Skip to content

[SLP] Fix CommonMask will be transformed into an incorrect mask if createShuffle is called multiple times. #124244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jan 28, 2025
Merged

[SLP] Fix CommonMask will be transformed into an incorrect mask if createShuffle is called multiple times. #124244

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
81c2cc1
[SLP][REVEC] Pre-commit test.
HanKuanChen Dec 18, 2024
d2165b5
[SLP][REVEC] Pre-commit test.
HanKuanChen Dec 20, 2024
cad78f0
[SLP] Fix CommonMask will be transformed into an incorrect mask if
HanKuanChen Jan 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 15 additions & 24 deletions llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9374,8 +9374,15 @@ class BaseShuffleAnalysis {
/// instruction.
template <typename T, typename ShuffleBuilderTy>
static T createShuffle(Value *V1, Value *V2, ArrayRef<int> Mask,
ShuffleBuilderTy &Builder) {
ShuffleBuilderTy &Builder, Type *ScalarTy) {
assert(V1 && "Expected at least one vector value.");
unsigned ScalarTyNumElements = getNumElements(ScalarTy);
SmallVector<int> NewMask(Mask);
if (ScalarTyNumElements != 1) {
assert(SLPReVec && "FixedVectorType is not expected.");
transformScalarShuffleIndiciesToVector(ScalarTyNumElements, NewMask);
Mask = NewMask;
}
if (V2)
Builder.resizeToMatch(V1, V2);
int VF = Mask.size();
Expand Down Expand Up @@ -9478,7 +9485,6 @@ class BaseShuffleAnalysis {
if (isa<PoisonValue>(V1))
return Builder.createPoison(
cast<VectorType>(V1->getType())->getElementType(), Mask.size());
SmallVector<int> NewMask(Mask);
bool IsIdentity = peekThroughShuffles(V1, NewMask, /*SinglePermute=*/true);
assert(V1 && "Expected non-null value after looking through shuffles.");

Expand Down Expand Up @@ -10643,17 +10649,12 @@ class BoUpSLP::ShuffleCostEstimator : public BaseShuffleAnalysis {
V2 = getAllOnesValue(*R.DL, getWidenedType(ScalarTy, CommonVF));
}
}
if (auto *VecTy = dyn_cast<FixedVectorType>(ScalarTy)) {
assert(SLPReVec && "FixedVectorType is not expected.");
transformScalarShuffleIndiciesToVector(VecTy->getNumElements(),
CommonMask);
}
InVectors.front() =
Constant::getNullValue(getWidenedType(ScalarTy, CommonMask.size()));
if (InVectors.size() == 2)
InVectors.pop_back();
return ExtraCost + BaseShuffleAnalysis::createShuffle<InstructionCost>(
V1, V2, CommonMask, Builder);
V1, V2, CommonMask, Builder, ScalarTy);
}

public:
Expand Down Expand Up @@ -14198,8 +14199,8 @@ class BoUpSLP::ShuffleInstructionBuilder final : public BaseShuffleAnalysis {
assert(V1 && "Expected at least one vector value.");
ShuffleIRBuilder ShuffleBuilder(Builder, R.GatherShuffleExtractSeq,
R.CSEBlocks, *R.DL);
return BaseShuffleAnalysis::createShuffle<Value *>(V1, V2, Mask,
ShuffleBuilder);
return BaseShuffleAnalysis::createShuffle<Value *>(
V1, V2, Mask, ShuffleBuilder, ScalarTy);
}

/// Cast value \p V to the vector type with the same number of elements, but
Expand Down Expand Up @@ -14518,14 +14519,6 @@ class BoUpSLP::ShuffleInstructionBuilder final : public BaseShuffleAnalysis {
ArrayRef<int> SubVectorsMask, unsigned VF = 0,
function_ref<void(Value *&, SmallVectorImpl<int> &)> Action = {}) {
IsFinalized = true;
unsigned ScalarTyNumElements = getNumElements(ScalarTy);
SmallVector<int> NewExtMask(ExtMask);
if (ScalarTyNumElements != 1) {
assert(SLPReVec && "FixedVectorType is not expected.");
transformScalarShuffleIndiciesToVector(ScalarTyNumElements, CommonMask);
transformScalarShuffleIndiciesToVector(ScalarTyNumElements, NewExtMask);
ExtMask = NewExtMask;
}
if (Action) {
Value *Vec = InVectors.front();
if (InVectors.size() == 2) {
Expand Down Expand Up @@ -14566,17 +14559,15 @@ class BoUpSLP::ShuffleInstructionBuilder final : public BaseShuffleAnalysis {
return !isKnownNonNegative(
V, SimplifyQuery(*R.DL));
}));
unsigned InsertionIndex = Idx * ScalarTyNumElements;
unsigned InsertionIndex = Idx * getNumElements(ScalarTy);
Vec = createInsertVector(
Builder, Vec, V, InsertionIndex,
std::bind(&ShuffleInstructionBuilder::createShuffle, this, _1, _2,
_3));
if (!CommonMask.empty()) {
std::iota(
std::next(CommonMask.begin(), InsertionIndex),
std::next(CommonMask.begin(),
(Idx + E->getVectorFactor()) * ScalarTyNumElements),
InsertionIndex);
std::iota(std::next(CommonMask.begin(), Idx),
std::next(CommonMask.begin(), Idx + E->getVectorFactor()),
Idx);
}
}
return Vec;
Expand Down
37 changes: 37 additions & 0 deletions llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,3 +231,40 @@ define ptr @test4() {
%28 = tail call float @llvm.sqrt.f32(float %26)
ret ptr null
}

define i32 @test5() {
; CHECK-LABEL: @test5(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call <4 x double> @llvm.vector.insert.v4f64.v2f64(<4 x double> poison, <2 x double> zeroinitializer, i64 0)
; CHECK-NEXT: [[TMP1:%.*]] = call <4 x double> @llvm.vector.insert.v4f64.v2f64(<4 x double> [[TMP0]], <2 x double> zeroinitializer, i64 2)
; CHECK-NEXT: [[TMP2:%.*]] = fdiv <4 x double> [[TMP1]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = call <8 x double> @llvm.vector.insert.v8f64.v2f64(<8 x double> poison, <2 x double> zeroinitializer, i64 0)
; CHECK-NEXT: [[TMP4:%.*]] = call <8 x double> @llvm.vector.insert.v8f64.v2f64(<8 x double> [[TMP3]], <2 x double> zeroinitializer, i64 2)
; CHECK-NEXT: [[TMP5:%.*]] = call <8 x double> @llvm.vector.insert.v8f64.v2f64(<8 x double> [[TMP4]], <2 x double> zeroinitializer, i64 4)
; CHECK-NEXT: [[TMP6:%.*]] = call <8 x double> @llvm.vector.insert.v8f64.v2f64(<8 x double> [[TMP5]], <2 x double> zeroinitializer, i64 6)
; CHECK-NEXT: [[TMP7:%.*]] = call <8 x double> @llvm.vector.insert.v8f64.v2f64(<8 x double> poison, <2 x double> zeroinitializer, i64 2)
; CHECK-NEXT: [[TMP8:%.*]] = call <8 x double> @llvm.vector.insert.v8f64.v2f64(<8 x double> [[TMP7]], <2 x double> zeroinitializer, i64 6)
; CHECK-NEXT: [[TMP9:%.*]] = call <8 x double> @llvm.vector.insert.v8f64.v4f64(<8 x double> poison, <4 x double> [[TMP2]], i64 0)
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <8 x double> [[TMP9]], <8 x double> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 10, i32 11, i32 2, i32 3, i32 14, i32 15>
; CHECK-NEXT: [[TMP11:%.*]] = fadd <8 x double> [[TMP6]], [[TMP10]]
; CHECK-NEXT: br label [[FOR_END47:%.*]]
; CHECK: for.end47:
; CHECK-NEXT: [[TMP12:%.*]] = phi <8 x double> [ [[TMP11]], [[ENTRY:%.*]] ]
; CHECK-NEXT: ret i32 0
;
entry:
%div0 = fdiv <2 x double> zeroinitializer, zeroinitializer
%div1 = fdiv <2 x double> zeroinitializer, zeroinitializer
%add0 = fadd <2 x double> zeroinitializer, %div0
%add1 = fadd <2 x double> zeroinitializer, zeroinitializer
%add2 = fadd <2 x double> %div1, zeroinitializer
%add3 = fadd <2 x double> zeroinitializer, zeroinitializer
br label %for.end47

for.end47: ; preds = %entry
%add0.lcssa = phi <2 x double> [ %add0, %entry ]
%add1.lcssa = phi <2 x double> [ %add1, %entry ]
%add2.lcssa = phi <2 x double> [ %add2, %entry ]
%add3.lcssa = phi <2 x double> [ %add3, %entry ]
ret i32 0
}
114 changes: 114 additions & 0 deletions llvm/test/Transforms/SLPVectorizer/revec-shufflevector.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,3 +121,117 @@ entry:
store <4 x i32> %1, ptr %3, align 4
ret void
}

define void @test6(ptr %in0, ptr %in1, ptr %in2) {
; CHECK-LABEL: @test6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds nuw i8, ptr [[IN0:%.*]], i64 32
; CHECK-NEXT: [[LOAD2:%.*]] = load <4 x float>, ptr [[GEP1]], align 16
; CHECK-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[IN0]], align 16
; CHECK-NEXT: [[TMP1:%.*]] = load <32 x i8>, ptr [[IN1:%.*]], align 1
; CHECK-NEXT: [[TMP2:%.*]] = uitofp <32 x i8> [[TMP1]] to <32 x float>
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <8 x float> [[TMP0]], <8 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <4 x float> [[LOAD2]], <4 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <16 x float> [[TMP14]], <16 x float> [[TMP15]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <16 x float> [[TMP16]], <16 x float> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[TMP4:%.*]] = fmul <32 x float> [[TMP3]], [[TMP2]]
; CHECK-NEXT: store <32 x float> [[TMP4]], ptr [[IN2:%.*]], align 16
; CHECK-NEXT: [[GEP10:%.*]] = getelementptr inbounds nuw i8, ptr [[IN1]], i64 32
; CHECK-NEXT: [[LOAD5:%.*]] = load <16 x i8>, ptr [[GEP10]], align 1
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[TMP0]], <8 x float> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[GEP11:%.*]] = getelementptr inbounds nuw i8, ptr [[IN2]], i64 128
; CHECK-NEXT: [[TMP6:%.*]] = uitofp <16 x i8> [[LOAD5]] to <16 x float>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x float> [[LOAD2]], <4 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <8 x float> [[TMP0]], <8 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <16 x float> [[TMP7]], <16 x float> [[TMP8]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <4 x float> [[TMP5]], <4 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <16 x float> [[TMP9]], <16 x float> [[TMP10]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <16 x float> [[TMP11]], <16 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[TMP13:%.*]] = fmul <16 x float> [[TMP12]], [[TMP6]]
; CHECK-NEXT: store <16 x float> [[TMP13]], ptr [[GEP11]], align 16
; CHECK-NEXT: ret void
;
entry:
%gep0 = getelementptr inbounds i8, ptr %in0, i64 16
%gep1 = getelementptr inbounds i8, ptr %in0, i64 32
%load0 = load <4 x float>, ptr %in0, align 16
%load1 = load <4 x float>, ptr %gep0, align 16
%load2 = load <4 x float>, ptr %gep1, align 16
%gep2 = getelementptr inbounds i8, ptr %in1, i64 16
%load3 = load <16 x i8>, ptr %in1, align 1
%load4 = load <16 x i8>, ptr %gep2, align 1
%shufflevector0 = shufflevector <16 x i8> %load3, <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%shufflevector1 = shufflevector <16 x i8> %load3, <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%shufflevector2 = shufflevector <16 x i8> %load4, <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%shufflevector3 = shufflevector <16 x i8> %load4, <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%zext0 = zext <8 x i8> %shufflevector0 to <8 x i16>
%zext1 = zext <8 x i8> %shufflevector1 to <8 x i16>
%zext2 = zext <8 x i8> %shufflevector2 to <8 x i16>
%zext3 = zext <8 x i8> %shufflevector3 to <8 x i16>
%shufflevector4 = shufflevector <8 x i16> %zext0, <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%shufflevector5 = shufflevector <8 x i16> %zext0, <8 x i16> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%shufflevector6 = shufflevector <8 x i16> %zext1, <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%shufflevector7 = shufflevector <8 x i16> %zext1, <8 x i16> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%shufflevector8 = shufflevector <8 x i16> %zext2, <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%shufflevector9 = shufflevector <8 x i16> %zext2, <8 x i16> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%shufflevector10 = shufflevector <8 x i16> %zext3, <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%shufflevector11 = shufflevector <8 x i16> %zext3, <8 x i16> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%uitofp0 = uitofp nneg <4 x i16> %shufflevector4 to <4 x float>
%uitofp1 = uitofp nneg <4 x i16> %shufflevector5 to <4 x float>
%uitofp2 = uitofp nneg <4 x i16> %shufflevector6 to <4 x float>
%uitofp3 = uitofp nneg <4 x i16> %shufflevector7 to <4 x float>
%uitofp4 = uitofp nneg <4 x i16> %shufflevector8 to <4 x float>
%uitofp5 = uitofp nneg <4 x i16> %shufflevector9 to <4 x float>
%uitofp6 = uitofp nneg <4 x i16> %shufflevector10 to <4 x float>
%uitofp7 = uitofp nneg <4 x i16> %shufflevector11 to <4 x float>
%fmul0 = fmul <4 x float> %load0, %uitofp0
%fmul1 = fmul <4 x float> %load1, %uitofp1
%fmul2 = fmul <4 x float> %load2, %uitofp2
%fmul3 = fmul <4 x float> %load0, %uitofp3
%fmul4 = fmul <4 x float> %load1, %uitofp4
%fmul5 = fmul <4 x float> %load2, %uitofp5
%fmul6 = fmul <4 x float> %load0, %uitofp6
%fmul7 = fmul <4 x float> %load1, %uitofp7
%gep3 = getelementptr inbounds i8, ptr %in2, i64 16
%gep4 = getelementptr inbounds i8, ptr %in2, i64 32
%gep5 = getelementptr inbounds i8, ptr %in2, i64 48
%gep6 = getelementptr inbounds i8, ptr %in2, i64 64
%gep7 = getelementptr inbounds i8, ptr %in2, i64 80
%gep8 = getelementptr inbounds i8, ptr %in2, i64 96
%gep9 = getelementptr inbounds i8, ptr %in2, i64 112
store <4 x float> %fmul0, ptr %in2, align 16
store <4 x float> %fmul1, ptr %gep3, align 16
store <4 x float> %fmul2, ptr %gep4, align 16
store <4 x float> %fmul3, ptr %gep5, align 16
store <4 x float> %fmul4, ptr %gep6, align 16
store <4 x float> %fmul5, ptr %gep7, align 16
store <4 x float> %fmul6, ptr %gep8, align 16
store <4 x float> %fmul7, ptr %gep9, align 16
%gep10 = getelementptr inbounds i8, ptr %in1, i64 32
%load5 = load <16 x i8>, ptr %gep10, align 1
%shufflevector12 = shufflevector <16 x i8> %load5, <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%shufflevector13 = shufflevector <16 x i8> %load5, <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%zext4 = zext <8 x i8> %shufflevector12 to <8 x i16>
%zext5 = zext <8 x i8> %shufflevector13 to <8 x i16>
%shufflevector14 = shufflevector <8 x i16> %zext4, <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%shufflevector15 = shufflevector <8 x i16> %zext4, <8 x i16> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%shufflevector16 = shufflevector <8 x i16> %zext5, <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%shufflevector17 = shufflevector <8 x i16> %zext5, <8 x i16> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%uitofp8 = uitofp nneg <4 x i16> %shufflevector14 to <4 x float>
%uitofp9 = uitofp nneg <4 x i16> %shufflevector15 to <4 x float>
%uitofp10 = uitofp nneg <4 x i16> %shufflevector16 to <4 x float>
%uitofp11 = uitofp nneg <4 x i16> %shufflevector17 to <4 x float>
%fmul8 = fmul <4 x float> %load2, %uitofp8
%fmul9 = fmul <4 x float> %load0, %uitofp9
%fmul10 = fmul <4 x float> %load1, %uitofp10
%fmul11 = fmul <4 x float> %load2, %uitofp11
%gep11 = getelementptr inbounds i8, ptr %in2, i64 128
%gep12 = getelementptr inbounds i8, ptr %in2, i64 144
%gep13 = getelementptr inbounds i8, ptr %in2, i64 160
%gep14 = getelementptr inbounds i8, ptr %in2, i64 176
store <4 x float> %fmul8, ptr %gep11, align 16
store <4 x float> %fmul9, ptr %gep12, align 16
store <4 x float> %fmul10, ptr %gep13, align 16
store <4 x float> %fmul11, ptr %gep14, align 16
ret void
}
Loading