forked from OSchip/llvm-project
[AVX-512] Teach fast isel to use masked compare and movss for handling scalar cmp and select sequence when AVX-512 is enabled. This matches the behavior of normal isel.
llvm-svn: 288636
This commit is contained in:
Craig Topper
parent
227d4279a8
commit
7ef6ea324a
|
|
@ -170,6 +170,12 @@ private:
|
|||
|
||||
const MachineInstrBuilder &addFullAddress(const MachineInstrBuilder &MIB,
|
||||
X86AddressMode &AM);
|
||||
|
||||
unsigned fastEmitInst_rrrr(unsigned MachineInstOpcode,
|
||||
const TargetRegisterClass *RC, unsigned Op0,
|
||||
bool Op0IsKill, unsigned Op1, bool Op1IsKill,
|
||||
unsigned Op2, bool Op2IsKill, unsigned Op3,
|
||||
bool Op3IsKill);
|
||||
};
|
||||
|
||||
} // end anonymous namespace.
|
||||
|
|
@ -2180,9 +2186,36 @@ bool X86FastISel::X86FastEmitSSESelect(MVT RetVT, const Instruction *I) {
|
|||
|
||||
const TargetRegisterClass *RC = TLI.getRegClassFor(RetVT);
|
||||
unsigned ResultReg;
|
||||
|
||||
if (Subtarget->hasAVX()) {
|
||||
const TargetRegisterClass *FR32 = &X86::FR32RegClass;
|
||||
|
||||
if (Subtarget->hasAVX512()) {
|
||||
// If we have AVX512 we can use a mask compare and masked movss/sd.
|
||||
const TargetRegisterClass *VR128X = &X86::VR128XRegClass;
|
||||
const TargetRegisterClass *VK1 = &X86::VK1RegClass;
|
||||
|
||||
unsigned CmpOpcode =
|
||||
(RetVT.SimpleTy == MVT::f32) ? X86::VCMPSSZrr : X86::VCMPSDZrr;
|
||||
unsigned CmpReg = fastEmitInst_rri(CmpOpcode, VK1, CmpLHSReg, CmpLHSIsKill,
|
||||
CmpRHSReg, CmpRHSIsKill, CC);
|
||||
|
||||
// Need an IMPLICIT_DEF for the input that is used to generate the upper
|
||||
// bits of the result register since its not based on any of the inputs.
|
||||
unsigned ImplicitDefReg = createResultReg(VR128X);
|
||||
BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
|
||||
TII.get(TargetOpcode::IMPLICIT_DEF), ImplicitDefReg);
|
||||
|
||||
// Place RHSReg is the passthru of the masked movss/sd operation and put
|
||||
// LHS in the input. The mask input comes from the compare.
|
||||
unsigned MovOpcode =
|
||||
(RetVT.SimpleTy == MVT::f32) ? X86::VMOVSSZrrk : X86::VMOVSDZrrk;
|
||||
unsigned MovReg = fastEmitInst_rrrr(MovOpcode, VR128X, RHSReg, RHSIsKill,
|
||||
CmpReg, true, ImplicitDefReg, true,
|
||||
LHSReg, LHSIsKill);
|
||||
|
||||
ResultReg = createResultReg(RC);
|
||||
BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
|
||||
TII.get(TargetOpcode::COPY), ResultReg).addReg(MovReg);
|
||||
|
||||
} else if (Subtarget->hasAVX()) {
|
||||
const TargetRegisterClass *VR128 = &X86::VR128RegClass;
|
||||
|
||||
// If we have AVX, create 1 blendv instead of 3 logic instructions.
|
||||
|
|
@ -2195,7 +2228,7 @@ bool X86FastISel::X86FastEmitSSESelect(MVT RetVT, const Instruction *I) {
|
|||
unsigned BlendOpcode =
|
||||
(RetVT.SimpleTy == MVT::f32) ? X86::VBLENDVPSrr : X86::VBLENDVPDrr;
|
||||
|
||||
unsigned CmpReg = fastEmitInst_rri(CmpOpcode, FR32, CmpLHSReg, CmpLHSIsKill,
|
||||
unsigned CmpReg = fastEmitInst_rri(CmpOpcode, RC, CmpLHSReg, CmpLHSIsKill,
|
||||
CmpRHSReg, CmpRHSIsKill, CC);
|
||||
unsigned VBlendReg = fastEmitInst_rrr(BlendOpcode, VR128, RHSReg, RHSIsKill,
|
||||
LHSReg, LHSIsKill, CmpReg, true);
|
||||
|
|
@ -3849,6 +3882,38 @@ bool X86FastISel::tryToFoldLoadIntoMI(MachineInstr *MI, unsigned OpNo,
|
|||
return true;
|
||||
}
|
||||
|
||||
unsigned X86FastISel::fastEmitInst_rrrr(unsigned MachineInstOpcode,
|
||||
const TargetRegisterClass *RC,
|
||||
unsigned Op0, bool Op0IsKill,
|
||||
unsigned Op1, bool Op1IsKill,
|
||||
unsigned Op2, bool Op2IsKill,
|
||||
unsigned Op3, bool Op3IsKill) {
|
||||
const MCInstrDesc &II = TII.get(MachineInstOpcode);
|
||||
|
||||
unsigned ResultReg = createResultReg(RC);
|
||||
Op0 = constrainOperandRegClass(II, Op0, II.getNumDefs());
|
||||
Op1 = constrainOperandRegClass(II, Op1, II.getNumDefs() + 1);
|
||||
Op2 = constrainOperandRegClass(II, Op2, II.getNumDefs() + 2);
|
||||
Op2 = constrainOperandRegClass(II, Op2, II.getNumDefs() + 3);
|
||||
|
||||
if (II.getNumDefs() >= 1)
|
||||
BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, II, ResultReg)
|
||||
.addReg(Op0, getKillRegState(Op0IsKill))
|
||||
.addReg(Op1, getKillRegState(Op1IsKill))
|
||||
.addReg(Op2, getKillRegState(Op2IsKill))
|
||||
.addReg(Op3, getKillRegState(Op3IsKill));
|
||||
else {
|
||||
BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, II)
|
||||
.addReg(Op0, getKillRegState(Op0IsKill))
|
||||
.addReg(Op1, getKillRegState(Op1IsKill))
|
||||
.addReg(Op2, getKillRegState(Op2IsKill))
|
||||
.addReg(Op3, getKillRegState(Op3IsKill));
|
||||
BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
|
||||
TII.get(TargetOpcode::COPY), ResultReg).addReg(II.ImplicitDefs[0]);
|
||||
}
|
||||
return ResultReg;
|
||||
}
|
||||
|
||||
|
||||
namespace llvm {
|
||||
FastISel *X86::createFastISel(FunctionLoweringInfo &funcInfo,
|
||||
|
|
|
|||
|
|
@ -3,8 +3,8 @@
|
|||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -fast-isel -fast-isel-abort=1 | FileCheck %s --check-prefix=SSE
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s --check-prefix=AVX
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -fast-isel -fast-isel-abort=1 -mattr=avx | FileCheck %s --check-prefix=AVX
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512SLOW
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -fast-isel -fast-isel-abort=1 -mattr=avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512FAST
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512f | FileCheck %s --check-prefix=AVX512
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -fast-isel -fast-isel-abort=1 -mattr=avx512f | FileCheck %s --check-prefix=AVX512
|
||||
|
||||
; Test all cmp predicates that can be used with SSE.
|
||||
|
||||
|
|
@ -23,18 +23,12 @@ define float @select_fcmp_oeq_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_oeq_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpeqss %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_oeq_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpeqss %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_oeq_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpeqss %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp oeq float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -56,18 +50,12 @@ define double @select_fcmp_oeq_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_oeq_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpeqsd %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_oeq_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpeqsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_oeq_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpeqsd %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp oeq double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -90,18 +78,12 @@ define float @select_fcmp_ogt_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ogt_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpltss %xmm0, %xmm1, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ogt_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpltss %xmm0, %xmm1, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ogt_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpltss %xmm0, %xmm1, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ogt float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -124,18 +106,12 @@ define double @select_fcmp_ogt_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ogt_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpltsd %xmm0, %xmm1, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ogt_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpltsd %xmm0, %xmm1, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ogt_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpltsd %xmm0, %xmm1, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ogt double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -158,18 +134,12 @@ define float @select_fcmp_oge_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_oge_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpless %xmm0, %xmm1, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_oge_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpless %xmm0, %xmm1, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_oge_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpless %xmm0, %xmm1, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp oge float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -192,18 +162,12 @@ define double @select_fcmp_oge_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_oge_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmplesd %xmm0, %xmm1, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_oge_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmplesd %xmm0, %xmm1, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_oge_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmplesd %xmm0, %xmm1, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp oge double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -225,18 +189,12 @@ define float @select_fcmp_olt_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_olt_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpltss %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_olt_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpltss %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_olt_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpltss %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp olt float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -258,18 +216,12 @@ define double @select_fcmp_olt_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_olt_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpltsd %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_olt_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpltsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_olt_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpltsd %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp olt double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -291,18 +243,12 @@ define float @select_fcmp_ole_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ole_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpless %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ole_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpless %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ole_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpless %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ole float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -324,18 +270,12 @@ define double @select_fcmp_ole_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ole_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmplesd %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ole_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmplesd %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ole_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmplesd %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ole double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -357,18 +297,12 @@ define float @select_fcmp_ord_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ord_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpordss %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ord_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpordss %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ord_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpordss %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ord float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -390,18 +324,12 @@ define double @select_fcmp_ord_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ord_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpordsd %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ord_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpordsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ord_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpordsd %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ord double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -423,18 +351,12 @@ define float @select_fcmp_uno_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_uno_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpunordss %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_uno_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpunordss %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_uno_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpunordss %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp uno float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -456,18 +378,12 @@ define double @select_fcmp_uno_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_uno_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpunordsd %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_uno_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpunordsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_uno_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpunordsd %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp uno double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -489,18 +405,12 @@ define float @select_fcmp_ugt_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ugt_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpnless %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ugt_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpnless %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ugt_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpnless %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ugt float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -522,18 +432,12 @@ define double @select_fcmp_ugt_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ugt_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpnlesd %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ugt_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpnlesd %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ugt_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpnlesd %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ugt double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -555,18 +459,12 @@ define float @select_fcmp_uge_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_uge_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpnltss %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_uge_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpnltss %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_uge_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpnltss %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp uge float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -588,18 +486,12 @@ define double @select_fcmp_uge_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_uge_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpnltsd %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_uge_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpnltsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_uge_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpnltsd %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp uge double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -622,18 +514,12 @@ define float @select_fcmp_ult_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ult_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpnless %xmm0, %xmm1, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ult_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpnless %xmm0, %xmm1, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ult_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpnless %xmm0, %xmm1, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ult float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -656,18 +542,12 @@ define double @select_fcmp_ult_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ult_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpnlesd %xmm0, %xmm1, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ult_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpnlesd %xmm0, %xmm1, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ult_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpnlesd %xmm0, %xmm1, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ult double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -690,18 +570,12 @@ define float @select_fcmp_ule_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ule_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpnltss %xmm0, %xmm1, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ule_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpnltss %xmm0, %xmm1, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ule_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpnltss %xmm0, %xmm1, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ule float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -724,18 +598,12 @@ define double @select_fcmp_ule_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_ule_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpnltsd %xmm0, %xmm1, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_ule_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpnltsd %xmm0, %xmm1, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_ule_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpnltsd %xmm0, %xmm1, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp ule double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
@ -757,18 +625,12 @@ define float @select_fcmp_une_f32(float %a, float %b, float %c, float %d) {
|
|||
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_une_f32:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpneqss %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_une_f32:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpneqss %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_une_f32:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpneqss %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovss %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovaps %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp une float %a, %b
|
||||
%2 = select i1 %1, float %c, float %d
|
||||
|
|
@ -790,18 +652,12 @@ define double @select_fcmp_une_f64(double %a, double %b, double %c, double %d) {
|
|||
; AVX-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512SLOW-LABEL: select_fcmp_une_f64:
|
||||
; AVX512SLOW: # BB#0:
|
||||
; AVX512SLOW-NEXT: vcmpneqsd %xmm1, %xmm0, %k1
|
||||
; AVX512SLOW-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512SLOW-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512SLOW-NEXT: retq
|
||||
;
|
||||
; AVX512FAST-LABEL: select_fcmp_une_f64:
|
||||
; AVX512FAST: # BB#0:
|
||||
; AVX512FAST-NEXT: vcmpneqsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512FAST-NEXT: vblendvpd %xmm0, %xmm2, %xmm3, %xmm0
|
||||
; AVX512FAST-NEXT: retq
|
||||
; AVX512-LABEL: select_fcmp_une_f64:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vcmpneqsd %xmm1, %xmm0, %k1
|
||||
; AVX512-NEXT: vmovsd %xmm2, %xmm0, %xmm3 {%k1}
|
||||
; AVX512-NEXT: vmovapd %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
%1 = fcmp une double %a, %b
|
||||
%2 = select i1 %1, double %c, double %d
|
||||
|
|
|
|||
Loading…
Reference in New Issue