp
index 68a4a0be3a1db7..7390cc58054528 100644
--- a/llvm/lib/Target/X86/X86FixupVectorConstants.cpp
+++ b/llvm/lib/Target/X86/X86FixupVectorConstants.cpp
@@ -338,6 +338,7 @@ bool X86FixupVectorConstantsPass::processInstruction(MachineFunction &MF,
bool HasDQI = ST->hasDQI();
bool HasBWI = ST->hasBWI();
bool HasVLX = ST->hasVLX();
+ bool MultiDomain = ST->hasAVX512() || ST->hasNoDomainDelayMov();
struct FixupEntry {
int Op;
@@ -401,47 +402,107 @@ bool X86FixupVectorConstantsPass::processInstruction(MachineFunction &MF,
case X86::VMOVAPDrm:
case X86::VMOVAPSrm:
case X86::VMOVUPDrm:
- case X86::VMOVUPSrm:
- return FixupConstant({{X86::VMOVSSrm, 1, 32, rebuildZeroUpperCst},
- {X86::VBROADCASTSSrm, 1, 32, rebuildSplatCst},
- {X86::VMOVSDrm, 1, 64, rebuildZeroUpperCst},
- {X86::VMOVDDUPrm, 1, 64, rebuildSplatCst}},
- 128, 1);
+ case X86::VMOVUPSrm: {
+ FixupEntry Fixups[] = {
+ {MultiDomain ? X86::VPMOVSXBQrm : 0, 2, 8, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXBQrm : 0, 2, 8, rebuildZExtCst},
+ {X86::VMOVSSrm, 1, 32, rebuildZeroUpperCst},
+ {X86::VBROADCASTSSrm, 1, 32, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXBDrm : 0, 4, 8, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXBDrm : 0, 4, 8, rebuildZExtCst},
+ {MultiDomain ? X86::VPMOVSXWQrm : 0, 2, 16, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXWQrm : 0, 2, 16, rebuildZExtCst},
+ {X86::VMOVSDrm, 1, 64, rebuildZeroUpperCst},
+ {X86::VMOVDDUPrm, 1, 64, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXWDrm : 0, 4, 16, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXWDrm : 0, 4, 16, rebuildZExtCst},
+ {MultiDomain ? X86::VPMOVSXDQrm : 0, 2, 32, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXDQrm : 0, 2, 32, rebuildZExtCst}};
+ return FixupConstant(Fixups, 128, 1);
+ }
case X86::VMOVAPDYrm:
case X86::VMOVAPSYrm:
case X86::VMOVUPDYrm:
- case X86::VMOVUPSYrm:
- return FixupConstant({{X86::VBROADCASTSSYrm, 1, 32, rebuildSplatCst},
- {X86::VBROADCASTSDYrm, 1, 64, rebuildSplatCst},
- {X86::VBROADCASTF128rm, 1, 128, rebuildSplatCst}},
- 256, 1);
+ case X86::VMOVUPSYrm: {
+ FixupEntry Fixups[] = {
+ {X86::VBROADCASTSSYrm, 1, 32, rebuildSplatCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVSXBQYrm : 0, 4, 8, rebuildSExtCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVZXBQYrm : 0, 4, 8, rebuildZExtCst},
+ {X86::VBROADCASTSDYrm, 1, 64, rebuildSplatCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVSXBDYrm : 0, 8, 8, rebuildSExtCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVZXBDYrm : 0, 8, 8, rebuildZExtCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVSXWQYrm : 0, 4, 16, rebuildSExtCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVZXWQYrm : 0, 4, 16, rebuildZExtCst},
+ {X86::VBROADCASTF128rm, 1, 128, rebuildSplatCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVSXWDYrm : 0, 8, 16, rebuildSExtCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVZXWDYrm : 0, 8, 16, rebuildZExtCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVSXDQYrm : 0, 4, 32, rebuildSExtCst},
+ {HasAVX2 && MultiDomain ? X86::VPMOVZXDQYrm : 0, 4, 32,
+ rebuildZExtCst}};
+ return FixupConstant(Fixups, 256, 1);
+ }
case X86::VMOVAPDZ128rm:
case X86::VMOVAPSZ128rm:
case X86::VMOVUPDZ128rm:
- case X86::VMOVUPSZ128rm:
- return FixupConstant({{X86::VMOVSSZrm, 1, 32, rebuildZeroUpperCst},
- {X86::VBROADCASTSSZ128rm, 1, 32, rebuildSplatCst},
- {X86::VMOVSDZrm, 1, 64, rebuildZeroUpperCst},
- {X86::VMOVDDUPZ128rm, 1, 64, rebuildSplatCst}},
- 128, 1);
+ case X86::VMOVUPSZ128rm: {
+ FixupEntry Fixups[] = {
+ {MultiDomain ? X86::VPMOVSXBQZ128rm : 0, 2, 8, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXBQZ128rm : 0, 2, 8, rebuildZExtCst},
+ {X86::VMOVSSZrm, 1, 32, rebuildZeroUpperCst},
+ {X86::VBROADCASTSSZ128rm, 1, 32, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXBDZ128rm : 0, 4, 8, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXBDZ128rm : 0, 4, 8, rebuildZExtCst},
+ {MultiDomain ? X86::VPMOVSXWQZ128rm : 0, 2, 16, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXWQZ128rm : 0, 2, 16, rebuildZExtCst},
+ {X86::VMOVSDZrm, 1, 64, rebuildZeroUpperCst},
+ {X86::VMOVDDUPZ128rm, 1, 64, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXWDZ128rm : 0, 4, 16, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXWDZ128rm : 0, 4, 16, rebuildZExtCst},
+ {MultiDomain ? X86::VPMOVSXDQZ128rm : 0, 2, 32, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXDQZ128rm : 0, 2, 32, rebuildZExtCst}};
+ return FixupConstant(Fixups, 128, 1);
+ }
case X86::VMOVAPDZ256rm:
case X86::VMOVAPSZ256rm:
case X86::VMOVUPDZ256rm:
- case X86::VMOVUPSZ256rm:
- return FixupConstant(
- {{X86::VBROADCASTSSZ256rm, 1, 32, rebuildSplatCst},
- {X86::VBROADCASTSDZ256rm, 1, 64, rebuildSplatCst},
- {X86::VBROADCASTF32X4Z256rm, 1, 128, rebuildSplatCst}},
- 256, 1);
+ case X86::VMOVUPSZ256rm: {
+ FixupEntry Fixups[] = {
+ {X86::VBROADCASTSSZ256rm, 1, 32, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXBQZ256rm : 0, 4, 8, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXBQZ256rm : 0, 4, 8, rebuildZExtCst},
+ {X86::VBROADCASTSDZ256rm, 1, 64, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXBDZ256rm : 0, 8, 8, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXBDZ256rm : 0, 8, 8, rebuildZExtCst},
+ {MultiDomain ? X86::VPMOVSXWQZ256rm : 0, 4, 16, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXWQZ256rm : 0, 4, 16, rebuildZExtCst},
+ {X86::VBROADCASTF32X4Z256rm, 1, 128, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXWDZ256rm : 0, 8, 16, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXWDZ256rm : 0, 8, 16, rebuildZExtCst},
+ {MultiDomain ? X86::VPMOVSXDQZ256rm : 0, 4, 32, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXDQZ256rm : 0, 4, 32, rebuildZExtCst}};
+ return FixupConstant(Fixups, 256, 1);
+ }
case X86::VMOVAPDZrm:
case X86::VMOVAPSZrm:
case X86::VMOVUPDZrm:
- case X86::VMOVUPSZrm:
- return FixupConstant({{X86::VBROADCASTSSZrm, 1, 32, rebuildSplatCst},
- {X86::VBROADCASTSDZrm, 1, 64, rebuildSplatCst},
- {X86::VBROADCASTF32X4Zrm, 1, 128, rebuildSplatCst},
- {X86::VBROADCASTF64X4Zrm, 1, 256, rebuildSplatCst}},
- 512, 1);
+ case X86::VMOVUPSZrm: {
+ FixupEntry Fixups[] = {
+ {X86::VBROADCASTSSZrm, 1, 32, rebuildSplatCst},
+ {X86::VBROADCASTSDZrm, 1, 64, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXBQZrm : 0, 8, 8, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXBQZrm : 0, 8, 8, rebuildZExtCst},
+ {X86::VBROADCASTF32X4Zrm, 1, 128, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXBDZrm : 0, 16, 8, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXBDZrm : 0, 16, 8, rebuildZExtCst},
+ {MultiDomain ? X86::VPMOVSXWQZrm : 0, 8, 16, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXWQZrm : 0, 8, 16, rebuildZExtCst},
+ {X86::VBROADCASTF64X4Zrm, 1, 256, rebuildSplatCst},
+ {MultiDomain ? X86::VPMOVSXWDZrm : 0, 16, 16, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXWDZrm : 0, 16, 16, rebuildZExtCst},
+ {MultiDomain ? X86::VPMOVSXDQZrm : 0, 8, 32, rebuildSExtCst},
+ {MultiDomain ? X86::VPMOVZXDQZrm : 0, 8, 32, rebuildZExtCst}};
+ return FixupConstant(Fixups, 512, 1);
+ }
/* Integer Loads */
case X86::MOVDQArm:
case X86::MOVDQUrm: {
diff --git a/llvm/test/CodeGen/X86/avx512-build-vector.ll b/llvm/test/CodeGen/X86/avx512-build-vector.ll
index 55478a2e93154b..b21a0c4e36c2bd 100644
--- a/llvm/test/CodeGen/X86/avx512-build-vector.ll
+++ b/llvm/test/CodeGen/X86/avx512-build-vector.ll
@@ -15,7 +15,7 @@ define <16 x float> @test3(<4 x float> %a) {
; CHECK-LABEL: test3:
; CHECK: ## %bb.0:
; CHECK-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
-; CHECK-NEXT: vmovaps {{.*#+}} zmm2 = [0,1,2,3,4,18,16,7,8,9,10,11,12,13,14,15]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} zmm2 = [0,1,2,3,4,18,16,7,8,9,10,11,12,13,14,15]
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpermt2ps %zmm0, %zmm2, %zmm1
; CHECK-NEXT: vmovaps %zmm1, %zmm0
diff --git a/llvm/test/CodeGen/X86/avx512-mask-op.ll b/llvm/test/CodeGen/X86/avx512-mask-op.ll
index 8d98290ba29a6a..8aa898f3ec5765 100644
--- a/llvm/test/CodeGen/X86/avx512-mask-op.ll
+++ b/llvm/test/CodeGen/X86/avx512-mask-op.ll
@@ -1060,12 +1060,12 @@ define i32 @test13_crash(i32 %x, i32 %y) {
define <4 x i1> @test14() {
; CHECK-LABEL: test14:
; CHECK: ## %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} xmm0 = [1,1,0,1]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm0 = [1,1,0,1]
; CHECK-NEXT: retq
;
; X86-LABEL: test14:
; X86: ## %bb.0:
-; X86-NEXT: vmovaps {{.*#+}} xmm0 = [1,1,0,1]
+; X86-NEXT: vpmovsxbd {{.*#+}} xmm0 = [1,1,0,1]
; X86-NEXT: retl
%a = bitcast i16 21845 to <16 x i1>
%b = extractelement <16 x i1> %a, i32 2
diff --git a/llvm/test/CodeGen/X86/avx512-shuffles/partial_permute.ll b/llvm/test/CodeGen/X86/avx512-shuffles/partial_permute.ll
index 5078130f180779..5d901a8a380a9c 100644
--- a/llvm/test/CodeGen/X86/avx512-shuffles/partial_permute.ll
+++ b/llvm/test/CodeGen/X86/avx512-shuffles/partial_permute.ll
@@ -903,7 +903,7 @@ define <8 x i16> @test_16xi16_to_8xi16_E84C94EF(<16 x i16> %vec) {
define <4 x i32> @test_8xi32_to_4xi32_perm_mask0(<8 x i32> %vec) {
; CHECK-LABEL: test_8xi32_to_4xi32_perm_mask0:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} xmm1 = [4,0,3,2]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm1 = [4,0,3,2]
; CHECK-NEXT: vpermps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; CHECK-NEXT: vzeroupper
@@ -1001,7 +1001,7 @@ define <4 x i32> @test_masked_z_8xi32_to_4xi32_perm_mask2(<8 x i32> %vec, <4 x i
define <4 x i32> @test_8xi32_to_4xi32_perm_mask3(<8 x i32> %vec) {
; CHECK-LABEL: test_8xi32_to_4xi32_perm_mask3:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} xmm1 = [5,3,2,5]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm1 = [5,3,2,5]
; CHECK-NEXT: vpermps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; CHECK-NEXT: vzeroupper
@@ -1189,7 +1189,7 @@ define <4 x i32> @test_masked_z_8xi32_to_4xi32_perm_mem_mask3(ptr %vp, <4 x i32>
define <8 x i32> @test_16xi32_to_8xi32_perm_mask0(<16 x i32> %vec) {
; CHECK-LABEL: test_16xi32_to_8xi32_perm_mask0:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} ymm1 = [1,13,11,14,7,10,1,6]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} ymm1 = [1,13,11,14,7,10,1,6]
; CHECK-NEXT: vpermps %zmm0, %zmm1, %zmm0
; CHECK-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0
; CHECK-NEXT: retq
@@ -1283,7 +1283,7 @@ define <8 x i32> @test_masked_z_16xi32_to_8xi32_perm_mask2(<16 x i32> %vec, <8 x
define <8 x i32> @test_16xi32_to_8xi32_perm_mask3(<16 x i32> %vec) {
; CHECK-LABEL: test_16xi32_to_8xi32_perm_mask3:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} ymm1 = [14,5,7,7,10,3,9,3]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} ymm1 = [14,5,7,7,10,3,9,3]
; CHECK-NEXT: vpermps %zmm0, %zmm1, %zmm0
; CHECK-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0
; CHECK-NEXT: retq
@@ -1321,7 +1321,7 @@ define <8 x i32> @test_masked_z_16xi32_to_8xi32_perm_mask3(<16 x i32> %vec, <8 x
define <4 x i32> @test_16xi32_to_4xi32_perm_mask0(<16 x i32> %vec) {
; CHECK-LABEL: test_16xi32_to_4xi32_perm_mask0:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} ymm1 = [0,2,4,12,4,6,4,12]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} ymm1 = [0,2,4,12,4,6,4,12]
; CHECK-NEXT: vpermps %zmm0, %zmm1, %zmm0
; CHECK-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; CHECK-NEXT: vzeroupper
@@ -1424,7 +1424,7 @@ define <4 x i32> @test_masked_z_16xi32_to_4xi32_perm_mask2(<16 x i32> %vec, <4 x
define <4 x i32> @test_16xi32_to_4xi32_perm_mask3(<16 x i32> %vec) {
; CHECK-LABEL: test_16xi32_to_4xi32_perm_mask3:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} xmm1 = [3,0,0,13]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm1 = [3,0,0,13]
; CHECK-NEXT: vpermps %zmm0, %zmm1, %zmm0
; CHECK-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; CHECK-NEXT: vzeroupper
@@ -1465,7 +1465,7 @@ define <4 x i32> @test_masked_z_16xi32_to_4xi32_perm_mask3(<16 x i32> %vec, <4 x
define <8 x i32> @test_16xi32_to_8xi32_perm_mem_mask0(ptr %vp) {
; CHECK-LABEL: test_16xi32_to_8xi32_perm_mem_mask0:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} ymm0 = [7,0,6,0,1,2,4,4]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} ymm0 = [7,0,6,0,1,2,4,4]
; CHECK-NEXT: vpermps 32(%rdi), %ymm0, %ymm0
; CHECK-NEXT: retq
%vec = load <16 x i32>, ptr %vp
@@ -1768,7 +1768,7 @@ define <4 x i32> @test_masked_z_16xi32_to_4xi32_perm_mem_mask3(ptr %vp, <4 x i32
define <4 x i32> @test_16xi32_to_4xi32_perm_mask9(<16 x i32> %vec) {
; CHECK-FAST-LABEL: test_16xi32_to_4xi32_perm_mask9:
; CHECK-FAST: # %bb.0:
-; CHECK-FAST-NEXT: vmovaps {{.*#+}} xmm1 = [12,9,4,10]
+; CHECK-FAST-NEXT: vpmovsxbd {{.*#+}} xmm1 = [12,9,4,10]
; CHECK-FAST-NEXT: vpermps %zmm0, %zmm1, %zmm0
; CHECK-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; CHECK-FAST-NEXT: vzeroupper
@@ -2050,7 +2050,7 @@ define <4 x i64> @test_masked_z_8xi64_to_4xi64_perm_mask2(<8 x i64> %vec, <4 x i
define <4 x i64> @test_8xi64_to_4xi64_perm_mask3(<8 x i64> %vec) {
; CHECK-FAST-LABEL: test_8xi64_to_4xi64_perm_mask3:
; CHECK-FAST: # %bb.0:
-; CHECK-FAST-NEXT: vmovaps {{.*#+}} ymm1 = [6,0,0,7]
+; CHECK-FAST-NEXT: vpmovsxbq {{.*#+}} ymm1 = [6,0,0,7]
; CHECK-FAST-NEXT: vpermpd %zmm0, %zmm1, %zmm0
; CHECK-FAST-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0
; CHECK-FAST-NEXT: retq
@@ -2185,7 +2185,7 @@ define <4 x i64> @test_masked_z_8xi64_to_4xi64_perm_mask5(<8 x i64> %vec, <4 x i
define <4 x i64> @test_8xi64_to_4xi64_perm_mask6(<8 x i64> %vec) {
; CHECK-FAST-LABEL: test_8xi64_to_4xi64_perm_mask6:
; CHECK-FAST: # %bb.0:
-; CHECK-FAST-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,3]
+; CHECK-FAST-NEXT: vpmovsxbq {{.*#+}} ymm1 = [7,6,5,3]
; CHECK-FAST-NEXT: vpermpd %zmm0, %zmm1, %zmm0
; CHECK-FAST-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0
; CHECK-FAST-NEXT: retq
@@ -2711,7 +2711,7 @@ define <4 x i64> @test_masked_z_8xi64_to_4xi64_perm_mem_mask7(ptr %vp, <4 x i64>
define <2 x i64> @test_8xi64_to_2xi64_perm_mem_mask0(ptr %vp) {
; CHECK-FAST-LABEL: test_8xi64_to_2xi64_perm_mem_mask0:
; CHECK-FAST: # %bb.0:
-; CHECK-FAST-NEXT: vmovaps {{.*#+}} xmm0 = [4,1]
+; CHECK-FAST-NEXT: vpmovsxbq {{.*#+}} xmm0 = [4,1]
; CHECK-FAST-NEXT: vpermpd (%rdi), %zmm0, %zmm0
; CHECK-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; CHECK-FAST-NEXT: vzeroupper
@@ -2847,7 +2847,7 @@ define <4 x float> @test_masked_8xfloat_to_4xfloat_perm_mask1(<8 x float> %vec,
; CHECK-LABEL: test_masked_8xfloat_to_4xfloat_perm_mask1:
; CHECK: # %bb.0:
; CHECK-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
-; CHECK-NEXT: vmovaps {{.*#+}} xmm3 = [1,3,5,0]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm3 = [1,3,5,0]
; CHECK-NEXT: vxorps %xmm4, %xmm4, %xmm4
; CHECK-NEXT: vcmpeqps %xmm4, %xmm2, %k1
; CHECK-NEXT: vpermps %ymm0, %ymm3, %ymm1 {%k1}
@@ -2863,7 +2863,7 @@ define <4 x float> @test_masked_8xfloat_to_4xfloat_perm_mask1(<8 x float> %vec,
define <4 x float> @test_masked_z_8xfloat_to_4xfloat_perm_mask1(<8 x float> %vec, <4 x float> %mask) {
; CHECK-LABEL: test_masked_z_8xfloat_to_4xfloat_perm_mask1:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} xmm2 = [1,3,5,0]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm2 = [1,3,5,0]
; CHECK-NEXT: vxorps %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vcmpeqps %xmm3, %xmm1, %k1
; CHECK-NEXT: vpermps %ymm0, %ymm2, %ymm0 {%k1} {z}
@@ -2879,7 +2879,7 @@ define <4 x float> @test_masked_8xfloat_to_4xfloat_perm_mask2(<8 x float> %vec,
; CHECK-LABEL: test_masked_8xfloat_to_4xfloat_perm_mask2:
; CHECK: # %bb.0:
; CHECK-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
-; CHECK-NEXT: vmovaps {{.*#+}} xmm3 = [3,2,7,0]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm3 = [3,2,7,0]
; CHECK-NEXT: vxorps %xmm4, %xmm4, %xmm4
; CHECK-NEXT: vcmpeqps %xmm4, %xmm2, %k1
; CHECK-NEXT: vpermps %ymm0, %ymm3, %ymm1 {%k1}
@@ -2895,7 +2895,7 @@ define <4 x float> @test_masked_8xfloat_to_4xfloat_perm_mask2(<8 x float> %vec,
define <4 x float> @test_masked_z_8xfloat_to_4xfloat_perm_mask2(<8 x float> %vec, <4 x float> %mask) {
; CHECK-LABEL: test_masked_z_8xfloat_to_4xfloat_perm_mask2:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} xmm2 = [3,2,7,0]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm2 = [3,2,7,0]
; CHECK-NEXT: vxorps %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vcmpeqps %xmm3, %xmm1, %k1
; CHECK-NEXT: vpermps %ymm0, %ymm2, %ymm0 {%k1} {z}
@@ -2910,7 +2910,7 @@ define <4 x float> @test_masked_z_8xfloat_to_4xfloat_perm_mask2(<8 x float> %vec
define <4 x float> @test_8xfloat_to_4xfloat_perm_mask3(<8 x float> %vec) {
; CHECK-LABEL: test_8xfloat_to_4xfloat_perm_mask3:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} xmm1 = [3,3,5,2]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm1 = [3,3,5,2]
; CHECK-NEXT: vpermps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; CHECK-NEXT: vzeroupper
@@ -2922,7 +2922,7 @@ define <4 x float> @test_masked_8xfloat_to_4xfloat_perm_mask3(<8 x float> %vec,
; CHECK-LABEL: test_masked_8xfloat_to_4xfloat_perm_mask3:
; CHECK: # %bb.0:
; CHECK-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
-; CHECK-NEXT: vmovaps {{.*#+}} xmm3 = [3,3,5,2]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm3 = [3,3,5,2]
; CHECK-NEXT: vxorps %xmm4, %xmm4, %xmm4
; CHECK-NEXT: vcmpeqps %xmm4, %xmm2, %k1
; CHECK-NEXT: vpermps %ymm0, %ymm3, %ymm1 {%k1}
@@ -2938,7 +2938,7 @@ define <4 x float> @test_masked_8xfloat_to_4xfloat_perm_mask3(<8 x float> %vec,
define <4 x float> @test_masked_z_8xfloat_to_4xfloat_perm_mask3(<8 x float> %vec, <4 x float> %mask) {
; CHECK-LABEL: test_masked_z_8xfloat_to_4xfloat_perm_mask3:
; CHECK: # %bb.0:
-; CHECK-NEXT: vmovaps {{.*#+}} xmm2 = [3,3,5,2]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm2 = [3,3,5,2]
; CHECK-NEXT: vxorps %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vcmpeqps %xmm3, %xmm1, %k1
; CHECK-NEXT: vpermps %ymm0, %ymm2, %ymm0 {%k1} {z}
@@ -2954,7 +2954,7 @@ define <4 x float> @test_8xfloat_to_4xfloat_perm_mem_mask0(ptr %vp) {
; CHECK-LABEL: test_8xfloat_to_4xfloat_perm_mem_mask0:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovaps 16(%rdi), %xmm1
-; CHECK-NEXT: vmovaps {{.*#+}} xmm0 = [2,6,0,1]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm0 = [2,6,0,1]
; CHECK-NEXT: vpermi2ps (%rdi), %xmm1, %xmm0
; CHECK-NEXT: retq
%vec = load <8 x float>, ptr %vp
@@ -2965,7 +2965,7 @@ define <4 x float> @test_masked_8xfloat_to_4xfloat_perm_mem_mask0(ptr %vp, <4 x
; CHECK-LABEL: test_masked_8xfloat_to_4xfloat_perm_mem_mask0:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovaps 16(%rdi), %xmm2
-; CHECK-NEXT: vmovaps {{.*#+}} xmm3 = [2,6,0,1]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm3 = [2,6,0,1]
; CHECK-NEXT: vpermi2ps (%rdi), %xmm2, %xmm3
; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2
; CHECK-NEXT: vcmpeqps %xmm2, %xmm1, %k1
@@ -2982,7 +2982,7 @@ define <4 x float> @test_masked_z_8xfloat_to_4xfloat_perm_mem_mask0(ptr %vp, <4
; CHECK-LABEL: test_masked_z_8xfloat_to_4xfloat_perm_mem_mask0:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovaps 16(%rdi), %xmm2
-; CHECK-NEXT: vmovaps {{.*#+}} xmm1 = [2,6,0,1]
+; CHECK-NEXT: vpmovsxbd {{.*#+}} xmm1 = [2,6,0,1]
; CHECK-NEXT: vxorps %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vcmpeqps %xmm3, %xmm0, %k1
; CHECK-NEXT: vpermi2ps (%rdi), %xmm2, %xmm1 {%k1} {z}
@@ -2999,7 +2999,7 @@ define <4 x float> @test_masked_8xfloat_to_4xfloat_perm_mem_mask1(ptr %vp, <4 x
; CHECK-LABEL: test_masked_8xfloat_to_4xfloat_pe...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/122601
More information about the llvm-commits
mailing list