[SLP]Model single unique value insert + shuffle as splat + select, where profitable
When we have the remaining unique scalar, that should be inserted into non-poison vector and into non-zero position: ``` %vec1 = insertelement %vec, %v, pos1 %res = shuffle %vec1, poison, <0, 1, 2,..., pos1, pos1 + 1, ..., pos1, ...> ``` better to estimate if it is profitable to model it as is or model it as: ``` %bv = insertelement poison, %v, 0 %splat = shuffle %bv, poison, <poison, ..., 0, ..., 0, ...> %res = shuffle %vec, %splat, <0, 1, 2,..., pos1 + VF, pos1 + 1, ...> ``` Reviewers: preames, hiraditya, RKSimon Reviewed By: preames Pull Request: https://github.com/llvm/llvm-project/pull/136590
This commit is contained in:
Alexey Bataev
GitHub
parent
f010725e39
commit
0252d338fa
@ -12613,11 +12613,13 @@ public:
|
||||
}
|
||||
InstructionCost createFreeze(InstructionCost Cost) { return Cost; }
|
||||
/// Finalize emission of the shuffles.
|
||||
InstructionCost
|
||||
finalize(ArrayRef<int> ExtMask,
|
||||
ArrayRef<std::pair<const TreeEntry *, unsigned>> SubVectors,
|
||||
ArrayRef<int> SubVectorsMask, unsigned VF = 0,
|
||||
function_ref<void(Value *&, SmallVectorImpl<int> &)> Action = {}) {
|
||||
InstructionCost finalize(
|
||||
ArrayRef<int> ExtMask,
|
||||
ArrayRef<std::pair<const TreeEntry *, unsigned>> SubVectors,
|
||||
ArrayRef<int> SubVectorsMask, unsigned VF = 0,
|
||||
function_ref<void(Value *&, SmallVectorImpl<int> &,
|
||||
function_ref<Value *(Value *, Value *, ArrayRef<int>)>)>
|
||||
Action = {}) {
|
||||
IsFinalized = true;
|
||||
if (Action) {
|
||||
const PointerUnion<Value *, const TreeEntry *> &Vec = InVectors.front();
|
||||
@ -12629,7 +12631,10 @@ public:
|
||||
assert(VF > 0 &&
|
||||
"Expected vector length for the final value before action.");
|
||||
Value *V = cast<Value *>(Vec);
|
||||
Action(V, CommonMask);
|
||||
Action(V, CommonMask, [this](Value *V1, Value *V2, ArrayRef<int> Mask) {
|
||||
Cost += createShuffle(V1, V2, Mask);
|
||||
return V1;
|
||||
});
|
||||
InVectors.front() = V;
|
||||
}
|
||||
if (!SubVectors.empty()) {
|
||||
@ -16593,11 +16598,13 @@ public:
|
||||
/// Finalize emission of the shuffles.
|
||||
/// \param Action the action (if any) to be performed before final applying of
|
||||
/// the \p ExtMask mask.
|
||||
Value *
|
||||
finalize(ArrayRef<int> ExtMask,
|
||||
ArrayRef<std::pair<const TreeEntry *, unsigned>> SubVectors,
|
||||
ArrayRef<int> SubVectorsMask, unsigned VF = 0,
|
||||
function_ref<void(Value *&, SmallVectorImpl<int> &)> Action = {}) {
|
||||
Value *finalize(
|
||||
ArrayRef<int> ExtMask,
|
||||
ArrayRef<std::pair<const TreeEntry *, unsigned>> SubVectors,
|
||||
ArrayRef<int> SubVectorsMask, unsigned VF = 0,
|
||||
function_ref<void(Value *&, SmallVectorImpl<int> &,
|
||||
function_ref<Value *(Value *, Value *, ArrayRef<int>)>)>
|
||||
Action = {}) {
|
||||
IsFinalized = true;
|
||||
if (Action) {
|
||||
Value *Vec = InVectors.front();
|
||||
@ -16616,7 +16623,9 @@ public:
|
||||
std::iota(ResizeMask.begin(), std::next(ResizeMask.begin(), VecVF), 0);
|
||||
Vec = createShuffle(Vec, nullptr, ResizeMask);
|
||||
}
|
||||
Action(Vec, CommonMask);
|
||||
Action(Vec, CommonMask, [this](Value *V1, Value *V2, ArrayRef<int> Mask) {
|
||||
return createShuffle(V1, V2, Mask);
|
||||
});
|
||||
InVectors.front() = Vec;
|
||||
}
|
||||
if (!SubVectors.empty()) {
|
||||
@ -17278,9 +17287,67 @@ ResTy BoUpSLP::processBuildVector(const TreeEntry *E, Type *ScalarTy,
|
||||
else
|
||||
Res = ShuffleBuilder.finalize(
|
||||
E->ReuseShuffleIndices, SubVectors, SubVectorsMask, E->Scalars.size(),
|
||||
[&](Value *&Vec, SmallVectorImpl<int> &Mask) {
|
||||
TryPackScalars(NonConstants, Mask, /*IsRootPoison=*/false);
|
||||
Vec = ShuffleBuilder.gather(NonConstants, Mask.size(), Vec);
|
||||
[&](Value *&Vec, SmallVectorImpl<int> &Mask, auto CreateShuffle) {
|
||||
bool IsSplat = isSplat(NonConstants);
|
||||
SmallVector<int> BVMask(Mask.size(), PoisonMaskElem);
|
||||
TryPackScalars(NonConstants, BVMask, /*IsRootPoison=*/false);
|
||||
auto CheckIfSplatIsProfitable = [&]() {
|
||||
// Estimate the cost of splatting + shuffle and compare with
|
||||
// insert + shuffle.
|
||||
constexpr TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
|
||||
Value *V = *find_if_not(NonConstants, IsaPred<UndefValue>);
|
||||
if (isa<ExtractElementInst>(V) || isVectorized(V))
|
||||
return false;
|
||||
InstructionCost SplatCost = TTI->getVectorInstrCost(
|
||||
Instruction::InsertElement, VecTy, CostKind, /*Index=*/0,
|
||||
PoisonValue::get(VecTy), V);
|
||||
SmallVector<int> NewMask(Mask.begin(), Mask.end());
|
||||
for (auto [Idx, I] : enumerate(BVMask))
|
||||
if (I != PoisonMaskElem)
|
||||
NewMask[Idx] = Mask.size();
|
||||
SplatCost += ::getShuffleCost(*TTI, TTI::SK_PermuteTwoSrc, VecTy,
|
||||
NewMask, CostKind);
|
||||
InstructionCost BVCost = TTI->getVectorInstrCost(
|
||||
Instruction::InsertElement, VecTy, CostKind,
|
||||
*find_if(Mask, [](int I) { return I != PoisonMaskElem; }),
|
||||
Vec, V);
|
||||
// Shuffle required?
|
||||
if (count(BVMask, PoisonMaskElem) <
|
||||
static_cast<int>(BVMask.size() - 1)) {
|
||||
SmallVector<int> NewMask(Mask.begin(), Mask.end());
|
||||
for (auto [Idx, I] : enumerate(BVMask))
|
||||
if (I != PoisonMaskElem)
|
||||
NewMask[Idx] = I;
|
||||
BVCost += ::getShuffleCost(*TTI, TTI::SK_PermuteSingleSrc,
|
||||
VecTy, NewMask, CostKind);
|
||||
}
|
||||
return SplatCost <= BVCost;
|
||||
};
|
||||
if (!IsSplat || Mask.size() <= 2 || !CheckIfSplatIsProfitable()) {
|
||||
for (auto [Idx, I] : enumerate(BVMask))
|
||||
if (I != PoisonMaskElem)
|
||||
Mask[Idx] = I;
|
||||
Vec = ShuffleBuilder.gather(NonConstants, Mask.size(), Vec);
|
||||
} else {
|
||||
Value *V = *find_if_not(NonConstants, IsaPred<UndefValue>);
|
||||
SmallVector<Value *> Values(NonConstants.size(),
|
||||
PoisonValue::get(ScalarTy));
|
||||
Values[0] = V;
|
||||
Value *BV = ShuffleBuilder.gather(Values, BVMask.size());
|
||||
SmallVector<int> SplatMask(BVMask.size(), PoisonMaskElem);
|
||||
transform(BVMask, SplatMask.begin(), [](int I) {
|
||||
return I == PoisonMaskElem ? PoisonMaskElem : 0;
|
||||
});
|
||||
if (!ShuffleVectorInst::isIdentityMask(SplatMask, VF))
|
||||
BV = CreateShuffle(BV, nullptr, SplatMask);
|
||||
for (auto [Idx, I] : enumerate(BVMask))
|
||||
if (I != PoisonMaskElem)
|
||||
Mask[Idx] = BVMask.size() + Idx;
|
||||
Vec = CreateShuffle(Vec, BV, Mask);
|
||||
for (auto [Idx, I] : enumerate(Mask))
|
||||
if (I != PoisonMaskElem)
|
||||
Mask[Idx] = Idx;
|
||||
}
|
||||
});
|
||||
} else if (!allConstant(GatheredScalars)) {
|
||||
// Gather unique scalars and all constants.
|
||||
|
||||
@ -38,7 +38,8 @@ define void @test() {
|
||||
; CHECK-NEXT: br i1 poison, label %[[BB167:.*]], label %[[BB77:.*]]
|
||||
; CHECK: [[BB77]]:
|
||||
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <16 x float> [[TMP11]], <16 x float> poison, <8 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 14, i32 15, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x float> [[TMP12]], float [[I70]], i32 0
|
||||
; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x float> poison, float [[I70]], i32 0
|
||||
; CHECK-NEXT: [[TMP23:%.*]] = shufflevector <8 x float> [[TMP12]], <8 x float> [[TMP17]], <8 x i32> <i32 8, i32 poison, i32 poison, i32 poison, i32 4, i32 5, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x float> poison, float [[I70]], i32 1
|
||||
; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x float> [[TMP14]], float [[I68]], i32 2
|
||||
; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x float> [[TMP19]], float [[I66]], i32 3
|
||||
@ -48,7 +49,7 @@ define void @test() {
|
||||
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <16 x float> [[TMP39]], <16 x float> [[TMP25]], <16 x i32> <i32 poison, i32 poison, i32 2, i32 3, i32 18, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 19, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: br label %[[BB78:.*]]
|
||||
; CHECK: [[BB78]]:
|
||||
; CHECK-NEXT: [[TMP15:%.*]] = phi <8 x float> [ [[TMP17]], %[[BB77]] ], [ [[TMP36:%.*]], %[[BB78]] ]
|
||||
; CHECK-NEXT: [[TMP15:%.*]] = phi <8 x float> [ [[TMP23]], %[[BB77]] ], [ [[TMP36:%.*]], %[[BB78]] ]
|
||||
; CHECK-NEXT: [[TMP22:%.*]] = phi <8 x float> [ [[TMP21]], %[[BB77]] ], [ [[TMP31:%.*]], %[[BB78]] ]
|
||||
; CHECK-NEXT: [[TMP24:%.*]] = shufflevector <8 x float> [[TMP22]], <8 x float> poison, <16 x i32> <i32 0, i32 3, i32 1, i32 2, i32 3, i32 0, i32 2, i32 3, i32 2, i32 6, i32 2, i32 3, i32 0, i32 7, i32 6, i32 6>
|
||||
; CHECK-NEXT: [[TMP38:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 1, i32 0, i32 3, i32 1, i32 3, i32 5, i32 3, i32 1, i32 0, i32 4, i32 5, i32 5>
|
||||
|
||||
@ -255,7 +255,9 @@ define void @select_uniform_ugt_16xi8(ptr %ptr, i8 %x) {
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i8>, ptr [[GEP_12]], align 1
|
||||
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i8> [[TMP2]], <2 x i8> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <8 x i8> [[TMP0]], <8 x i8> [[TMP4]], <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 8, i32 9, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <16 x i8> [[TMP5]], i8 [[L_11]], i32 11
|
||||
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <16 x i8> poison, i8 [[L_11]], i32 0
|
||||
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <16 x i8> [[TMP10]], <16 x i8> poison, <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <16 x i8> [[TMP5]], <16 x i8> [[TMP11]], <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 8, i32 9, i32 10, i32 27, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP7:%.*]] = call <16 x i8> @llvm.vector.insert.v16i8.v8i8(<16 x i8> [[TMP6]], <8 x i8> [[TMP0]], i64 0)
|
||||
; CHECK-NEXT: [[TMP8:%.*]] = call <16 x i8> @llvm.vector.insert.v16i8.v4i8(<16 x i8> [[TMP7]], <4 x i8> [[TMP3]], i64 12)
|
||||
; CHECK-NEXT: [[TMP9:%.*]] = icmp ugt <16 x i8> [[TMP8]], splat (i8 -1)
|
||||
|
||||
@ -12,7 +12,9 @@ define i32 @test() {
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> zeroinitializer, [[TMP1]]
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <12 x i32> <i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1, i32 2, i32 2, i32 2, i32 2, i32 3>
|
||||
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 0, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <16 x i32> [[TMP7]], i32 [[G_228_PROMOTED166_I1105_I]], i32 7
|
||||
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <16 x i32> poison, i32 [[G_228_PROMOTED166_I1105_I]], i32 0
|
||||
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <16 x i32> [[TMP5]], <16 x i32> poison, <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <16 x i32> [[TMP7]], <16 x i32> [[TMP9]], <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 23, i32 8, i32 9, i32 10, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP6:%.*]] = call <16 x i32> @llvm.vector.insert.v16i32.v12i32(<16 x i32> poison, <12 x i32> [[TMP3]], i64 0)
|
||||
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <16 x i32> [[TMP6]], <16 x i32> [[TMP8]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 23, i32 24, i32 25, i32 26, i32 7, i32 8, i32 9, i32 10, i32 11>
|
||||
; CHECK-NEXT: [[TMP12:%.*]] = icmp ugt <16 x i32> [[TMP11]], zeroinitializer
|
||||
|
||||
@ -9,6 +9,8 @@ define i32 @test(i64 %l.549) {
|
||||
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i64> poison, i64 [[CONV3]], i32 3
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x i64> poison, i64 0, i32 0
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x i64> [[TMP3]], i64 0, i32 1
|
||||
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <4 x i64> poison, i64 [[L_549]], i32 0
|
||||
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <4 x i64> [[TMP8]], <4 x i64> poison, <4 x i32> <i32 poison, i32 0, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: br label %[[IF_THEN19:.*]]
|
||||
; CHECK: [[P:.*]]:
|
||||
; CHECK-NEXT: [[TMP5:%.*]] = phi <2 x i64> [ zeroinitializer, %[[IF_END29:.*]] ], [ [[TMP13:%.*]], %[[IF_END25:.*]] ]
|
||||
@ -23,20 +25,20 @@ define i32 @test(i64 %l.549) {
|
||||
; CHECK: [[LOR_LHS_FALSE]]:
|
||||
; CHECK-NEXT: br i1 false, label %[[LAND_LHS_TRUE]], label %[[S]]
|
||||
; CHECK: [[R]]:
|
||||
; CHECK-NEXT: [[TMP8:%.*]] = phi <4 x i64> [ [[TMP7]], %[[Q]] ], [ [[TMP16:%.*]], %[[IF_THEN19]] ]
|
||||
; CHECK-NEXT: [[TMP18:%.*]] = phi <4 x i64> [ [[TMP7]], %[[Q]] ], [ [[TMP16:%.*]], %[[IF_THEN19]] ]
|
||||
; CHECK-NEXT: br i1 false, label %[[S]], label %[[LAND_LHS_TRUE]]
|
||||
; CHECK: [[LAND_LHS_TRUE]]:
|
||||
; CHECK-NEXT: [[TMP9:%.*]] = phi <4 x i64> [ [[TMP8]], %[[R]] ], [ zeroinitializer, %[[LOR_LHS_FALSE]] ]
|
||||
; CHECK-NEXT: [[TMP19:%.*]] = phi <4 x i64> [ [[TMP18]], %[[R]] ], [ zeroinitializer, %[[LOR_LHS_FALSE]] ]
|
||||
; CHECK-NEXT: br i1 false, label %[[Q]], label %[[S]]
|
||||
; CHECK: [[S]]:
|
||||
; CHECK-NEXT: [[TMP10:%.*]] = phi <4 x i64> [ [[TMP9]], %[[LAND_LHS_TRUE]] ], [ [[TMP8]], %[[R]] ], [ [[TMP7]], %[[LOR_LHS_FALSE]] ], [ [[TMP17]], %[[P]] ]
|
||||
; CHECK-NEXT: [[TMP10:%.*]] = phi <4 x i64> [ [[TMP19]], %[[LAND_LHS_TRUE]] ], [ [[TMP18]], %[[R]] ], [ [[TMP7]], %[[LOR_LHS_FALSE]] ], [ [[TMP17]], %[[P]] ]
|
||||
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x i64> [[TMP10]], <4 x i64> poison, <2 x i32> <i32 0, i32 1>
|
||||
; CHECK-NEXT: br label %[[IF_THEN19]]
|
||||
; CHECK: [[IF_THEN19]]:
|
||||
; CHECK-NEXT: [[TMP12:%.*]] = phi <2 x i64> [ zeroinitializer, %[[ENTRY]] ], [ [[TMP11]], %[[S]] ]
|
||||
; CHECK-NEXT: [[TMP13]] = shufflevector <2 x i64> [[TMP12]], <2 x i64> poison, <2 x i32> <i32 1, i32 0>
|
||||
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <2 x i64> [[TMP12]], <2 x i64> poison, <4 x i32> <i32 0, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <4 x i64> [[TMP14]], i64 [[L_549]], i32 1
|
||||
; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <4 x i64> [[TMP14]], <4 x i64> [[TMP9]], <4 x i32> <i32 0, i32 5, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP16]] = call <4 x i64> @llvm.vector.insert.v4i64.v2i64(<4 x i64> [[TMP15]], <2 x i64> [[TMP2]], i64 2)
|
||||
; CHECK-NEXT: br i1 false, label %[[R]], label %[[IF_END25]]
|
||||
; CHECK: [[IF_END25]]:
|
||||
|
||||
@ -30,16 +30,18 @@ define i32 @test(i32 %s.0) {
|
||||
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 poison, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <8 x i32> [[TMP13]], <8 x i32> <i32 0, i32 poison, i32 0, i32 0, i32 0, i32 0, i32 0, i32 poison>, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 12, i32 13, i32 14, i32 poison>
|
||||
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x i32> [[TMP14]], i32 [[J_4]], i32 7
|
||||
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x i32> poison, i32 [[J_4]], i32 0
|
||||
; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <8 x i32> [[TMP15]], <8 x i32> poison, <8 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0>
|
||||
; CHECK-NEXT: [[TMP29:%.*]] = shufflevector <8 x i32> [[TMP14]], <8 x i32> [[TMP16]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 15>
|
||||
; CHECK-NEXT: br label %[[IF_END24]]
|
||||
; CHECK: [[IF_THEN18:.*]]:
|
||||
; CHECK-NEXT: br label %[[T]]
|
||||
; CHECK: [[T]]:
|
||||
; CHECK-NEXT: [[TMP16:%.*]] = phi <8 x i32> [ [[TMP27:%.*]], %[[O]] ], [ poison, %[[IF_THEN18]] ]
|
||||
; CHECK-NEXT: [[TMP30:%.*]] = phi <8 x i32> [ [[TMP27:%.*]], %[[O]] ], [ poison, %[[IF_THEN18]] ]
|
||||
; CHECK-NEXT: [[TMP17]] = extractelement <4 x i32> [[TMP23:%.*]], i32 0
|
||||
; CHECK-NEXT: br i1 false, label %[[IF_END24]], label %[[K]]
|
||||
; CHECK: [[IF_END24]]:
|
||||
; CHECK-NEXT: [[TMP18:%.*]] = phi <8 x i32> [ [[TMP15]], %[[IF_THEN11]] ], [ [[TMP11]], %[[IF_END6]] ], [ [[TMP16]], %[[T]] ]
|
||||
; CHECK-NEXT: [[TMP18:%.*]] = phi <8 x i32> [ [[TMP29]], %[[IF_THEN11]] ], [ [[TMP11]], %[[IF_END6]] ], [ [[TMP30]], %[[T]] ]
|
||||
; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <8 x i32> [[TMP18]], <8 x i32> poison, <2 x i32> <i32 7, i32 1>
|
||||
; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <8 x i32> [[TMP18]], <8 x i32> poison, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
|
||||
; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <8 x i32> [[TMP18]], <8 x i32> poison, <4 x i32> <i32 2, i32 3, i32 4, i32 6>
|
||||
|
||||
@ -124,15 +124,15 @@ define double @preserve_loop_info(ptr %arg, i1 %arg2) {
|
||||
; CHECK: outer.header:
|
||||
; CHECK-NEXT: br label [[INNER:%.*]]
|
||||
; CHECK: inner:
|
||||
; CHECK-NEXT: br i1 %arg2, label [[OUTER_LATCH:%.*]], label [[INNER]]
|
||||
; CHECK-NEXT: br i1 [[ARG2:%.*]], label [[OUTER_LATCH:%.*]], label [[INNER]]
|
||||
; CHECK: outer.latch:
|
||||
; CHECK-NEXT: br i1 %arg2, label [[BB:%.*]], label [[OUTER_HEADER]]
|
||||
; CHECK-NEXT: br i1 [[ARG2]], label [[BB:%.*]], label [[OUTER_HEADER]]
|
||||
; CHECK: bb:
|
||||
; CHECK-NEXT: [[TMP5:%.*]] = load ptr, ptr undef, align 8
|
||||
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [3 x double], ptr [[TMP]], i64 0, i64 1
|
||||
; CHECK-NEXT: br label [[LOOP_3HEADER:%.*]]
|
||||
; CHECK: loop.3header:
|
||||
; CHECK-NEXT: br i1 %arg2, label [[LOOP_3LATCH:%.*]], label [[BB9:%.*]]
|
||||
; CHECK-NEXT: br i1 [[ARG2]], label [[LOOP_3LATCH:%.*]], label [[BB9:%.*]]
|
||||
; CHECK: bb9:
|
||||
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [3 x double], ptr [[TMP5]], i64 undef, i64 1
|
||||
; CHECK-NEXT: store double undef, ptr [[TMP]], align 16
|
||||
@ -140,7 +140,7 @@ define double @preserve_loop_info(ptr %arg, i1 %arg2) {
|
||||
; CHECK-NEXT: store double [[TMP12]], ptr [[TMP7]], align 8
|
||||
; CHECK-NEXT: br label [[LOOP_3LATCH]]
|
||||
; CHECK: loop.3latch:
|
||||
; CHECK-NEXT: br i1 %arg2, label [[BB14:%.*]], label [[LOOP_3HEADER]]
|
||||
; CHECK-NEXT: br i1 [[ARG2]], label [[BB14:%.*]], label [[LOOP_3HEADER]]
|
||||
; CHECK: bb14:
|
||||
; CHECK-NEXT: [[TMP15:%.*]] = call double undef(ptr [[TMP]], ptr [[ARG:%.*]])
|
||||
; CHECK-NEXT: ret double undef
|
||||
@ -189,7 +189,8 @@ define void @gather_sequence_crash(<2 x float> %arg, ptr %arg1, float %arg2, ptr
|
||||
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds float, ptr [[ARG1:%.*]], i32 3
|
||||
; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <2 x float> [[ARG:%.*]], <2 x float> poison, <4 x i32> <i32 poison, i32 0, i32 1, i32 poison>
|
||||
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> <float poison, float poison, float poison, float 0.000000e+00>, <4 x i32> <i32 poison, i32 1, i32 2, i32 7>
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x float> [[TMP1]], float [[ARG2:%.*]], i32 0
|
||||
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x float> poison, float [[ARG2:%.*]], i32 0
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> [[TMP6]], <4 x i32> <i32 4, i32 1, i32 2, i32 3>
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = fmul <4 x float> [[TMP2]], zeroinitializer
|
||||
; CHECK-NEXT: store <4 x float> [[TMP3]], ptr [[TMP8]], align 4
|
||||
; CHECK-NEXT: ret void
|
||||
|
||||
@ -6,7 +6,9 @@ define i32 @foo() {
|
||||
; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
|
||||
; CHECK-NEXT: [[ENTRY:.*:]]
|
||||
; CHECK-NEXT: [[D:%.*]] = load i32, ptr null, align 4
|
||||
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> <i32 0, i32 undef, i32 1, i32 0>, i32 [[D]], i32 1
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <8 x i32> poison, i32 [[D]], i32 0
|
||||
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <8 x i32> [[TMP3]], <8 x i32> poison, <4 x i32> <i32 poison, i32 0, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <4 x i32> <i32 0, i32 undef, i32 1, i32 0>, <4 x i32> [[TMP4]], <4 x i32> <i32 0, i32 5, i32 2, i32 3>
|
||||
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 1>
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = add <8 x i32> zeroinitializer, [[TMP1]]
|
||||
; CHECK-NEXT: store <8 x i32> [[TMP2]], ptr getelementptr inbounds ([64 x i32], ptr null, i64 0, i64 15), align 4
|
||||
|
||||
@ -11,7 +11,8 @@ define i32 @test(i1 %cond) {
|
||||
; CHECK-NEXT: [[TMP0:%.*]] = phi <2 x i32> [ [[TMP8:%.*]], %[[BB]] ], [ zeroinitializer, %[[ENTRY]] ]
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP0]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> <i32 poison, i32 poison, i32 0, i32 0>, <4 x i32> <i32 poison, i32 1, i32 6, i32 7>
|
||||
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x i32> [[TMP3]], i32 [[P1]], i32 0
|
||||
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <4 x i32> poison, i32 [[P1]], i32 0
|
||||
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP10]], <4 x i32> <i32 4, i32 1, i32 2, i32 3>
|
||||
; CHECK-NEXT: [[TMP5:%.*]] = or <4 x i32> zeroinitializer, [[TMP4]]
|
||||
; CHECK-NEXT: [[OR92]] = or i32 1, 0
|
||||
; CHECK-NEXT: [[TMP6:%.*]] = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> [[TMP5]])
|
||||
|
||||
@ -9,12 +9,13 @@ define i32 @test(ptr %sptr, i64 %0) {
|
||||
; CHECK-NEXT: [[CONV_I:%.*]] = trunc i64 [[TMP0]] to i32
|
||||
; CHECK-NEXT: [[IV2:%.*]] = getelementptr i8, ptr [[SPTR]], i64 4
|
||||
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, ptr [[IV2]], align 4
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[CONV_I]], i32 1
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 1>
|
||||
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x i32> poison, i32 [[CONV_I]], i32 0
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP6]], <4 x i32> poison, <4 x i32> <i32 poison, i32 0, i32 poison, i32 0>
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP3]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
|
||||
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 1, i32 5, i32 1, i32 poison>
|
||||
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> <i32 poison, i32 poison, i32 poison, i32 0>, <4 x i32> <i32 0, i32 1, i32 2, i32 7>
|
||||
; CHECK-NEXT: [[TMP7:%.*]] = icmp slt <4 x i32> [[TMP3]], [[TMP5]]
|
||||
; CHECK-NEXT: [[TMP12:%.*]] = icmp sle <4 x i32> [[TMP3]], [[TMP5]]
|
||||
; CHECK-NEXT: [[TMP7:%.*]] = icmp slt <4 x i32> [[TMP2]], [[TMP5]]
|
||||
; CHECK-NEXT: [[TMP12:%.*]] = icmp sle <4 x i32> [[TMP2]], [[TMP5]]
|
||||
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <4 x i1> [[TMP7]], <4 x i1> [[TMP12]], <4 x i32> <i32 0, i32 1, i32 6, i32 3>
|
||||
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq <4 x i32> [[TMP1]], zeroinitializer
|
||||
; CHECK-NEXT: [[TMP10:%.*]] = or <4 x i1> [[TMP9]], [[TMP8]]
|
||||
|
||||
@ -19,7 +19,8 @@ define void @test() {
|
||||
; CHECK-NEXT: [[TMP6:%.*]] = load float, ptr [[ARRAYIDX31]], align 4
|
||||
; CHECK-NEXT: [[TMP14:%.*]] = load <4 x float>, ptr [[ARRAYIDX]], align 4
|
||||
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x float> [[TMP14]], <4 x float> poison, <4 x i32> <i32 poison, i32 0, i32 1, i32 2>
|
||||
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x float> [[TMP4]], float [[TMP0]], i32 0
|
||||
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> poison, float [[TMP0]], i32 0
|
||||
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x float> [[TMP4]], <4 x float> [[TMP7]], <4 x i32> <i32 4, i32 1, i32 2, i32 3>
|
||||
; CHECK-NEXT: [[TMP15:%.*]] = fmul fast <4 x float> [[TMP11]], [[TMP14]]
|
||||
; CHECK-NEXT: store <4 x float> [[TMP15]], ptr [[ARRAYIDX6]], align 4
|
||||
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 5
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user