Skip to content

[RISCV][TTI] Implement instruction cost for vp.splice. #124221

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.

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 4, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
8 changes: 8 additions & 0 deletions llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -1235,6 +1235,14 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
: RISCV::VMV_V_X,
LT.second, CostKind);
}
case Intrinsic::experimental_vp_splice: {
// To support type-based query from vectorizer, set the index to 0.
// Note that index only change the cost from vslide.vx to vslide.vi and in
// current implementations they have same costs.
return getShuffleCost(TTI::SK_Splice,
cast<VectorType>(ICA.getArgTypes()[0]), {}, CostKind,
0, cast<VectorType>(ICA.getReturnType()));
}
}

if (ST->hasVInstructions() && RetTy->isVectorTy()) {
Expand Down
52 changes: 52 additions & 0 deletions llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
Original file line number Diff line number Diff line change
Expand Up @@ -2351,6 +2351,58 @@ define void @splat() {
ret void
}

define void @splice() {
; CHECK-LABEL: 'splice'
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vp.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vp.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1, <vscale x 32 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vp.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vp.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vp.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vp.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vp.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vp.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vp.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vp.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vp.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vp.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vp.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPEBASED-LABEL: 'splice'
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vp.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vp.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1, <vscale x 32 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vp.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vp.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vp.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vp.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vp.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vp.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vp.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vp.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vp.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vp.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vp.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%splice_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vp.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vp.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1, <vscale x 32 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vp.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vp.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vp.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vp.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vp.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vp.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vp.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vp.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1, <vscale x 16 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vp.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1, <vscale x 8 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vp.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1, <vscale x 4 x i1> zeroinitializer, i32 poison, i32 poison)
%splice_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vp.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1, <vscale x 2 x i1> zeroinitializer, i32 poison, i32 poison)
ret void
}

declare <2 x i8> @llvm.vp.add.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)
declare <4 x i8> @llvm.vp.add.v4i8(<4 x i8>, <4 x i8>, <4 x i1>, i32)
declare <8 x i8> @llvm.vp.add.v8i8(<8 x i8>, <8 x i8>, <8 x i1>, i32)
Expand Down
Loading