Skip to content

SimplifyLibCalls: Permit pow(2, x) -> ldexp(1, x) fold for vectors #92532

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
May 19, 2024
Merged

SimplifyLibCalls: Permit pow(2, x) -> ldexp(1, x) fold for vectors #92532

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
7 changes: 4 additions & 3 deletions llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2087,15 +2087,16 @@ Value *LibCallSimplifier::replacePowWithExp(CallInst *Pow, IRBuilderBase &B) {

AttributeList NoAttrs; // Attributes are only meaningful on the original call

const bool UseIntrinsic = Pow->doesNotAccessMemory();

// pow(2.0, itofp(x)) -> ldexp(1.0, x)
// TODO: This does not work for vectors because there is no ldexp intrinsic.
if (!Ty->isVectorTy() && match(Base, m_SpecificFP(2.0)) &&
if ((UseIntrinsic || !Ty->isVectorTy()) && match(Base, m_SpecificFP(2.0)) &&
(isa<SIToFPInst>(Expo) || isa<UIToFPInst>(Expo)) &&
hasFloatFn(M, TLI, Ty, LibFunc_ldexp, LibFunc_ldexpf, LibFunc_ldexpl)) {
if (Value *ExpoI = getIntToFPVal(Expo, B, TLI->getIntSize())) {
Constant *One = ConstantFP::get(Ty, 1.0);

if (Pow->doesNotAccessMemory()) {
if (UseIntrinsic) {
return copyFlags(*Pow, B.CreateIntrinsic(Intrinsic::ldexp,
{Ty, ExpoI->getType()},
{One, ExpoI}, Pow, "exp2"));
Expand Down
69 changes: 20 additions & 49 deletions llvm/test/Transforms/InstCombine/pow-to-ldexp.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,16 +144,10 @@ define half @pow_sitofp_f16_const_base_2(i32 %x) {
}

define <2 x float> @pow_sitofp_v2f32_const_base_2(<2 x i32> %x) {
; LDEXP-EXP2-LABEL: define <2 x float> @pow_sitofp_v2f32_const_base_2(
; LDEXP-EXP2-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-EXP2-NEXT: [[EXP2:%.*]] = tail call <2 x float> @llvm.ldexp.v2f32.v2i32(<2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x i32> [[X]])
; LDEXP-EXP2-NEXT: ret <2 x float> [[EXP2]]
;
; LDEXP-NOEXP2-LABEL: define <2 x float> @pow_sitofp_v2f32_const_base_2(
; LDEXP-NOEXP2-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-NOEXP2-NEXT: [[ITOFP:%.*]] = sitofp <2 x i32> [[X]] to <2 x float>
; LDEXP-NOEXP2-NEXT: [[POW:%.*]] = tail call <2 x float> @llvm.pow.v2f32(<2 x float> <float 2.000000e+00, float 2.000000e+00>, <2 x float> [[ITOFP]])
; LDEXP-NOEXP2-NEXT: ret <2 x float> [[POW]]
; LDEXP-LABEL: define <2 x float> @pow_sitofp_v2f32_const_base_2(
; LDEXP-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-NEXT: [[EXP2:%.*]] = tail call <2 x float> @llvm.ldexp.v2f32.v2i32(<2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x i32> [[X]])
; LDEXP-NEXT: ret <2 x float> [[EXP2]]
;
; NOLDEXP-LABEL: define <2 x float> @pow_sitofp_v2f32_const_base_2(
; NOLDEXP-SAME: <2 x i32> [[X:%.*]]) {
Expand Down Expand Up @@ -205,15 +199,10 @@ define <2 x float> @pow_sitofp_v2f32_const_base_mixed_2(<2 x i32> %x) {
}

define <2 x float> @pow_sitofp_v2f32_const_base_2__flags(<2 x i32> %x) {
; LDEXP-EXP2-LABEL: define <2 x float> @pow_sitofp_v2f32_const_base_2__flags(
; LDEXP-EXP2-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-EXP2-NEXT: [[EXP2:%.*]] = tail call nsz afn <2 x float> @llvm.ldexp.v2f32.v2i32(<2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x i32> [[X]])
; LDEXP-EXP2-NEXT: ret <2 x float> [[EXP2]]
;
; LDEXP-NOEXP2-LABEL: define <2 x float> @pow_sitofp_v2f32_const_base_2__flags(
; LDEXP-NOEXP2-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-NOEXP2-NEXT: [[POW:%.*]] = tail call nsz afn <2 x float> @llvm.powi.v2f32.v2i32(<2 x float> <float 2.000000e+00, float 2.000000e+00>, <2 x i32> [[X]])
; LDEXP-NOEXP2-NEXT: ret <2 x float> [[POW]]
; LDEXP-LABEL: define <2 x float> @pow_sitofp_v2f32_const_base_2__flags(
; LDEXP-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-NEXT: [[EXP2:%.*]] = tail call nsz afn <2 x float> @llvm.ldexp.v2f32.v2i32(<2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x i32> [[X]])
; LDEXP-NEXT: ret <2 x float> [[EXP2]]
;
; NOLDEXP-LABEL: define <2 x float> @pow_sitofp_v2f32_const_base_2__flags(
; NOLDEXP-SAME: <2 x i32> [[X:%.*]]) {
Expand All @@ -227,16 +216,10 @@ define <2 x float> @pow_sitofp_v2f32_const_base_2__flags(<2 x i32> %x) {
}

define <vscale x 4 x float> @pow_sitofp_nxv4f32_const_base_2(<vscale x 4 x i32> %x) {
; LDEXP-EXP2-LABEL: define <vscale x 4 x float> @pow_sitofp_nxv4f32_const_base_2(
; LDEXP-EXP2-SAME: <vscale x 4 x i32> [[X:%.*]]) {
; LDEXP-EXP2-NEXT: [[EXP2:%.*]] = tail call <vscale x 4 x float> @llvm.ldexp.nxv4f32.nxv4i32(<vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 1.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32> [[X]])
; LDEXP-EXP2-NEXT: ret <vscale x 4 x float> [[EXP2]]
;
; LDEXP-NOEXP2-LABEL: define <vscale x 4 x float> @pow_sitofp_nxv4f32_const_base_2(
; LDEXP-NOEXP2-SAME: <vscale x 4 x i32> [[X:%.*]]) {
; LDEXP-NOEXP2-NEXT: [[ITOFP:%.*]] = sitofp <vscale x 4 x i32> [[X]] to <vscale x 4 x float>
; LDEXP-NOEXP2-NEXT: [[POW:%.*]] = tail call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 2.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x float> [[ITOFP]])
; LDEXP-NOEXP2-NEXT: ret <vscale x 4 x float> [[POW]]
; LDEXP-LABEL: define <vscale x 4 x float> @pow_sitofp_nxv4f32_const_base_2(
; LDEXP-SAME: <vscale x 4 x i32> [[X:%.*]]) {
; LDEXP-NEXT: [[EXP2:%.*]] = tail call <vscale x 4 x float> @llvm.ldexp.nxv4f32.nxv4i32(<vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 1.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32> [[X]])
; LDEXP-NEXT: ret <vscale x 4 x float> [[EXP2]]
;
; NOLDEXP-LABEL: define <vscale x 4 x float> @pow_sitofp_nxv4f32_const_base_2(
; NOLDEXP-SAME: <vscale x 4 x i32> [[X:%.*]]) {
Expand All @@ -250,16 +233,10 @@ define <vscale x 4 x float> @pow_sitofp_nxv4f32_const_base_2(<vscale x 4 x i32>
}

define <2 x half> @pow_sitofp_v2f16_const_base_2(<2 x i32> %x) {
; LDEXP-EXP2-LABEL: define <2 x half> @pow_sitofp_v2f16_const_base_2(
; LDEXP-EXP2-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-EXP2-NEXT: [[EXP2:%.*]] = tail call <2 x half> @llvm.ldexp.v2f16.v2i32(<2 x half> <half 0xH3C00, half 0xH3C00>, <2 x i32> [[X]])
; LDEXP-EXP2-NEXT: ret <2 x half> [[EXP2]]
;
; LDEXP-NOEXP2-LABEL: define <2 x half> @pow_sitofp_v2f16_const_base_2(
; LDEXP-NOEXP2-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-NOEXP2-NEXT: [[ITOFP:%.*]] = sitofp <2 x i32> [[X]] to <2 x half>
; LDEXP-NOEXP2-NEXT: [[POW:%.*]] = tail call <2 x half> @llvm.pow.v2f16(<2 x half> <half 0xH4000, half 0xH4000>, <2 x half> [[ITOFP]])
; LDEXP-NOEXP2-NEXT: ret <2 x half> [[POW]]
; LDEXP-LABEL: define <2 x half> @pow_sitofp_v2f16_const_base_2(
; LDEXP-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-NEXT: [[EXP2:%.*]] = tail call <2 x half> @llvm.ldexp.v2f16.v2i32(<2 x half> <half 0xH3C00, half 0xH3C00>, <2 x i32> [[X]])
; LDEXP-NEXT: ret <2 x half> [[EXP2]]
;
; NOLDEXP-LABEL: define <2 x half> @pow_sitofp_v2f16_const_base_2(
; NOLDEXP-SAME: <2 x i32> [[X:%.*]]) {
Expand All @@ -273,16 +250,10 @@ define <2 x half> @pow_sitofp_v2f16_const_base_2(<2 x i32> %x) {
}

define <2 x double> @pow_sitofp_v2f64_const_base_2(<2 x i32> %x) {
; LDEXP-EXP2-LABEL: define <2 x double> @pow_sitofp_v2f64_const_base_2(
; LDEXP-EXP2-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-EXP2-NEXT: [[EXP2:%.*]] = tail call <2 x double> @llvm.ldexp.v2f64.v2i32(<2 x double> <double 1.000000e+00, double 1.000000e+00>, <2 x i32> [[X]])
; LDEXP-EXP2-NEXT: ret <2 x double> [[EXP2]]
;
; LDEXP-NOEXP2-LABEL: define <2 x double> @pow_sitofp_v2f64_const_base_2(
; LDEXP-NOEXP2-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-NOEXP2-NEXT: [[ITOFP:%.*]] = sitofp <2 x i32> [[X]] to <2 x double>
; LDEXP-NOEXP2-NEXT: [[POW:%.*]] = tail call <2 x double> @llvm.pow.v2f64(<2 x double> <double 2.000000e+00, double 2.000000e+00>, <2 x double> [[ITOFP]])
; LDEXP-NOEXP2-NEXT: ret <2 x double> [[POW]]
; LDEXP-LABEL: define <2 x double> @pow_sitofp_v2f64_const_base_2(
; LDEXP-SAME: <2 x i32> [[X:%.*]]) {
; LDEXP-NEXT: [[EXP2:%.*]] = tail call <2 x double> @llvm.ldexp.v2f64.v2i32(<2 x double> <double 1.000000e+00, double 1.000000e+00>, <2 x i32> [[X]])
; LDEXP-NEXT: ret <2 x double> [[EXP2]]
;
; NOLDEXP-LABEL: define <2 x double> @pow_sitofp_v2f64_const_base_2(
; NOLDEXP-SAME: <2 x i32> [[X:%.*]]) {
Expand Down
Loading