Skip to content

[CostModel] getTypeBasedIntrinsicInstrCost - add default cost approximations for funnel shifts #124175

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 1 commit into from
Jan 24, 2025
Merged

[CostModel] getTypeBasedIntrinsicInstrCost - add default cost approximations for funnel shifts #124175

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
29 changes: 29 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 @@ -2258,6 +2258,12 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
case Intrinsic::abs:
ISD = ISD::ABS;
break;
case Intrinsic::fshl:
ISD = ISD::FSHL;
break;
case Intrinsic::fshr:
ISD = ISD::FSHR;
break;
case Intrinsic::smax:
ISD = ISD::SMAX;
break;
Expand Down Expand Up @@ -2547,6 +2553,29 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
{TTI::OK_UniformConstantValue, TTI::OP_None});
return Cost;
}
case Intrinsic::fshl:
case Intrinsic::fshr: {
// fshl: (X << (Z % BW)) | (Y >> (BW - (Z % BW)))
// fshr: (X << (BW - (Z % BW))) | (Y >> (Z % BW))
Type *CondTy = RetTy->getWithNewBitWidth(1);
InstructionCost Cost = 0;
Cost +=
thisT()->getArithmeticInstrCost(BinaryOperator::Or, RetTy, CostKind);
Cost +=
thisT()->getArithmeticInstrCost(BinaryOperator::Sub, RetTy, CostKind);
Cost +=
thisT()->getArithmeticInstrCost(BinaryOperator::Shl, RetTy, CostKind);
Cost += thisT()->getArithmeticInstrCost(BinaryOperator::LShr, RetTy,
CostKind);
Cost += thisT()->getArithmeticInstrCost(BinaryOperator::URem, RetTy,
CostKind);
// Shift-by-zero handling.
Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
CmpInst::ICMP_EQ, CostKind);
Cost += thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
CmpInst::ICMP_EQ, CostKind);
return Cost;
}
case Intrinsic::fptosi_sat:
case Intrinsic::fptoui_sat: {
if (Tys.empty())
Expand Down
16 changes: 8 additions & 8 deletions llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1025,10 +1025,10 @@ define void @fshr() #0 {
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'fshr'
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
Expand All @@ -1054,10 +1054,10 @@ define void @fshl() #0 {
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'fshl'
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ define void @fshr(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i3
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPEBASED-LABEL: 'fshr'
; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %1 = call <vscale x 1 x i32> @llvm.fshr.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <vscale x 1 x i32> @llvm.fshr.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <vscale x 1 x i32> @llvm.fshr.nxv4i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
Expand All @@ -51,7 +51,7 @@ define void @fshl(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i3
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPEBASED-LABEL: 'fshl'
; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %1 = call <vscale x 1 x i32> @llvm.fshl.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <vscale x 1 x i32> @llvm.fshl.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <vscale x 1 x i32> @llvm.fshl.nxv4i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
Expand Down
Loading