Skip to content
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

[AArch64] Consider histcnt smaller than i32 in the cost model #108521

Merged
merged 3 commits into from
Sep 19, 2024
Merged

[AArch64] Consider histcnt smaller than i32 in the cost model #108521

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
6ca9685
[AArch64] Consider histcnt smaller than i32 in the cost model
DevM-uk Sep 13, 2024
282b196
Add EltSize
SamTebbs33 Sep 17, 2024
6b1d6b2
Format
SamTebbs33 Sep 19, 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
30 changes: 18 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 @@ -517,25 +517,31 @@ static bool isUnpackedVectorVT(EVT VecVT) {
static InstructionCost getHistogramCost(const IntrinsicCostAttributes &ICA) {
Type *BucketPtrsTy = ICA.getArgTypes()[0]; // Type of vector of pointers
Type *EltTy = ICA.getArgTypes()[1]; // Type of bucket elements
unsigned TotalHistCnts = 1;

// Only allow (32b and 64b) integers or pointers for now...
if ((!EltTy->isIntegerTy() && !EltTy->isPointerTy()) ||
(EltTy->getScalarSizeInBits() != 32 &&
EltTy->getScalarSizeInBits() != 64))
unsigned EltSize = EltTy->getScalarSizeInBits();
// Only allow (up to 64b) integers or pointers
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd suggest adding a variable unsigned EltSize = EltTy->getScalarSizeInBits(); and using it both in the initial size check and the total size check below.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

if ((!EltTy->isIntegerTy() && !EltTy->isPointerTy()) || EltSize > 64)
return InstructionCost::getInvalid();

// FIXME: Hacky check for legal vector types. We can promote smaller types
// but we cannot legalize vectors via splitting for histcnt.
// FIXME: We should be able to generate histcnt for fixed-length vectors
// using ptrue with a specific VL.
if (VectorType *VTy = dyn_cast<VectorType>(BucketPtrsTy))
if ((VTy->getElementCount().getKnownMinValue() != 2 &&
VTy->getElementCount().getKnownMinValue() != 4) ||
VTy->getPrimitiveSizeInBits().getKnownMinValue() > 128 ||
!VTy->isScalableTy())
if (VectorType *VTy = dyn_cast<VectorType>(BucketPtrsTy)) {
unsigned EC = VTy->getElementCount().getKnownMinValue();
if (!isPowerOf2_64(EC) || !VTy->isScalableTy())
return InstructionCost::getInvalid();

return InstructionCost(BaseHistCntCost);
// HistCnt only supports 32b and 64b element types
unsigned LegalEltSize = EltSize <= 32 ? 32 : 64;

if (EC == 2 || (!LegalEltSize == 32 && EC == 4))
return InstructionCost(BaseHistCntCost);

unsigned NaturalVectorWidth = AArch64::SVEBitsPerBlock / LegalEltSize;
TotalHistCnts = EC / NaturalVectorWidth;
}

return InstructionCost(BaseHistCntCost * TotalHistCnts);
}

InstructionCost
Expand Down
18 changes: 9 additions & 9 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 @@ -971,26 +971,26 @@ define void @histogram_nxv4i32(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %m
ret void
}

define void @histogram_nxv8i16(<vscale x 8 x ptr> %buckets, <vscale x 8 x i1> %mask) {
define void @histogram_nxv8i16(<vscale x 8 x ptr> %buckets, <vscale x 8 x i1> %mask) #3 {
; CHECK-LABEL: 'histogram_nxv8i16'
; CHECK-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv8i16'
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
ret void
}

define void @histogram_nxv16i8(<vscale x 16 x ptr> %buckets, <vscale x 16 x i1> %mask) {
define void @histogram_nxv16i8(<vscale x 16 x ptr> %buckets, <vscale x 16 x i1> %mask) #3 {
; CHECK-LABEL: 'histogram_nxv16i8'
; CHECK-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv16i8'
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call void @llvm.experimental.vector.histogram.add.nxv16p0.i64(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
Expand Down Expand Up @@ -1049,13 +1049,13 @@ define void @histogram_v16i8(<16 x ptr> %buckets, <16 x i1> %mask) {
ret void
}

define void @histogram_nxv4i64(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %mask) {
define void @histogram_nxv4i64(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %mask) #3 {
; CHECK-LABEL: 'histogram_nxv4i64'
; CHECK-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv4i64'
; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
Expand Down
Loading