[llvm] [AArch64][GlobalISel] Legalization for small anyext/sext/zext (PR #86438)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Mar 24 07:33:09 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
Author: David Green (davemgreen)
<details>
<summary>Changes</summary>
Similar to #<!-- -->85625, some of the codegen is still far from optimal but this helps fix quite a few fallback cases.
---
Patch is 69.34 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/86438.diff
16 Files Affected:
- (modified) llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp (+15-7)
- (modified) llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp (+3-2)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/legalize-build-vector.mir (+15-12)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/legalize-insert-vector-elt.mir (+15-14)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir (+30-27)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/legalize-shuffle-vector-widen-crash.ll (+11-3)
- (modified) llvm/test/CodeGen/AArch64/GlobalISel/legalize-xtn.mir (+7-11)
- (modified) llvm/test/CodeGen/AArch64/aarch64-smull.ll (+44-9)
- (modified) llvm/test/CodeGen/AArch64/arm64-extract-insert-varidx.ll (+16-18)
- (modified) llvm/test/CodeGen/AArch64/bitcast.ll (+98-47)
- (modified) llvm/test/CodeGen/AArch64/bswap.ll (+18-8)
- (modified) llvm/test/CodeGen/AArch64/fptoi.ll (+30-15)
- (modified) llvm/test/CodeGen/AArch64/itofp.ll (+198-80)
- (modified) llvm/test/CodeGen/AArch64/load.ll (+2-1)
- (modified) llvm/test/CodeGen/AArch64/neon-bitwise-instructions.ll (+38-8)
- (modified) llvm/test/CodeGen/AArch64/shift.ll (+174-51)
``````````diff
diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index 1b25da8833e4fb..c3a23ea0ad3738 100644
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -5421,14 +5421,22 @@ LegalizerHelper::moreElementsVector(MachineInstr &MI, unsigned TypeIdx,
case TargetOpcode::G_FPTOUI:
case TargetOpcode::G_SITOFP:
case TargetOpcode::G_UITOFP: {
- if (TypeIdx != 0)
- return UnableToLegalize;
Observer.changingInstr(MI);
- LLT SrcTy = LLT::fixed_vector(
- MoreTy.getNumElements(),
- MRI.getType(MI.getOperand(1).getReg()).getElementType());
- moreElementsVectorSrc(MI, SrcTy, 1);
- moreElementsVectorDst(MI, MoreTy, 0);
+ LLT SrcExtTy;
+ LLT DstExtTy;
+ if (TypeIdx == 0) {
+ DstExtTy = MoreTy;
+ SrcExtTy = LLT::fixed_vector(
+ MoreTy.getNumElements(),
+ MRI.getType(MI.getOperand(1).getReg()).getElementType());
+ } else {
+ DstExtTy = LLT::fixed_vector(
+ MoreTy.getNumElements(),
+ MRI.getType(MI.getOperand(0).getReg()).getElementType());
+ SrcExtTy = MoreTy;
+ }
+ moreElementsVectorSrc(MI, SrcExtTy, 1);
+ moreElementsVectorDst(MI, DstExtTy, 0);
Observer.changedInstr(MI);
return Legalized;
}
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
index 34e2c1d9c8e2f9..33dba6a5c61eaf 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
@@ -611,7 +611,9 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
Query.Types[0].isVector() &&
(Query.Types[1].getScalarSizeInBits() == 8 ||
Query.Types[1].getScalarSizeInBits() == 16);
- });
+ })
+ .clampMinNumElements(1, s8, 8)
+ .clampMinNumElements(1, s16, 4);
getActionDefinitionsBuilder(G_TRUNC)
.legalFor({{v2s32, v2s64}, {v4s16, v4s32}, {v8s8, v8s16}})
@@ -630,7 +632,6 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
})
.clampMinNumElements(0, s8, 8)
.clampMinNumElements(0, s16, 4)
- .clampMinNumElements(0, s32, 2)
.alwaysLegal();
getActionDefinitionsBuilder(G_SEXT_INREG)
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-build-vector.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-build-vector.mir
index c9556e27c6349a..a63d8b9c137725 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-build-vector.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-build-vector.mir
@@ -121,10 +121,11 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY $h0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY $h1
- ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[COPY]](s16)
- ; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[COPY1]](s16)
- ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[ANYEXT]](s32), [[ANYEXT1]](s32)
- ; CHECK-NEXT: $d0 = COPY [[BUILD_VECTOR]](<2 x s32>)
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[COPY]](s16), [[COPY1]](s16), [[DEF]](s16), [[DEF]](s16)
+ ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<4 x s32>) = G_ANYEXT [[BUILD_VECTOR]](<4 x s16>)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(<2 x s32>), [[UV1:%[0-9]+]]:_(<2 x s32>) = G_UNMERGE_VALUES [[ANYEXT]](<4 x s32>)
+ ; CHECK-NEXT: $d0 = COPY [[UV]](<2 x s32>)
; CHECK-NEXT: RET_ReallyLR
%0:_(s16) = COPY $h0
%1:_(s16) = COPY $h1
@@ -141,8 +142,8 @@ body: |
; CHECK-LABEL: name: widen_v2s8
; CHECK: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY [[DEF]](s32)
- ; CHECK-NEXT: %3:_(<2 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[DEF]](s32)
- ; CHECK-NEXT: $d0 = COPY %3(<2 x s32>)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[DEF]](s32)
+ ; CHECK-NEXT: $d0 = COPY [[BUILD_VECTOR]](<2 x s32>)
; CHECK-NEXT: RET_ReallyLR
%0:_(s8) = G_IMPLICIT_DEF
%1:_(s8) = G_IMPLICIT_DEF
@@ -157,12 +158,14 @@ name: widen_v4s8
body: |
bb.0:
; CHECK-LABEL: name: widen_v4s8
- ; CHECK: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
- ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY [[DEF]](s16)
- ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY [[DEF]](s16)
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY [[DEF]](s16)
- ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[COPY]](s16), [[COPY1]](s16), [[COPY2]](s16), [[DEF]](s16)
- ; CHECK-NEXT: $d0 = COPY [[BUILD_VECTOR]](<4 x s16>)
+ ; CHECK: [[DEF:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[DEF1:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[DEF2:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[DEF3:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[DEF]](s8), [[DEF1]](s8), [[DEF2]](s8), [[DEF3]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF]](s8)
+ ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<8 x s16>) = G_ANYEXT [[BUILD_VECTOR]](<8 x s8>)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(<4 x s16>), [[UV1:%[0-9]+]]:_(<4 x s16>) = G_UNMERGE_VALUES [[ANYEXT]](<8 x s16>)
+ ; CHECK-NEXT: $d0 = COPY [[UV]](<4 x s16>)
; CHECK-NEXT: RET_ReallyLR
%0:_(s8) = G_IMPLICIT_DEF
%1:_(s8) = G_IMPLICIT_DEF
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-insert-vector-elt.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-insert-vector-elt.mir
index e12353c7ef5bec..d3db2432e84cbc 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-insert-vector-elt.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-insert-vector-elt.mir
@@ -235,31 +235,32 @@ body: |
; CHECK-NEXT: successors: %bb.1(0x80000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
+ ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
+ ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY2]](s32)
+ ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[COPY3]](s32)
; CHECK-NEXT: [[DEF1:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
- ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
- ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s32)
- ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY3]](s32)
- ; CHECK-NEXT: [[DEF2:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
- ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16), [[TRUNC2]](s16), [[DEF2]](s16)
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[TRUNC]](s8), [[TRUNC1]](s8), [[TRUNC2]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
+ ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<8 x s16>) = G_ANYEXT [[BUILD_VECTOR]](<8 x s8>)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(<4 x s16>), [[UV1:%[0-9]+]]:_(<4 x s16>) = G_UNMERGE_VALUES [[ANYEXT]](<8 x s16>)
; CHECK-NEXT: [[C2:%[0-9]+]]:_(s16) = G_CONSTANT i16 0
- ; CHECK-NEXT: [[IVEC:%[0-9]+]]:_(<4 x s16>) = G_INSERT_VECTOR_ELT [[BUILD_VECTOR]], [[C2]](s16), [[C1]](s64)
- ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[IVEC]](<4 x s16>)
- ; CHECK-NEXT: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[UV]](s16)
- ; CHECK-NEXT: [[TRUNC4:%[0-9]+]]:_(s8) = G_TRUNC [[UV1]](s16)
- ; CHECK-NEXT: [[TRUNC5:%[0-9]+]]:_(s8) = G_TRUNC [[UV2]](s16)
+ ; CHECK-NEXT: [[IVEC:%[0-9]+]]:_(<4 x s16>) = G_INSERT_VECTOR_ELT [[UV]], [[C2]](s16), [[C1]](s64)
+ ; CHECK-NEXT: [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16), [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[IVEC]](<4 x s16>)
+ ; CHECK-NEXT: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[UV2]](s16)
+ ; CHECK-NEXT: [[TRUNC4:%[0-9]+]]:_(s8) = G_TRUNC [[UV3]](s16)
+ ; CHECK-NEXT: [[TRUNC5:%[0-9]+]]:_(s8) = G_TRUNC [[UV4]](s16)
; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<16 x s8>) = G_BUILD_VECTOR [[TRUNC3]](s8), [[TRUNC4]](s8), [[TRUNC5]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
; CHECK-NEXT: [[BUILD_VECTOR2:%[0-9]+]]:_(<16 x s8>) = G_BUILD_VECTOR [[C]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<16 x s8>) = G_SHUFFLE_VECTOR [[BUILD_VECTOR1]](<16 x s8>), [[BUILD_VECTOR2]], shufflemask(0, 16, 16, 16, 1, 16, 16, 16, 2, 16, 16, 16, undef, undef, undef, undef)
; CHECK-NEXT: [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[SHUF]](<16 x s8>)
; CHECK-NEXT: [[UITOFP:%[0-9]+]]:_(<4 x s32>) = G_UITOFP [[BITCAST]](<4 x s32>)
- ; CHECK-NEXT: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UITOFP]](<4 x s32>)
- ; CHECK-NEXT: G_STORE [[UV4]](s32), [[COPY]](p0) :: (store (s32), align 16)
+ ; CHECK-NEXT: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UITOFP]](<4 x s32>)
+ ; CHECK-NEXT: G_STORE [[UV6]](s32), [[COPY]](p0) :: (store (s32), align 16)
; CHECK-NEXT: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
; CHECK-NEXT: [[PTR_ADD:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C3]](s64)
- ; CHECK-NEXT: G_STORE [[UV5]](s32), [[PTR_ADD]](p0) :: (store (s32) into unknown-address + 4)
+ ; CHECK-NEXT: G_STORE [[UV7]](s32), [[PTR_ADD]](p0) :: (store (s32) into unknown-address + 4)
; CHECK-NEXT: [[C4:%[0-9]+]]:_(s64) = G_CONSTANT i64 8
; CHECK-NEXT: [[PTR_ADD1:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C4]](s64)
- ; CHECK-NEXT: G_STORE [[UV6]](s32), [[PTR_ADD1]](p0) :: (store (s32) into unknown-address + 8, align 8)
+ ; CHECK-NEXT: G_STORE [[UV8]](s32), [[PTR_ADD1]](p0) :: (store (s32) into unknown-address + 8, align 8)
; CHECK-NEXT: G_BR %bb.1
bb.1:
liveins: $w1, $w2, $w3, $x0
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir
index 63a26dcfea4762..e49a94c12ed468 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir
@@ -293,41 +293,44 @@ body: |
; CHECK-NEXT: [[ICMP2:%[0-9]+]]:_(s32) = G_ICMP intpred(eq), %w0(s32), [[C]]
; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ICMP2]], 1
; CHECK-NEXT: [[DEF:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
- ; CHECK-NEXT: [[DEF1:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
- ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY [[DEF1]](s16)
- ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY [[DEF1]](s16)
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY [[DEF1]](s16)
- ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[COPY]](s16), [[COPY1]](s16), [[COPY2]](s16), [[DEF1]](s16)
; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
+ ; CHECK-NEXT: [[DEF1:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
+ ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<8 x s16>) = G_ANYEXT [[BUILD_VECTOR]](<8 x s8>)
+ ; CHECK-NEXT: [[UV:%[0-9]+]]:_(<4 x s16>), [[UV1:%[0-9]+]]:_(<4 x s16>) = G_UNMERGE_VALUES [[ANYEXT]](<8 x s16>)
; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[SEXT_INREG]](s32)
- ; CHECK-NEXT: [[IVEC:%[0-9]+]]:_(<4 x s16>) = G_INSERT_VECTOR_ELT [[BUILD_VECTOR]], [[TRUNC]](s16), [[C1]](s64)
- ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[IVEC]](<4 x s16>)
- ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[UV]](s16)
- ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[UV1]](s16)
- ; CHECK-NEXT: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[UV2]](s16)
- ; CHECK-NEXT: [[TRUNC4:%[0-9]+]]:_(s8) = G_TRUNC [[UV3]](s16)
- ; CHECK-NEXT: [[DEF2:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
- ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[TRUNC1]](s8), [[TRUNC2]](s8), [[TRUNC3]](s8), [[TRUNC4]](s8), [[DEF2]](s8), [[DEF2]](s8), [[DEF2]](s8), [[DEF2]](s8)
- ; CHECK-NEXT: [[BUILD_VECTOR2:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF2]](s8), [[DEF2]](s8), [[DEF2]](s8), [[DEF2]](s8)
+ ; CHECK-NEXT: [[IVEC:%[0-9]+]]:_(<4 x s16>) = G_INSERT_VECTOR_ELT [[UV]], [[TRUNC]](s16), [[C1]](s64)
+ ; CHECK-NEXT: [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16), [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[IVEC]](<4 x s16>)
+ ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[UV2]](s16)
+ ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[UV3]](s16)
+ ; CHECK-NEXT: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[UV4]](s16)
+ ; CHECK-NEXT: [[TRUNC4:%[0-9]+]]:_(s8) = G_TRUNC [[UV5]](s16)
+ ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[TRUNC1]](s8), [[TRUNC2]](s8), [[TRUNC3]](s8), [[TRUNC4]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
+ ; CHECK-NEXT: [[BUILD_VECTOR2:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<8 x s8>) = G_SHUFFLE_VECTOR [[BUILD_VECTOR1]](<8 x s8>), [[BUILD_VECTOR2]], shufflemask(0, 0, 0, 0, undef, undef, undef, undef)
- ; CHECK-NEXT: [[UV4:%[0-9]+]]:_(<4 x s8>), [[UV5:%[0-9]+]]:_(<4 x s8>) = G_UNMERGE_VALUES [[SHUF]](<8 x s8>)
- ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s16) = G_CONSTANT i16 1
- ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s16) = COPY [[C2]](s16)
- ; CHECK-NEXT: [[COPY4:%[0-9]+]]:_(s16) = COPY [[C2]](s16)
- ; CHECK-NEXT: [[COPY5:%[0-9]+]]:_(s16) = COPY [[C2]](s16)
- ; CHECK-NEXT: [[BUILD_VECTOR3:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[COPY3]](s16), [[COPY4]](s16), [[COPY5]](s16), [[C2]](s16)
- ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[UV4]](<4 x s8>)
- ; CHECK-NEXT: [[XOR:%[0-9]+]]:_(<4 x s16>) = G_XOR [[ANYEXT]], [[BUILD_VECTOR3]]
+ ; CHECK-NEXT: [[UV6:%[0-9]+]]:_(<4 x s8>), [[UV7:%[0-9]+]]:_(<4 x s8>) = G_UNMERGE_VALUES [[SHUF]](<8 x s8>)
+ ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s8) = G_CONSTANT i8 1
+ ; CHECK-NEXT: [[UV8:%[0-9]+]]:_(s8), [[UV9:%[0-9]+]]:_(s8), [[UV10:%[0-9]+]]:_(s8), [[UV11:%[0-9]+]]:_(s8) = G_UNMERGE_VALUES [[UV6]](<4 x s8>)
+ ; CHECK-NEXT: [[BUILD_VECTOR3:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[UV8]](s8), [[UV9]](s8), [[UV10]](s8), [[UV11]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
+ ; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(<8 x s16>) = G_ANYEXT [[BUILD_VECTOR3]](<8 x s8>)
+ ; CHECK-NEXT: [[UV12:%[0-9]+]]:_(<4 x s16>), [[UV13:%[0-9]+]]:_(<4 x s16>) = G_UNMERGE_VALUES [[ANYEXT1]](<8 x s16>)
+ ; CHECK-NEXT: [[BUILD_VECTOR4:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[C2]](s8), [[C2]](s8), [[C2]](s8), [[C2]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
+ ; CHECK-NEXT: [[ANYEXT2:%[0-9]+]]:_(<8 x s16>) = G_ANYEXT [[BUILD_VECTOR4]](<8 x s8>)
+ ; CHECK-NEXT: [[UV14:%[0-9]+]]:_(<4 x s16>), [[UV15:%[0-9]+]]:_(<4 x s16>) = G_UNMERGE_VALUES [[ANYEXT2]](<8 x s16>)
+ ; CHECK-NEXT: [[XOR:%[0-9]+]]:_(<4 x s16>) = G_XOR [[UV12]], [[UV14]]
; CHECK-NEXT: [[TRUNC5:%[0-9]+]]:_(<4 x s16>) = G_TRUNC [[ICMP]](<4 x s32>)
- ; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[UV4]](<4 x s8>)
- ; CHECK-NEXT: [[AND:%[0-9]+]]:_(<4 x s16>) = G_AND [[TRUNC5]], [[ANYEXT1]]
+ ; CHECK-NEXT: [[UV16:%[0-9]+]]:_(s8), [[UV17:%[0-9]+]]:_(s8), [[UV18:%[0-9]+]]:_(s8), [[UV19:%[0-9]+]]:_(s8) = G_UNMERGE_VALUES [[UV6]](<4 x s8>)
+ ; CHECK-NEXT: [[BUILD_VECTOR5:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[UV16]](s8), [[UV17]](s8), [[UV18]](s8), [[UV19]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8), [[DEF1]](s8)
+ ; CHECK-NEXT: [[ANYEXT3:%[0-9]+]]:_(<8 x s16>) = G_ANYEXT [[BUILD_VECTOR5]](<8 x s8>)
+ ; CHECK-NEXT: [[UV20:%[0-9]+]]:_(<4 x s16>), [[UV21:%[0-9]+]]:_(<4 x s16>) = G_UNMERGE_VALUES [[ANYEXT3]](<8 x s16>)
+ ; CHECK-NEXT: [[AND:%[0-9]+]]:_(<4 x s16>) = G_AND [[TRUNC5]], [[UV20]]
; CHECK-NEXT: [[TRUNC6:%[0-9]+]]:_(<4 x s16>) = G_TRUNC [[ICMP1]](<4 x s32>)
; CHECK-NEXT: [[AND1:%[0-9]+]]:_(<4 x s16>) = G_AND [[TRUNC6]], [[XOR]]
; CHECK-NEXT: [[OR:%[0-9]+]]:_(<4 x s16>) = G_OR [[AND]], [[AND1]]
- ; CHECK-NEXT: [[ANYEXT2:%[0-9]+]]:_(<4 x s32>) = G_ANYEXT [[OR]](<4 x s16>)
+ ; CHECK-NEXT: [[ANYEXT4:%[0-9]+]]:_(<4 x s32>) = G_ANYEXT [[OR]](<4 x s16>)
; CHECK-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
- ; CHECK-NEXT: [[BUILD_VECTOR4:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[C3]](s32), [[C3]](s32), [[C3]](s32), [[C3]](s32)
- ; CHECK-NEXT: %zext_select:_(<4 x s32>) = G_AND [[ANYEXT2]], [[BUILD_VECTOR4]]
+ ; CHECK-NEXT: [[BUILD_VECTOR6:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[C3]](s32), [[C3]](s32), [[C3]](s32), [[C3]](s32)
+ ; CHECK-NEXT: %zext_select:_(<4 x s32>) = G_AND [[ANYEXT4]], [[BUILD_VECTOR6]]
; CHECK-NEXT: $q0 = COPY %zext_select(<4 x s32>)
; CHECK-NEXT: RET_ReallyLR implicit $q0
%w0:_(s32) = COPY $w0
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-shuffle-vector-widen-crash.ll b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-shuffle-vector-widen-crash.ll
index 42a8f51002f200..f7efaeaa507053 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-shuffle-vector-widen-crash.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-shuffle-vector-widen-crash.ll
@@ -1,16 +1,24 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
-; RUN: llc -global-isel-abort=2 -global-isel -o - %s | FileCheck %s
+; RUN: llc -global-isel -o - %s | FileCheck %s
target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
target triple = "arm64-apple-macosx11.0.0"
declare i32 @llvm.aarch64.neon.uaddv.i32.v4i32(<4 x i32>) #0
-; This test currently falls back but ensures we don't crash.
-
define i32 @bar() {
; CHECK-LABEL: bar:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: movi.2d v0, #0000000000000000
+; CHECK-NEXT: mov b1, v0[1]
+; CHECK-NEXT: mov b2, v0[2]
+; CHECK-NEXT: mov b3, v0[3]
+; CHECK-NEXT: mov.h v0[1], v1[0]
+; CHECK-NEXT: mov.h v2[1], v3[0]
+; CHECK-NEXT: ushll.4s v0, v0, #0
+; CHECK-NEXT: ushll.4s v1, v2, #0
+; CHECK-NEXT: mov.d v0[1], v1[0]
+; CHECK-NEXT: movi.4s v1, #1
+; CHECK-NEXT: and.16b v0, v0, v1
; CHECK-NEXT: addv.4s s0, v0
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-xtn.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-xtn.mir
index ed40a2ff7ea70f..e729f027baa715 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-xtn.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-xtn.mir
@@ -541,17 +541,13 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $d0
; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
- ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
- ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[UV]](s32), [[UV1]](s32), [[DEF]](s32), [[DEF]](s32)
- ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[DEF]](s32), [[DEF]](s32), [[DEF]](s32), [[DEF]](s32)
- ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(<4 x s16>) = G_TRUNC [[BUILD_VECTOR]](<4 x s32>)
- ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(<4 x s16>) = G_TRUNC [[BUILD_VECTOR1]](<4 x s32>)
- ; CHECK-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s16>) = G_CONCAT_VECTORS [[TRUNC]](<4 x s16>), [[TRUNC1]](<4 x s16>)
- ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(<8 x s8>) = G_TRUNC [[CONCAT_VECTORS]](<8 x s16>)
- ; CHECK-NEXT: [[UV2:%[0-9]+]]:_(<2 x s8>), [[UV3:%[0-9]+]]:_(<2 x s8>), [[UV4:%[0-9]+]]:_(<2 x s8>), [[UV5:%[0-9]+]]:_(<2 x s8>) = G_UNMERGE_VALUES [[TRUNC2]](<8 x s8>)
- ; CHECK-NEXT: [[CONCAT_VECTORS1:%[0-9]+]]:_(<4 ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/86438
More information about the llvm-commits
mailing list