Skip to content

[VectorCombine] foldShuffleOfShuffles - fold "shuffle (shuffle x, y, m1), (shuffle y, x, m2)" -> "shuffle x, y, m3" #120959

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
RKSimon merged 2 commits into from
Dec 23, 2024
Merged

[VectorCombine] foldShuffleOfShuffles - fold "shuffle (shuffle x, y, m1), (shuffle y, x, m2)" -> "shuffle x, y, m3" #120959

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
45fe97d
[VectorCombine] foldShuffleOfShuffles - fold "shuffle (shuffle x, y, …
RKSimon Dec 23, 2024
8076b41
Split if-else chain
RKSimon Dec 23, 2024
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
105 changes: 63 additions & 42 deletions llvm/lib/Transforms/Vectorize/VectorCombine.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1871,6 +1871,7 @@ bool VectorCombine::foldShuffleOfCastops(Instruction &I) {
}

/// Try to convert any of:
/// "shuffle (shuffle x, y), (shuffle y, x)"
/// "shuffle (shuffle x, undef), (shuffle y, undef)"
/// "shuffle (shuffle x, undef), y"
/// "shuffle x, (shuffle y, undef)"
Expand All @@ -1883,78 +1884,104 @@ bool VectorCombine::foldShuffleOfShuffles(Instruction &I) {
return false;

ArrayRef<int> InnerMask0, InnerMask1;
Value *V0 = nullptr, *V1 = nullptr;
UndefValue *U0 = nullptr, *U1 = nullptr;
bool Match0 = match(
OuterV0, m_Shuffle(m_Value(V0), m_UndefValue(U0), m_Mask(InnerMask0)));
bool Match1 = match(
OuterV1, m_Shuffle(m_Value(V1), m_UndefValue(U1), m_Mask(InnerMask1)));
Value *X0, *X1, *Y0, *Y1;
bool Match0 =
match(OuterV0, m_Shuffle(m_Value(X0), m_Value(Y0), m_Mask(InnerMask0)));
bool Match1 =
match(OuterV1, m_Shuffle(m_Value(X1), m_Value(Y1), m_Mask(InnerMask1)));
if (!Match0 && !Match1)
return false;

V0 = Match0 ? V0 : OuterV0;
V1 = Match1 ? V1 : OuterV1;
X0 = Match0 ? X0 : OuterV0;
Y0 = Match0 ? Y0 : OuterV0;
X1 = Match1 ? X1 : OuterV1;
Y1 = Match1 ? Y1 : OuterV1;
auto *ShuffleDstTy = dyn_cast<FixedVectorType>(I.getType());
auto *ShuffleSrcTy = dyn_cast<FixedVectorType>(V0->getType());
auto *ShuffleImmTy = dyn_cast<FixedVectorType>(I.getOperand(0)->getType());
auto *ShuffleSrcTy = dyn_cast<FixedVectorType>(X0->getType());
auto *ShuffleImmTy = dyn_cast<FixedVectorType>(OuterV0->getType());
if (!ShuffleDstTy || !ShuffleSrcTy || !ShuffleImmTy ||
V0->getType() != V1->getType())
X0->getType() != X1->getType())
return false;

unsigned NumSrcElts = ShuffleSrcTy->getNumElements();
unsigned NumImmElts = ShuffleImmTy->getNumElements();

// Bail if either inner masks reference a RHS undef arg.
if ((Match0 && !isa<PoisonValue>(U0) &&
any_of(InnerMask0, [&](int M) { return M >= (int)NumSrcElts; })) ||
(Match1 && !isa<PoisonValue>(U1) &&
any_of(InnerMask1, [&](int M) { return M >= (int)NumSrcElts; })))
return false;

// Merge shuffles - replace index to the RHS poison arg with PoisonMaskElem,
// Attempt to merge shuffles, matching upto 2 source operands.
// Replace index to a poison arg with PoisonMaskElem.
// Bail if either inner masks reference an undef arg.
SmallVector<int, 16> NewMask(OuterMask);
Value *NewX = nullptr, *NewY = nullptr;
for (int &M : NewMask) {
Value *Src = nullptr;
if (0 <= M && M < (int)NumImmElts) {
if (Match0)
M = (InnerMask0[M] >= (int)NumSrcElts) ? PoisonMaskElem : InnerMask0[M];
Src = OuterV0;
if (Match0) {
M = InnerMask0[M];
Src = M >= (int)NumSrcElts ? Y0 : X0;
M = M >= (int)NumSrcElts ? (M - NumSrcElts) : M;
}
} else if (M >= (int)NumImmElts) {
Src = OuterV1;
M -= NumImmElts;
if (Match1) {
if (InnerMask1[M - NumImmElts] >= (int)NumSrcElts)
M = PoisonMaskElem;
else
M = InnerMask1[M - NumImmElts] + (V0 == V1 ? 0 : NumSrcElts);
M = InnerMask1[M];
Src = M >= (int)NumSrcElts ? Y1 : X1;
M = M >= (int)NumSrcElts ? (M - NumSrcElts) : M;
}
}
if (Src && M != PoisonMaskElem) {
assert(0 <= M && M < (int)NumSrcElts && "Unexpected shuffle mask index");
if (isa<UndefValue>(Src)) {
// We've referenced an undef element - if its poison, update the shuffle
// mask, else bail.
if (!isa<PoisonValue>(Src))
return false;
M = PoisonMaskElem;
continue;
} else if (!NewX || NewX == Src) {
Copy link
Member

@alexey-bataev alexey-bataev Dec 23, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Drop else here

NewX = Src;
continue;
} else if (!NewY || NewY == Src) {
Copy link
Member

@alexey-bataev alexey-bataev Dec 23, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Drop else here

M += NumSrcElts;
NewY = Src;
continue;
}
return false;
}
}

if (!NewX)
return PoisonValue::get(ShuffleDstTy);
if (!NewY)
NewY = PoisonValue::get(ShuffleSrcTy);

// Have we folded to an Identity shuffle?
if (ShuffleVectorInst::isIdentityMask(NewMask, NumSrcElts)) {
replaceValue(I, *V0);
replaceValue(I, *NewX);
return true;
}

// Try to merge the shuffles if the new shuffle is not costly.
InstructionCost InnerCost0 = 0;
if (Match0)
InnerCost0 = TTI.getShuffleCost(
TargetTransformInfo::SK_PermuteSingleSrc, ShuffleSrcTy, InnerMask0,
CostKind, 0, nullptr, {V0, U0}, cast<ShuffleVectorInst>(OuterV0));
InnerCost0 = TTI.getInstructionCost(cast<Instruction>(OuterV0), CostKind);

InstructionCost InnerCost1 = 0;
if (Match1)
InnerCost1 = TTI.getShuffleCost(
TargetTransformInfo::SK_PermuteSingleSrc, ShuffleSrcTy, InnerMask1,
CostKind, 0, nullptr, {V1, U1}, cast<ShuffleVectorInst>(OuterV1));
InnerCost1 = TTI.getInstructionCost(cast<Instruction>(OuterV1), CostKind);

InstructionCost OuterCost = TTI.getShuffleCost(
TargetTransformInfo::SK_PermuteTwoSrc, ShuffleImmTy, OuterMask, CostKind,
0, nullptr, {OuterV0, OuterV1}, &I);

InstructionCost OldCost = InnerCost0 + InnerCost1 + OuterCost;

InstructionCost NewCost =
TTI.getShuffleCost(TargetTransformInfo::SK_PermuteTwoSrc, ShuffleSrcTy,
NewMask, CostKind, 0, nullptr, {V0, V1});
bool IsUnary = all_of(NewMask, [&](int M) { return M < (int)NumSrcElts; });
TargetTransformInfo::ShuffleKind SK =
IsUnary ? TargetTransformInfo::SK_PermuteSingleSrc
: TargetTransformInfo::SK_PermuteTwoSrc;
InstructionCost NewCost = TTI.getShuffleCost(
SK, ShuffleSrcTy, NewMask, CostKind, 0, nullptr, {NewX, NewY});
if (!OuterV0->hasOneUse())
NewCost += InnerCost0;
if (!OuterV1->hasOneUse())
Expand All @@ -1966,13 +1993,7 @@ bool VectorCombine::foldShuffleOfShuffles(Instruction &I) {
if (NewCost > OldCost)
return false;

// Clear unused sources to poison.
if (none_of(NewMask, [&](int M) { return 0 <= M && M < (int)NumSrcElts; }))
V0 = PoisonValue::get(ShuffleSrcTy);
if (none_of(NewMask, [&](int M) { return (int)NumSrcElts <= M; }))
V1 = PoisonValue::get(ShuffleSrcTy);

Value *Shuf = Builder.CreateShuffleVector(V0, V1, NewMask);
Value *Shuf = Builder.CreateShuffleVector(NewX, NewY, NewMask);
replaceValue(I, *Shuf);
return true;
}
Expand Down
60 changes: 15 additions & 45 deletions llvm/test/Transforms/PhaseOrdering/X86/hadd.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -391,21 +391,11 @@ define <4 x i32> @add_v4i32_01uu(<4 x i32> %a, <4 x i32> %b) {
;

define <8 x i32> @add_v8i32_01234567(<8 x i32> %a, <8 x i32> %b) {
; SSE-LABEL: @add_v8i32_01234567(
; SSE-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> [[B:%.*]], <4 x i32> <i32 0, i32 2, i32 8, i32 10>
; SSE-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> [[B]], <4 x i32> <i32 4, i32 6, i32 12, i32 14>
; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> [[B]], <4 x i32> <i32 1, i32 3, i32 9, i32 11>
; SSE-NEXT: [[TMP4:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> [[B]], <4 x i32> <i32 5, i32 7, i32 13, i32 15>
; SSE-NEXT: [[TMP5:%.*]] = add <4 x i32> [[TMP1]], [[TMP3]]
; SSE-NEXT: [[TMP6:%.*]] = add <4 x i32> [[TMP2]], [[TMP4]]
; SSE-NEXT: [[TMP7:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; SSE-NEXT: ret <8 x i32> [[TMP7]]
;
; AVX-LABEL: @add_v8i32_01234567(
; AVX-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> [[B:%.*]], <8 x i32> <i32 0, i32 2, i32 8, i32 10, i32 4, i32 6, i32 12, i32 14>
; AVX-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> [[B]], <8 x i32> <i32 1, i32 3, i32 9, i32 11, i32 5, i32 7, i32 13, i32 15>
; AVX-NEXT: [[TMP3:%.*]] = add <8 x i32> [[TMP1]], [[TMP2]]
; AVX-NEXT: ret <8 x i32> [[TMP3]]
; CHECK-LABEL: @add_v8i32_01234567(
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> [[B:%.*]], <8 x i32> <i32 0, i32 2, i32 8, i32 10, i32 4, i32 6, i32 12, i32 14>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> [[B]], <8 x i32> <i32 1, i32 3, i32 9, i32 11, i32 5, i32 7, i32 13, i32 15>
; CHECK-NEXT: [[TMP3:%.*]] = add <8 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret <8 x i32> [[TMP3]]
;
%a0 = extractelement <8 x i32> %a, i32 0
%a1 = extractelement <8 x i32> %a, i32 1
Expand Down Expand Up @@ -786,21 +776,11 @@ define <4 x float> @add_v4f32_01uu(<4 x float> %a, <4 x float> %b) {
;

define <8 x float> @add_v8f32_01234567(<8 x float> %a, <8 x float> %b) {
; SSE-LABEL: @add_v8f32_01234567(
; SSE-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> [[B:%.*]], <4 x i32> <i32 0, i32 2, i32 8, i32 10>
; SSE-NEXT: [[TMP2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <4 x i32> <i32 4, i32 6, i32 12, i32 14>
; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <4 x i32> <i32 1, i32 3, i32 9, i32 11>
; SSE-NEXT: [[TMP4:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <4 x i32> <i32 5, i32 7, i32 13, i32 15>
; SSE-NEXT: [[TMP5:%.*]] = fadd <4 x float> [[TMP1]], [[TMP3]]
; SSE-NEXT: [[TMP6:%.*]] = fadd <4 x float> [[TMP2]], [[TMP4]]
; SSE-NEXT: [[TMP7:%.*]] = shufflevector <4 x float> [[TMP5]], <4 x float> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; SSE-NEXT: ret <8 x float> [[TMP7]]
;
; AVX-LABEL: @add_v8f32_01234567(
; AVX-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> [[B:%.*]], <8 x i32> <i32 0, i32 2, i32 8, i32 10, i32 4, i32 6, i32 12, i32 14>
; AVX-NEXT: [[TMP2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <8 x i32> <i32 1, i32 3, i32 9, i32 11, i32 5, i32 7, i32 13, i32 15>
; AVX-NEXT: [[TMP3:%.*]] = fadd <8 x float> [[TMP1]], [[TMP2]]
; AVX-NEXT: ret <8 x float> [[TMP3]]
; CHECK-LABEL: @add_v8f32_01234567(
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> [[B:%.*]], <8 x i32> <i32 0, i32 2, i32 8, i32 10, i32 4, i32 6, i32 12, i32 14>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <8 x i32> <i32 1, i32 3, i32 9, i32 11, i32 5, i32 7, i32 13, i32 15>
; CHECK-NEXT: [[TMP3:%.*]] = fadd <8 x float> [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret <8 x float> [[TMP3]]
;
%a0 = extractelement <8 x float> %a, i32 0
%a1 = extractelement <8 x float> %a, i32 1
Expand Down Expand Up @@ -969,21 +949,11 @@ define <2 x double> @add_v2f64_0u(<2 x double> %a, <2 x double> %b) {
;

define <4 x double> @add_v4f64_0123(<4 x double> %a, <4 x double> %b) {
; SSE-LABEL: @add_v4f64_0123(
; SSE-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <2 x i32> <i32 0, i32 4>
; SSE-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <2 x i32> <i32 2, i32 6>
; SSE-NEXT: [[TMP3:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <2 x i32> <i32 1, i32 5>
; SSE-NEXT: [[TMP4:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <2 x i32> <i32 3, i32 7>
; SSE-NEXT: [[TMP5:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
; SSE-NEXT: [[TMP6:%.*]] = fadd <2 x double> [[TMP2]], [[TMP4]]
; SSE-NEXT: [[TMP7:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; SSE-NEXT: ret <4 x double> [[TMP7]]
;
; AVX-LABEL: @add_v4f64_0123(
; AVX-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <4 x i32> <i32 1, i32 5, i32 3, i32 7>
; AVX-NEXT: [[TMP3:%.*]] = fadd <4 x double> [[TMP1]], [[TMP2]]
; AVX-NEXT: ret <4 x double> [[TMP3]]
; CHECK-LABEL: @add_v4f64_0123(
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <4 x i32> <i32 1, i32 5, i32 3, i32 7>
; CHECK-NEXT: [[TMP3:%.*]] = fadd <4 x double> [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret <4 x double> [[TMP3]]
;
%a0 = extractelement <4 x double> %a, i32 0
%a1 = extractelement <4 x double> %a, i32 1
Expand Down
6 changes: 2 additions & 4 deletions llvm/test/Transforms/VectorCombine/AArch64/select-shuffle.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -952,8 +952,7 @@ define <16 x i32> @testoutofbounds(<16 x i32> %x, <16 x i32> %y) {
; CHECK-NEXT: [[A:%.*]] = add nsw <16 x i32> [[S1]], [[S2]]
; CHECK-NEXT: [[B:%.*]] = sub nsw <16 x i32> [[S1]], [[S2]]
; CHECK-NEXT: [[S3:%.*]] = shufflevector <16 x i32> [[A]], <16 x i32> [[B]], <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i32> [[S3]], <16 x i32> poison, <16 x i32> <i32 16, i32 1, i32 18, i32 3, i32 20, i32 5, i32 22, i32 7, i32 24, i32 9, i32 26, i32 11, i32 28, i32 13, i32 30, i32 15>
; CHECK-NEXT: [[ADD:%.*]] = add <16 x i32> [[S3]], [[S4]]
; CHECK-NEXT: [[ADD:%.*]] = add <16 x i32> [[S3]], [[B]]
; CHECK-NEXT: ret <16 x i32> [[ADD]]
;
%s1 = shufflevector <16 x i32> %x, <16 x i32> %y, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
Expand All @@ -973,8 +972,7 @@ define <64 x i32> @testlargerextrashuffle2(i32 %call.i, <16 x i32> %0) {
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <16 x i32> [[TMP0]], i32 [[CALL_I]], i32 15
; CHECK-NEXT: [[TMP3:%.*]] = sub <16 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = add <16 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <16 x i32> [[TMP3]], <16 x i32> [[TMP4]], <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 20, i32 5, i32 6, i32 23, i32 8, i32 9, i32 26, i32 11, i32 12, i32 29, i32 14, i32 15>
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <16 x i32> [[TMP5]], <16 x i32> poison, <64 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 12, i32 13, i32 14, i32 15, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, 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: [[TMP6:%.*]] = shufflevector <16 x i32> [[TMP3]], <16 x i32> [[TMP4]], <64 x i32> <i32 0, i32 17, i32 2, i32 3, i32 20, i32 5, i32 6, i32 23, i32 8, i32 9, i32 26, i32 11, i32 12, i32 29, i32 14, i32 15, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, 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: ret <64 x i32> [[TMP6]]
;
entry:
Expand Down
Loading