Index: lib/Target/X86/X86InstrInfo.cpp =================================================================== --- lib/Target/X86/X86InstrInfo.cpp +++ lib/Target/X86/X86InstrInfo.cpp @@ -4379,22 +4379,36 @@ static bool hasPartialRegUpdate(unsigned Opcode) { switch (Opcode) { case X86::CVTSI2SSrr: + case X86::CVTSI2SSrm: case X86::CVTSI2SS64rr: + case X86::CVTSI2SS64rm: case X86::CVTSI2SDrr: + case X86::CVTSI2SDrm: case X86::CVTSI2SD64rr: + case X86::CVTSI2SD64rm: case X86::CVTSD2SSrr: + case X86::CVTSD2SSrm: case X86::Int_CVTSD2SSrr: + case X86::Int_CVTSD2SSrm: case X86::CVTSS2SDrr: + case X86::CVTSS2SDrm: case X86::Int_CVTSS2SDrr: + case X86::Int_CVTSS2SDrm: case X86::RCPSSr: + case X86::RCPSSm: case X86::RCPSSr_Int: + case X86::RCPSSm_Int: case X86::ROUNDSDr: + case X86::ROUNDSDm: case X86::ROUNDSDr_Int: case X86::ROUNDSSr: + case X86::ROUNDSSm: case X86::ROUNDSSr_Int: case X86::RSQRTSSr: + case X86::RSQRTSSm: case X86::RSQRTSSr_Int: case X86::SQRTSSr: + case X86::SQRTSSm: case X86::SQRTSSr_Int: return true; } Index: test/CodeGen/X86/sse-domains.ll =================================================================== --- test/CodeGen/X86/sse-domains.ll +++ test/CodeGen/X86/sse-domains.ll @@ -85,3 +85,59 @@ %sub = fsub float %s1.0.lcssa, %s2.0.lcssa ret float %sub } + +; This loop contains a cvtsi2sd instruction that has a loop-carried +; false dependency on an xmm that is modified by other scalar instructions +; that follow it in the loop. Additionally, the source of convert is a +; memory operand. Verify the execution dependency fix pass breaks this +; dependency by inserting a xor before the convert. +@x = common global [1024 x double] zeroinitializer, align 16 +@y = common global [1024 x double] zeroinitializer, align 16 +@z = common global [1024 x double] zeroinitializer, align 16 +@w = common global [1024 x double] zeroinitializer, align 16 +@v = common global [1024 x i32] zeroinitializer, align 16 + +define void @f3() { +entry: + br label %for.cond1.preheader + +for.cond1.preheader: ; preds = %for.inc14, %entry + %i.025 = phi i32 [ 0, %entry ], [ %inc15, %for.inc14 ] + br label %for.body3 + +for.body3: + %indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body3 ] + %arrayidx = getelementptr inbounds [1024 x i32]* @v, i64 0, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %conv = sitofp i32 %0 to double + %arrayidx5 = getelementptr inbounds [1024 x double]* @x, i64 0, i64 %indvars.iv + %1 = load double* %arrayidx5, align 8 + %mul = fmul double %conv, %1 + %arrayidx7 = getelementptr inbounds [1024 x double]* @y, i64 0, i64 %indvars.iv + %2 = load double* %arrayidx7, align 8 + %mul8 = fmul double %mul, %2 + %arrayidx10 = getelementptr inbounds [1024 x double]* @z, i64 0, i64 %indvars.iv + %3 = load double* %arrayidx10, align 8 + %mul11 = fmul double %mul8, %3 + %arrayidx13 = getelementptr inbounds [1024 x double]* @w, i64 0, i64 %indvars.iv + store double %mul11, double* %arrayidx13, align 8 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 1024 + br i1 %exitcond, label %for.inc14, label %for.body3 + +for.inc14: ; preds = %for.body3 + %inc15 = add nsw i32 %i.025, 1 + %exitcond26 = icmp eq i32 %inc15, 100000 + br i1 %exitcond26, label %for.end16, label %for.cond1.preheader + +for.end16: ; preds = %for.inc14 + ret void + +;CHECK-LABEL:@f3 +;CHECK: xorps [[XMM0:%xmm[0-9]+]], [[XMM0]] +;CHECK-NEXT: cvtsi2sdl {{.*}}, [[XMM0]] +;CHECK-NEXT: mulsd {{.*}}, [[XMM0]] +;CHECK-NEXT: mulsd {{.*}}, [[XMM0]] +;CHECK-NEXT: mulsd {{.*}}, [[XMM0]] +;CHECK-NEXT: movsd [[XMM0]], +}