Index: lib/Target/X86/X86FastISel.cpp =================================================================== --- lib/Target/X86/X86FastISel.cpp +++ lib/Target/X86/X86FastISel.cpp @@ -2009,10 +2009,25 @@ if (V->getType()->isFloatTy()) { unsigned OpReg = getRegForValue(V); if (OpReg == 0) return false; - unsigned ResultReg = createResultReg(&X86::FR64RegClass); - BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, - TII.get(X86::CVTSS2SDrr), ResultReg) - .addReg(OpReg); + // Avoid introducing a legacy SSE instruction if the target has AVX. + bool HasAVX = Subtarget->hasAVX(); + unsigned Opc = HasAVX ? X86::VCVTSS2SDrr : X86::CVTSS2SDrr; + + unsigned ImplicitDefReg = 0; + const TargetRegisterClass *RC = &X86::FR64RegClass; + if (HasAVX) { + ImplicitDefReg = createResultReg(RC); + BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, + TII.get(TargetOpcode::IMPLICIT_DEF), ImplicitDefReg); + } + + MachineInstrBuilder MIB; + unsigned ResultReg = createResultReg(RC); + MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), + ResultReg); + if (ImplicitDefReg) + MIB.addReg(ImplicitDefReg); + MIB.addReg(OpReg); updateValueMap(I, ResultReg); return true; } @@ -2022,19 +2037,32 @@ } bool X86FastISel::X86SelectFPTrunc(const Instruction *I) { - if (X86ScalarSSEf64) { - if (I->getType()->isFloatTy()) { - const Value *V = I->getOperand(0); - if (V->getType()->isDoubleTy()) { - unsigned OpReg = getRegForValue(V); - if (OpReg == 0) return false; - unsigned ResultReg = createResultReg(&X86::FR32RegClass); + if (X86ScalarSSEf64 && I->getType()->isFloatTy()) { + const Value *V = I->getOperand(0); + if (V->getType()->isDoubleTy()) { + unsigned OpReg = getRegForValue(V); + if (OpReg == 0) return false; + // Avoid introducing a legacy SSE instruction if the target has AVX. + bool HasAVX = Subtarget->hasAVX(); + unsigned Opc = HasAVX ? X86::VCVTSD2SSrr : X86::CVTSD2SSrr; + + unsigned ImplicitDefReg = 0; + const TargetRegisterClass *RC = &X86::FR32RegClass; + if (HasAVX) { + ImplicitDefReg = createResultReg(RC); BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, - TII.get(X86::CVTSD2SSrr), ResultReg) - .addReg(OpReg); - updateValueMap(I, ResultReg); - return true; + TII.get(TargetOpcode::IMPLICIT_DEF), ImplicitDefReg); } + + MachineInstrBuilder MIB; + unsigned ResultReg = createResultReg(RC); + MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), + ResultReg); + if (ImplicitDefReg) + MIB.addReg(ImplicitDefReg); + MIB.addReg(OpReg); + updateValueMap(I, ResultReg); + return true; } } Index: test/CodeGen/X86/fast-isel-fptrunc-fpext.ll =================================================================== --- test/CodeGen/X86/fast-isel-fptrunc-fpext.ll +++ test/CodeGen/X86/fast-isel-fptrunc-fpext.ll @@ -0,0 +1,63 @@ +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 -fast-isel | FileCheck %s --check-prefix=ALL --check-prefix=SSE +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx -fast-isel | FileCheck %s --check-prefix=ALL --check-prefix=AVX +; +; Verify that fast-isel doesn't select legacy SSE instructions on targets that +; feature AVX. +; +; Test cases are obtained from the following code snippet: +; /// +; double single_to_double_rr(float x) { +; return (double)x; +; } +; float double_to_single_rr(double x) { +; return (float)x; +; } +; double single_to_double_rm(float *x) { +; return (double)*x; +; } +; float double_to_single_rm(double *x) { +; return (float)*x; +; } +; /// + +define double @single_to_double_rr(float %x) { +; ALL-LABEL: single_to_double_rr: +; SSE: cvtss2sd %xmm0, %xmm0 +; AVX: vcvtss2sd %xmm0, %xmm0, %xmm0 +; ALL-NEXT: ret +entry: + %conv = fpext float %x to double + ret double %conv +} + +define float @double_to_single_rr(double %x) { +; ALL-LABEL: double_to_single_rr: +; SSE: cvtsd2ss %xmm0, %xmm0 +; AVX: vcvtsd2ss %xmm0, %xmm0, %xmm0 +; ALL-NEXT: ret +entry: + %conv = fptrunc double %x to float + ret float %conv +} + +define double @single_to_double_rm(float* %x) { +; ALL-LABEL: single_to_double_rm: +; SSE: cvtss2sd (%rdi), %xmm0 +; AVX: vcvtss2sd (%rdi), %xmm0, %xmm0 +; ALL-NEXT: ret +entry: + %0 = load float* %x, align 4 + %conv = fpext float %0 to double + ret double %conv +} + +define float @double_to_single_rm(double* %x) { +; ALL-LABEL: double_to_single_rm: +; SSE: cvtsd2ss (%rdi), %xmm0 +; AVX: vcvtsd2ss (%rdi), %xmm0, %xmm0 +; ALL-NEXT: ret +entry: + %0 = load double* %x, align 8 + %conv = fptrunc double %0 to float + ret float %conv +}