Skip to content

[X86] Lower mathlib call ldexp into scalef when avx512 is enabled #166839

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

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
+326 −1,743
Open

[X86] Lower mathlib call ldexp into scalef when avx512 is enabled #166839

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
9f7bddb
[X86] Lower mathlib call ldexp into scalef when avx512 is enabled #16…
KavinTheG Nov 6, 2025
484cea4
Widen 128/256 bit vector types when AVX512VL is not available.
KavinTheG Nov 8, 2025
8649bce
Added fp16 vector handling to LowerFLDEXP.
KavinTheG Nov 12, 2025
1806c40
Call SCALEF instead of SCALEFS for v4f32/v2f64 and refactored code.
KavinTheG Nov 14, 2025
c30244b
Minor refactoring.
KavinTheG Nov 17, 2025
e1bcedc
Ensure Exp is type integer after switch statement.
KavinTheG Nov 19, 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
74 changes: 73 additions & 1 deletion llvm/lib/Target/X86/X86ISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2101,6 +2101,11 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
// These operations are handled on non-VLX by artificially widening in
// isel patterns.

for (MVT VT : {MVT::f16, MVT::f32, MVT::f64, MVT::v8f16, MVT::v4f32,
MVT::v2f64, MVT::v16f16, MVT::v8f32, MVT::v4f64, MVT::v32f16,
MVT::v16f32, MVT::v8f64})
setOperationAction(ISD::FLDEXP, VT, Custom);

setOperationAction(ISD::STRICT_FP_TO_UINT, MVT::v8i32, Custom);
setOperationAction(ISD::STRICT_FP_TO_UINT, MVT::v4i32, Custom);
setOperationAction(ISD::STRICT_FP_TO_UINT, MVT::v2i32, Custom);
Expand Down Expand Up @@ -19149,6 +19154,72 @@ SDValue X86TargetLowering::LowerINSERT_VECTOR_ELT(SDValue Op,
return SDValue();
}

static SDValue LowerFLDEXP(SDValue Op, const X86Subtarget &Subtarget,
SelectionDAG &DAG) {
SDLoc DL(Op);
SDValue X = Op.getOperand(0);
MVT XTy = X.getSimpleValueType();
SDValue Exp = Op.getOperand(1);

switch (XTy.SimpleTy) {
default:
return SDValue();
case MVT::f16:
if (!Subtarget.hasFP16())
X = DAG.getFPExtendOrRound(X, DL, MVT::f32);
[[fallthrough]];
case MVT::f32:
case MVT::f64: {
MVT VT = MVT::getVectorVT(X.getSimpleValueType(),
128 / X.getSimpleValueType().getSizeInBits());
Exp = DAG.getNode(ISD::SINT_TO_FP, DL, X.getValueType(), Exp);
SDValue VX = DAG.getNode(ISD::SCALAR_TO_VECTOR, DL, VT, X);
SDValue VExp = DAG.getNode(ISD::SCALAR_TO_VECTOR, DL, VT, Exp);
SDValue Scalefs = DAG.getNode(X86ISD::SCALEFS, DL, VT, VX, VExp);
SDValue Final = DAG.getExtractVectorElt(DL, X.getValueType(), Scalefs, 0);
return DAG.getFPExtendOrRound(Final, DL, XTy);
}
case MVT::v4f32:
case MVT::v2f64:
case MVT::v8f32:
case MVT::v4f64:
case MVT::v16f32:
case MVT::v8f64:
if (XTy.getSizeInBits() == 512 || Subtarget.hasVLX()) {
Exp = DAG.getNode(ISD::SINT_TO_FP, DL, XTy, Exp);
return DAG.getNode(X86ISD::SCALEF, DL, XTy, X, Exp);
}
break;
case MVT::v8f16:
case MVT::v16f16:
if (Subtarget.hasFP16()) {
if (Subtarget.hasVLX()) {
Exp = DAG.getNode(ISD::SINT_TO_FP, DL, XTy, Exp);
return DAG.getNode(X86ISD::SCALEF, DL, XTy, X, Exp);
}
break;
}
X = DAG.getFPExtendOrRound(X, DL, XTy.changeVectorElementType(MVT::f32));
Exp = DAG.getSExtOrTrunc(Exp, DL,
X.getSimpleValueType().changeTypeToInteger());
break;
case MVT::v32f16:
if (Subtarget.hasFP16()) {
Exp = DAG.getNode(ISD::SINT_TO_FP, DL, XTy, Exp);
return DAG.getNode(X86ISD::SCALEF, DL, XTy, X, Exp);
}
return splitVectorOp(Op, DAG, DL);
}
SDValue WideX = widenSubVector(X, true, Subtarget, DAG, DL, 512);
SDValue WideExp = widenSubVector(Exp, true, Subtarget, DAG, DL, 512);
Exp = DAG.getNode(ISD::SINT_TO_FP, DL, WideExp.getSimpleValueType(), Exp);
SDValue Scalef =
DAG.getNode(X86ISD::SCALEF, DL, WideX.getValueType(), WideX, WideExp);
SDValue Final =
DAG.getExtractSubvector(DL, X.getSimpleValueType(), Scalef, 0);
return DAG.getFPExtendOrRound(Final, DL, XTy);
}

static SDValue LowerSCALAR_TO_VECTOR(SDValue Op, const X86Subtarget &Subtarget,
SelectionDAG &DAG) {
SDLoc dl(Op);
Expand Down Expand Up @@ -33681,7 +33752,8 @@ SDValue X86TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
case ISD::ADDRSPACECAST: return LowerADDRSPACECAST(Op, DAG);
case X86ISD::CVTPS2PH: return LowerCVTPS2PH(Op, DAG);
case ISD::PREFETCH: return LowerPREFETCH(Op, Subtarget, DAG);
// clang-format on
case ISD::FLDEXP: return LowerFLDEXP(Op, Subtarget, DAG);
// clang-format on
}
}

Expand Down
158 changes: 53 additions & 105 deletions llvm/test/CodeGen/X86/fold-int-pow2-with-fmul-or-fdiv.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,38 +79,54 @@ define <4 x float> @fmul_pow2_ldexp_4xfloat(<4 x i32> %i) {
; CHECK-SSE-NEXT: .cfi_def_cfa_offset 8
; CHECK-SSE-NEXT: retq
;
; CHECK-AVX-LABEL: fmul_pow2_ldexp_4xfloat:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: subq $40, %rsp
; CHECK-AVX-NEXT: .cfi_def_cfa_offset 48
; CHECK-AVX-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX-NEXT: vextractps $1, %xmm0, %edi
; CHECK-AVX-NEXT: vmovss {{.*#+}} xmm0 = [9.0E+0,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX-NEXT: callq ldexpf@PLT
; CHECK-AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-AVX-NEXT: vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-AVX-NEXT: vmovd %xmm0, %edi
; CHECK-AVX-NEXT: vmovss {{.*#+}} xmm0 = [9.0E+0,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX-NEXT: callq ldexpf@PLT
; CHECK-AVX-NEXT: vinsertps $16, (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[2,3]
; CHECK-AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-AVX-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-AVX-NEXT: vextractps $2, %xmm0, %edi
; CHECK-AVX-NEXT: vmovss {{.*#+}} xmm0 = [9.0E+0,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX-NEXT: callq ldexpf@PLT
; CHECK-AVX-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; CHECK-AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-AVX-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-AVX-NEXT: vextractps $3, %xmm0, %edi
; CHECK-AVX-NEXT: vmovss {{.*#+}} xmm0 = [9.0E+0,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX-NEXT: callq ldexpf@PLT
; CHECK-AVX-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
; CHECK-AVX-NEXT: addq $40, %rsp
; CHECK-AVX-NEXT: .cfi_def_cfa_offset 8
; CHECK-AVX-NEXT: retq
; CHECK-AVX2-LABEL: fmul_pow2_ldexp_4xfloat:
; CHECK-AVX2: # %bb.0:
; CHECK-AVX2-NEXT: subq $40, %rsp
; CHECK-AVX2-NEXT: .cfi_def_cfa_offset 48
; CHECK-AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX2-NEXT: vextractps $1, %xmm0, %edi
; CHECK-AVX2-NEXT: vmovss {{.*#+}} xmm0 = [9.0E+0,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX2-NEXT: callq ldexpf@PLT
; CHECK-AVX2-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-AVX2-NEXT: vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-AVX2-NEXT: vmovd %xmm0, %edi
; CHECK-AVX2-NEXT: vmovss {{.*#+}} xmm0 = [9.0E+0,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX2-NEXT: callq ldexpf@PLT
; CHECK-AVX2-NEXT: vinsertps $16, (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX2-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[2,3]
; CHECK-AVX2-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-AVX2-NEXT: vextractps $2, %xmm0, %edi
; CHECK-AVX2-NEXT: vmovss {{.*#+}} xmm0 = [9.0E+0,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX2-NEXT: callq ldexpf@PLT
; CHECK-AVX2-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-AVX2-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; CHECK-AVX2-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-AVX2-NEXT: vextractps $3, %xmm0, %edi
; CHECK-AVX2-NEXT: vmovss {{.*#+}} xmm0 = [9.0E+0,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX2-NEXT: callq ldexpf@PLT
; CHECK-AVX2-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-AVX2-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
; CHECK-AVX2-NEXT: addq $40, %rsp
; CHECK-AVX2-NEXT: .cfi_def_cfa_offset 8
; CHECK-AVX2-NEXT: retq
;
; CHECK-ONLY-AVX512F-LABEL: fmul_pow2_ldexp_4xfloat:
; CHECK-ONLY-AVX512F: # %bb.0:
; CHECK-ONLY-AVX512F-NEXT: vbroadcastss {{.*#+}} xmm1 = [9.0E+0,9.0E+0,9.0E+0,9.0E+0]
; CHECK-ONLY-AVX512F-NEXT: vmovaps %xmm0, %xmm0
; CHECK-ONLY-AVX512F-NEXT: vscalefps %zmm0, %zmm1, %zmm0
; CHECK-ONLY-AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; CHECK-ONLY-AVX512F-NEXT: vzeroupper
; CHECK-ONLY-AVX512F-NEXT: retq
;
; CHECK-SKX-LABEL: fmul_pow2_ldexp_4xfloat:
; CHECK-SKX: # %bb.0:
; CHECK-SKX-NEXT: vcvtdq2ps %xmm0, %xmm0
; CHECK-SKX-NEXT: vbroadcastss {{.*#+}} xmm1 = [9.0E+0,9.0E+0,9.0E+0,9.0E+0]
; CHECK-SKX-NEXT: vscalefps %xmm0, %xmm1, %xmm0
; CHECK-SKX-NEXT: retq
%r = call <4 x float> @llvm.ldexp.v4f32.v4i32(<4 x float> <float 9.000000e+00, float 9.000000e+00, float 9.000000e+00, float 9.000000e+00>, <4 x i32> %i)
ret <4 x float> %r
}
Expand Down Expand Up @@ -562,79 +578,11 @@ define <8 x half> @fmul_pow2_ldexp_8xhalf(<8 x i16> %i) {
;
; CHECK-AVX512F-LABEL: fmul_pow2_ldexp_8xhalf:
; CHECK-AVX512F: # %bb.0:
; CHECK-AVX512F-NEXT: subq $72, %rsp
; CHECK-AVX512F-NEXT: .cfi_def_cfa_offset 80
; CHECK-AVX512F-NEXT: vmovdqa %xmm0, (%rsp) # 16-byte Spill
; CHECK-AVX512F-NEXT: vpextrw $7, %xmm0, %eax
; CHECK-AVX512F-NEXT: movswl %ax, %edi
; CHECK-AVX512F-NEXT: vmovss {{.*#+}} xmm0 = [8.192E+3,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX512F-NEXT: callq ldexpf@PLT
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %xmm0, %xmm0
; CHECK-AVX512F-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX512F-NEXT: vmovdqa (%rsp), %xmm0 # 16-byte Reload
; CHECK-AVX512F-NEXT: vpextrw $6, %xmm0, %eax
; CHECK-AVX512F-NEXT: movswl %ax, %edi
; CHECK-AVX512F-NEXT: vmovss {{.*#+}} xmm0 = [8.192E+3,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX512F-NEXT: callq ldexpf@PLT
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %xmm0, %xmm0
; CHECK-AVX512F-NEXT: vpunpcklwd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX512F-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1],xmm0[2],mem[2],xmm0[3],mem[3]
; CHECK-AVX512F-NEXT: vmovdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX512F-NEXT: vmovdqa (%rsp), %xmm0 # 16-byte Reload
; CHECK-AVX512F-NEXT: vpextrw $5, %xmm0, %eax
; CHECK-AVX512F-NEXT: movswl %ax, %edi
; CHECK-AVX512F-NEXT: vmovss {{.*#+}} xmm0 = [8.192E+3,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX512F-NEXT: callq ldexpf@PLT
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %xmm0, %xmm0
; CHECK-AVX512F-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX512F-NEXT: vmovdqa (%rsp), %xmm0 # 16-byte Reload
; CHECK-AVX512F-NEXT: vpextrw $4, %xmm0, %eax
; CHECK-AVX512F-NEXT: movswl %ax, %edi
; CHECK-AVX512F-NEXT: vmovss {{.*#+}} xmm0 = [8.192E+3,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX512F-NEXT: callq ldexpf@PLT
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %xmm0, %xmm0
; CHECK-AVX512F-NEXT: vpunpcklwd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX512F-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1],xmm0[2],mem[2],xmm0[3],mem[3]
; CHECK-AVX512F-NEXT: vpunpckldq {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX512F-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
; CHECK-AVX512F-NEXT: vmovdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX512F-NEXT: vmovdqa (%rsp), %xmm0 # 16-byte Reload
; CHECK-AVX512F-NEXT: vpextrw $3, %xmm0, %eax
; CHECK-AVX512F-NEXT: movswl %ax, %edi
; CHECK-AVX512F-NEXT: vmovss {{.*#+}} xmm0 = [8.192E+3,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX512F-NEXT: callq ldexpf@PLT
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %xmm0, %xmm0
; CHECK-AVX512F-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX512F-NEXT: vmovdqa (%rsp), %xmm0 # 16-byte Reload
; CHECK-AVX512F-NEXT: vpextrw $2, %xmm0, %eax
; CHECK-AVX512F-NEXT: movswl %ax, %edi
; CHECK-AVX512F-NEXT: vmovss {{.*#+}} xmm0 = [8.192E+3,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX512F-NEXT: callq ldexpf@PLT
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %xmm0, %xmm0
; CHECK-AVX512F-NEXT: vpunpcklwd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX512F-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1],xmm0[2],mem[2],xmm0[3],mem[3]
; CHECK-AVX512F-NEXT: vmovdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX512F-NEXT: vmovdqa (%rsp), %xmm0 # 16-byte Reload
; CHECK-AVX512F-NEXT: vpextrw $1, %xmm0, %eax
; CHECK-AVX512F-NEXT: movswl %ax, %edi
; CHECK-AVX512F-NEXT: vmovss {{.*#+}} xmm0 = [8.192E+3,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX512F-NEXT: callq ldexpf@PLT
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %xmm0, %xmm0
; CHECK-AVX512F-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-AVX512F-NEXT: vmovdqa (%rsp), %xmm0 # 16-byte Reload
; CHECK-AVX512F-NEXT: vmovd %xmm0, %eax
; CHECK-AVX512F-NEXT: movswl %ax, %edi
; CHECK-AVX512F-NEXT: vmovss {{.*#+}} xmm0 = [8.192E+3,0.0E+0,0.0E+0,0.0E+0]
; CHECK-AVX512F-NEXT: callq ldexpf@PLT
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %xmm0, %xmm0
; CHECK-AVX512F-NEXT: vpunpcklwd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX512F-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1],xmm0[2],mem[2],xmm0[3],mem[3]
; CHECK-AVX512F-NEXT: vpunpckldq {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX512F-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
; CHECK-AVX512F-NEXT: vpunpcklqdq {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; CHECK-AVX512F-NEXT: # xmm0 = xmm0[0],mem[0]
; CHECK-AVX512F-NEXT: addq $72, %rsp
; CHECK-AVX512F-NEXT: .cfi_def_cfa_offset 8
; CHECK-AVX512F-NEXT: vbroadcastss {{.*#+}} ymm1 = [8.192E+3,8.192E+3,8.192E+3,8.192E+3,8.192E+3,8.192E+3,8.192E+3,8.192E+3]
; CHECK-AVX512F-NEXT: vpmovsxwd %xmm0, %ymm0
; CHECK-AVX512F-NEXT: vscalefps %zmm0, %zmm1, %zmm0
; CHECK-AVX512F-NEXT: vcvtps2ph $4, %ymm0, %xmm0
; CHECK-AVX512F-NEXT: vzeroupper
; CHECK-AVX512F-NEXT: retq
%r = call <8 x half> @llvm.ldexp.v8f16.v8i16(<8 x half> <half 0xH7000, half 0xH7000, half 0xH7000, half 0xH7000, half 0xH7000, half 0xH7000, half 0xH7000, half 0xH7000>, <8 x i16> %i)
ret <8 x half> %r
Expand Down
Loading