Skip to content

[CostModel] Add type-based cost model for get.active.lane.mask intrinsic #130132

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
Mar 7, 2025
Merged

[CostModel] Add type-based cost model for get.active.lane.mask intrinsic #130132

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
fc515fb
[CostModel] Add type-based cost model for get.active.lane.mask intrinsic
david-arm Mar 6, 2025
3097f54
Address review comment
david-arm Mar 7, 2025
7f0015f
Address review comment
david-arm Mar 7, 2025
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
43 changes: 22 additions & 21 deletions llvm/include/llvm/CodeGen/BasicTTIImpl.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1986,27 +1986,6 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
}
return Cost;
}
case Intrinsic::get_active_lane_mask: {
EVT ResVT = getTLI()->getValueType(DL, RetTy, true);
EVT ArgType = getTLI()->getValueType(DL, ICA.getArgTypes()[0], true);

// If we're not expanding the intrinsic then we assume this is cheap
// to implement.
if (!getTLI()->shouldExpandGetActiveLaneMask(ResVT, ArgType)) {
return getTypeLegalizationCost(RetTy).first;
}

// Create the expanded types that will be used to calculate the uadd_sat
// operation.
Type *ExpRetTy = VectorType::get(
ICA.getArgTypes()[0], cast<VectorType>(RetTy)->getElementCount());
IntrinsicCostAttributes Attrs(Intrinsic::uadd_sat, ExpRetTy, {}, FMF);
InstructionCost Cost =
thisT()->getTypeBasedIntrinsicInstrCost(Attrs, CostKind);
Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, ExpRetTy, RetTy,
CmpInst::ICMP_ULT, CostKind);
return Cost;
}
case Intrinsic::experimental_cttz_elts: {
EVT ArgType = getTLI()->getValueType(DL, ICA.getArgTypes()[0], true);

Expand Down Expand Up @@ -2054,6 +2033,7 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {

return Cost;
}
case Intrinsic::get_active_lane_mask:
case Intrinsic::experimental_vector_match:
return thisT()->getTypeBasedIntrinsicInstrCost(ICA, CostKind);
case Intrinsic::modf:
Expand Down Expand Up @@ -2394,6 +2374,27 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
thisT()->getArithmeticInstrCost(BinaryOperator::And, RetTy, CostKind);
return Cost;
}
case Intrinsic::get_active_lane_mask: {
Type *ArgTy = ICA.getArgTypes()[0];
EVT ResVT = getTLI()->getValueType(DL, RetTy, true);
EVT ArgVT = getTLI()->getValueType(DL, ArgTy, true);

// If we're not expanding the intrinsic then we assume this is cheap
// to implement.
if (!getTLI()->shouldExpandGetActiveLaneMask(ResVT, ArgVT))
return getTypeLegalizationCost(RetTy).first;

// Create the expanded types that will be used to calculate the uadd_sat
// operation.
Type *ExpRetTy =
VectorType::get(ArgTy, cast<VectorType>(RetTy)->getElementCount());
IntrinsicCostAttributes Attrs(Intrinsic::uadd_sat, ExpRetTy, {}, FMF);
InstructionCost Cost =
thisT()->getTypeBasedIntrinsicInstrCost(Attrs, CostKind);
Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, ExpRetTy, RetTy,
CmpInst::ICMP_ULT, CostKind);
return Cost;
}
case Intrinsic::abs:
ISD = ISD::ABS;
break;
Expand Down
24 changes: 12 additions & 12 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 @@ -958,16 +958,16 @@ define void @get_lane_mask() #0 {
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'get_lane_mask'
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
Expand All @@ -976,8 +976,8 @@ define void @get_lane_mask() #0 {
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
Expand Down
Loading