Skip to content

[AArch64,TTI] Remove RealUse check for vector insert/extract costs. #146526

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+890 −321
Open

[AArch64,TTI] Remove RealUse check for vector insert/extract costs. #146526

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 7 additions & 12 deletions llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3712,7 +3712,7 @@ InstructionCost AArch64TTIImpl::getCFInstrCost(unsigned Opcode,

InstructionCost AArch64TTIImpl::getVectorInstrCostHelper(
unsigned Opcode, Type *Val, TTI::TargetCostKind CostKind, unsigned Index,
bool HasRealUse, const Instruction *I, Value *Scalar,
const Instruction *I, Value *Scalar,
ArrayRef<std::tuple<Value *, User *, int>> ScalarUserAndIdx) const {
assert(Val->isVectorTy() && "This must be a vector type");

Expand All @@ -3732,12 +3732,10 @@ InstructionCost AArch64TTIImpl::getVectorInstrCostHelper(
}

// The element at index zero is already inside the vector.
// - For a physical (HasRealUse==true) insert-element or extract-element
// - For a insert-element or extract-element
// instruction that extracts integers, an explicit FPR -> GPR move is
// needed. So it has non-zero cost.
// - For the rest of cases (virtual instruction or element type is float),
// consider the instruction free.
if (Index == 0 && (!HasRealUse || !Val->getScalarType()->isIntegerTy()))
if (Index == 0 && !Val->getScalarType()->isIntegerTy())
return 0;

// This is recognising a LD1 single-element structure to one lane of one
Expand Down Expand Up @@ -3887,25 +3885,22 @@ InstructionCost AArch64TTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
unsigned Index,
const Value *Op0,
const Value *Op1) const {
bool HasRealUse =
Opcode == Instruction::InsertElement && Op0 && !isa<UndefValue>(Op0);
return getVectorInstrCostHelper(Opcode, Val, CostKind, Index, HasRealUse);
return getVectorInstrCostHelper(Opcode, Val, CostKind, Index);
}

InstructionCost AArch64TTIImpl::getVectorInstrCost(
unsigned Opcode, Type *Val, TTI::TargetCostKind CostKind, unsigned Index,
Value *Scalar,
ArrayRef<std::tuple<Value *, User *, int>> ScalarUserAndIdx) const {
return getVectorInstrCostHelper(Opcode, Val, CostKind, Index, false, nullptr,
Scalar, ScalarUserAndIdx);
return getVectorInstrCostHelper(Opcode, Val, CostKind, Index, nullptr, Scalar,
ScalarUserAndIdx);
}

InstructionCost AArch64TTIImpl::getVectorInstrCost(const Instruction &I,
Type *Val,
TTI::TargetCostKind CostKind,
unsigned Index) const {
return getVectorInstrCostHelper(I.getOpcode(), Val, CostKind, Index,
true /* HasRealUse */, &I);
return getVectorInstrCostHelper(I.getOpcode(), Val, CostKind, Index, &I);
}

InstructionCost AArch64TTIImpl::getScalarizationOverhead(
Expand Down
8 changes: 3 additions & 5 deletions llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,16 +65,14 @@ class AArch64TTIImpl final : public BasicTTIImplBase<AArch64TTIImpl> {

// A helper function called by 'getVectorInstrCost'.
//
// 'Val' and 'Index' are forwarded from 'getVectorInstrCost'; 'HasRealUse'
// indicates whether the vector instruction is available in the input IR or
// just imaginary in vectorizer passes.
/// \param ScalarUserAndIdx encodes the information about extracts from a
// 'Val' and 'Index' are forwarded from 'getVectorInstrCost';
// \param ScalarUserAndIdx encodes the information about extracts from a
/// vector with 'Scalar' being the value being extracted,'User' being the user
/// of the extract(nullptr if user is not known before vectorization) and
/// 'Idx' being the extract lane.
InstructionCost getVectorInstrCostHelper(
unsigned Opcode, Type *Val, TTI::TargetCostKind CostKind, unsigned Index,
bool HasRealUse, const Instruction *I = nullptr, Value *Scalar = nullptr,
const Instruction *I = nullptr, Value *Scalar = nullptr,
ArrayRef<std::tuple<Value *, User *, int>> ScalarUserAndIdx = {}) const;

public:
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Analysis/CostModel/AArch64/reduce-add.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,11 @@ define void @reduce() {
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i8 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V32i8 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 5 for: %V64i8 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i16 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %V2i16 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i16 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i16 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> undef)
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V16i16 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i32 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %V2i32 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i32 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> undef)
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V8i32 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i64 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Analysis/CostModel/AArch64/reduce-and.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@ define void @reduce() {
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 5 for: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 9 for: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 0 for: %V1i8 = call i8 @llvm.vector.reduce.and.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V3i8 = call i8 @llvm.vector.reduce.and.v3i8(<3 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V1i8 = call i8 @llvm.vector.reduce.and.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:6 SizeLat:6 for: %V3i8 = call i8 @llvm.vector.reduce.and.v3i8(<3 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 7 for: %V4i8 = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 15 for: %V8i8 = call i8 @llvm.vector.reduce.and.v8i8(<8 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 17 for: %V16i8 = call i8 @llvm.vector.reduce.and.v16i8(<16 x i8> undef)
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Analysis/CostModel/AArch64/reduce-or.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@ define void @reduce() {
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 5 for: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 9 for: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 0 for: %V1i8 = call i8 @llvm.vector.reduce.or.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V3i8 = call i8 @llvm.vector.reduce.or.v3i8(<3 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V1i8 = call i8 @llvm.vector.reduce.or.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:6 SizeLat:6 for: %V3i8 = call i8 @llvm.vector.reduce.or.v3i8(<3 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 7 for: %V4i8 = call i8 @llvm.vector.reduce.or.v4i8(<4 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 15 for: %V8i8 = call i8 @llvm.vector.reduce.or.v8i8(<8 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 17 for: %V16i8 = call i8 @llvm.vector.reduce.or.v16i8(<16 x i8> undef)
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Analysis/CostModel/AArch64/reduce-xor.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@ define void @reduce() {
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V32 = call i1 @llvm.vector.reduce.xor.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 5 for: %V64 = call i1 @llvm.vector.reduce.xor.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 9 for: %V128 = call i1 @llvm.vector.reduce.xor.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found costs of 0 for: %V1i8 = call i8 @llvm.vector.reduce.xor.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V3i8 = call i8 @llvm.vector.reduce.xor.v3i8(<3 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %V1i8 = call i8 @llvm.vector.reduce.xor.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:6 SizeLat:6 for: %V3i8 = call i8 @llvm.vector.reduce.xor.v3i8(<3 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 7 for: %V4i8 = call i8 @llvm.vector.reduce.xor.v4i8(<4 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 15 for: %V8i8 = call i8 @llvm.vector.reduce.xor.v8i8(<8 x i8> undef)
; CHECK-NEXT: Cost Model: Found costs of 17 for: %V16i8 = call i8 @llvm.vector.reduce.xor.v16i8(<16 x i8> undef)
Expand Down
Loading
Loading