Skip to content

[RISCV][CostModel] Add cost for fabs/fsqrt of type bf16/f16 #121685

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

Closed
wants to merge 1 commit into from
Closed

[RISCV][CostModel] Add cost for fabs/fsqrt of type bf16/f16 #121685

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
60 changes: 49 additions & 11 deletions llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1035,21 +1035,59 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
}
break;
}
case Intrinsic::fabs:
case Intrinsic::fabs: {
auto LT = getTypeLegalizationCost(RetTy);
if (ST->hasVInstructions() && LT.second.isVector()) {
// lui a0, 8
// addi a0, a0, -1
// vsetvli a1, zero, e16, m1, ta, ma
// vand.vx v8, v8, a0
// f16 with zvfhmin and bf16 with zvfhbmin
if (LT.second.getVectorElementType() == MVT::bf16 ||
(LT.second.getVectorElementType() == MVT::f16 &&
!ST->hasVInstructionsF16()))
return LT.first * getRISCVInstructionCost(RISCV::VAND_VX, LT.second,
CostKind) +
2;
else
return LT.first *
getRISCVInstructionCost(RISCV::VFSGNJX_VV, LT.second, CostKind);
}
break;
}
case Intrinsic::sqrt: {
auto LT = getTypeLegalizationCost(RetTy);
// TODO: add f16/bf16, bf16 with zvfbfmin && f16 with zvfhmin
auto NVT = LT.second;
if (ST->hasVInstructions() && LT.second.isVector()) {
unsigned Op;
switch (ICA.getID()) {
case Intrinsic::fabs:
Op = RISCV::VFSGNJX_VV;
break;
case Intrinsic::sqrt:
Op = RISCV::VFSQRT_V;
break;
SmallVector<unsigned, 3> Opcodes;
// f16 with zvfhmin and bf16 with zvfbfmin and the type of nxv32[b]f16
// will be spilt.
if (LT.second.getVectorElementType() == MVT::bf16) {
if (LT.second == MVT::nxv32bf16) {
Opcodes = {RISCV::VFWCVTBF16_F_F_V, RISCV::VFWCVTBF16_F_F_V,
RISCV::VFSQRT_V, RISCV::VFSQRT_V,
RISCV::VFNCVTBF16_F_F_W, RISCV::VFNCVTBF16_F_F_W};
NVT = MVT::nxv16f32;
} else {
Opcodes = {RISCV::VFWCVTBF16_F_F_V, RISCV::VFSQRT_V,
RISCV::VFNCVTBF16_F_F_W};
NVT = TLI->getTypeToPromoteTo(ISD::FSQRT, NVT);
}
} else if (LT.second.getVectorElementType() == MVT::f16 &&
!ST->hasVInstructionsF16()) {
if (LT.second == MVT::nxv32f16) {
Opcodes = {RISCV::VFWCVT_F_F_V, RISCV::VFWCVT_F_F_V,
RISCV::VFSQRT_V, RISCV::VFSQRT_V,
RISCV::VFNCVT_F_F_W, RISCV::VFNCVT_F_F_W};
NVT = MVT::nxv16f32;
} else {
Opcodes = {RISCV::VFWCVT_F_F_V, RISCV::VFSQRT_V, RISCV::VFNCVT_F_F_W};
NVT = TLI->getTypeToPromoteTo(ISD::FSQRT, NVT);
}
} else {
Opcodes = {RISCV::VFSQRT_V};
}
return LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
return LT.first * getRISCVInstructionCost(Opcodes, NVT, CostKind);
}
break;
}
Expand Down
50 changes: 31 additions & 19 deletions llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,14 +5,14 @@
define void @fabs() {
; CHECK-LABEL: 'fabs'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call bfloat @llvm.fabs.bf16(bfloat undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call float @llvm.fabs.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
Expand Down Expand Up @@ -66,17 +66,29 @@ define void @fabs() {
}

define void @fabs_f16() {
; CHECK-LABEL: 'fabs_f16'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
; ZVFH-LABEL: 'fabs_f16'
; ZVFH-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVFHMIN-LABEL: 'fabs_f16'
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call half @llvm.fabs.f16(half undef)
call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
Expand Down
Loading
Loading