Skip to content

[TTI] Add costing for vp.strided.load and vp.strided.store #80360

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
Feb 2, 2024
Merged

[TTI] Add costing for vp.strided.load and vp.strided.store #80360

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
5c7893e
[TTI] Add costing for vp.strided.load and vp.strided.store
preames Feb 1, 2024
654e2af
Fix nit from review
preames Feb 2, 2024
d7cd9fc
Fix bug - wrong opcode for store case
preames Feb 2, 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
32 changes: 32 additions & 0 deletions llvm/include/llvm/CodeGen/BasicTTIImpl.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1375,6 +1375,18 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
true, CostKind);
}

InstructionCost getStridedMemoryOpCost(unsigned Opcode, Type *DataTy,
const Value *Ptr, bool VariableMask,
Align Alignment,
TTI::TargetCostKind CostKind,
const Instruction *I) {
// For a target without strided memory operations (or for an illegal
// operation type on one which does), assume we lower to a gather/scatter
// operation. (Which may in turn be scalarized.)
return thisT()->getGatherScatterOpCost(Opcode, DataTy, Ptr, VariableMask,
Alignment, CostKind, I);
}

InstructionCost getInterleavedMemoryOpCost(
unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
Align Alignment, unsigned AddressSpace, TTI::TargetCostKind CostKind,
Expand Down Expand Up @@ -1595,6 +1607,26 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
return thisT()->getGatherScatterOpCost(Instruction::Load, RetTy, Args[0],
VarMask, Alignment, CostKind, I);
}
case Intrinsic::experimental_vp_strided_store: {
const Value *Data = Args[0];
const Value *Ptr = Args[1];
const Value *Mask = Args[3];
const Value *EVL = Args[4];
bool VarMask = !isa<Constant>(Mask) || !isa<Constant>(EVL);
Align Alignment = I->getParamAlign(1).valueOrOne();
return thisT()->getStridedMemoryOpCost(Instruction::Store,
Data->getType(), Ptr, VarMask,
Alignment, CostKind, I);
}
case Intrinsic::experimental_vp_strided_load: {
const Value *Ptr = Args[0];
const Value *Mask = Args[2];
const Value *EVL = Args[3];
bool VarMask = !isa<Constant>(Mask) || !isa<Constant>(EVL);
Align Alignment = I->getParamAlign(0).valueOrOne();
return thisT()->getStridedMemoryOpCost(Instruction::Load, RetTy, Ptr,
VarMask, Alignment, CostKind, I);
}
case Intrinsic::experimental_stepvector: {
if (isa<ScalableVectorType>(RetTy))
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
Expand Down
8 changes: 4 additions & 4 deletions llvm/test/Analysis/CostModel/RISCV/gep.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,7 +272,7 @@ define void @non_foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = getelementptr i8, ptr %base, i32 42
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = getelementptr i8, ptr %base, i32 42
; RVI-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = getelementptr i8, ptr %base, i32 42
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store volatile <2 x i8> undef, ptr %7, align 2
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = getelementptr i8, ptr %base, i32 42
Expand All @@ -284,7 +284,7 @@ define void @non_foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = getelementptr i8, ptr %base, i32 42
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = getelementptr i8, ptr %base, i32 42
; RVI-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr %12, i64 undef, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr %12, i64 undef, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%1 = getelementptr i8, ptr %base, i32 42
Expand Down Expand Up @@ -342,7 +342,7 @@ define void @foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
; RVI-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %5 = getelementptr i8, ptr %base, i32 0
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %x5 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr %5, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %6 = getelementptr i8, ptr %base, i32 0
; RVI-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x6 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr %6, i64 undef, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %7 = getelementptr i8, ptr %base, i32 0
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store volatile <2 x i8> undef, ptr %7, align 2
; RVI-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %8 = getelementptr i8, ptr %base, i32 0
Expand All @@ -354,7 +354,7 @@ define void @foldable_vector_uses(ptr %base, <2 x ptr> %base.vec) {
; RVI-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %11 = getelementptr i8, ptr %base, i32 0
; RVI-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr %11, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %12 = getelementptr i8, ptr %base, i32 0
; RVI-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr %12, i64 undef, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr %12, i64 undef, <2 x i1> undef, i32 undef)
; RVI-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%1 = getelementptr i8, ptr %base, i32 0
Expand Down
Loading