| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py |
| ; RUN: opt < %s -basicaa -slp-vectorizer -S | FileCheck %s |
| |
| target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" |
| target triple = "x86_64-apple-macosx10.10.0" |
| |
| define void @testfunc(float* nocapture %dest, float* nocapture readonly %src) { |
| ; CHECK-LABEL: @testfunc( |
| ; CHECK-NEXT: entry: |
| ; CHECK-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK: for.body: |
| ; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ] |
| ; CHECK-NEXT: [[ACC1_056:%.*]] = phi float [ 0.000000e+00, [[ENTRY]] ], [ [[ADD13:%.*]], [[FOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP0:%.*]] = phi <2 x float> [ zeroinitializer, [[ENTRY]] ], [ [[TMP23:%.*]], [[FOR_BODY]] ] |
| ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 [[INDVARS_IV]] |
| ; CHECK-NEXT: [[TMP1:%.*]] = load float, float* [[ARRAYIDX]], align 4 |
| ; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1 |
| ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[DEST:%.*]], i64 [[INDVARS_IV]] |
| ; CHECK-NEXT: store float [[ACC1_056]], float* [[ARRAYIDX2]], align 4 |
| ; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x float> [[TMP0]], i32 1 |
| ; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x float> undef, float [[TMP2]], i32 0 |
| ; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x float> [[TMP0]], i32 0 |
| ; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x float> [[TMP3]], float [[TMP4]], i32 1 |
| ; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x float> undef, float [[TMP1]], i32 0 |
| ; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x float> [[TMP6]], float [[TMP1]], i32 1 |
| ; CHECK-NEXT: [[TMP8:%.*]] = fadd <2 x float> [[TMP5]], [[TMP7]] |
| ; CHECK-NEXT: [[TMP9:%.*]] = fmul <2 x float> zeroinitializer, [[TMP0]] |
| ; CHECK-NEXT: [[TMP10:%.*]] = fadd <2 x float> [[TMP9]], [[TMP8]] |
| ; CHECK-NEXT: [[TMP11:%.*]] = fcmp olt <2 x float> [[TMP10]], <float 1.000000e+00, float 1.000000e+00> |
| ; CHECK-NEXT: [[TMP12:%.*]] = select <2 x i1> [[TMP11]], <2 x float> [[TMP10]], <2 x float> <float 1.000000e+00, float 1.000000e+00> |
| ; CHECK-NEXT: [[TMP13:%.*]] = fcmp olt <2 x float> [[TMP12]], <float -1.000000e+00, float -1.000000e+00> |
| ; CHECK-NEXT: [[TMP14:%.*]] = fmul <2 x float> zeroinitializer, [[TMP12]] |
| ; CHECK-NEXT: [[TMP15:%.*]] = select <2 x i1> [[TMP13]], <2 x float> <float -0.000000e+00, float -0.000000e+00>, <2 x float> [[TMP14]] |
| ; CHECK-NEXT: [[TMP16:%.*]] = extractelement <2 x float> [[TMP15]], i32 0 |
| ; CHECK-NEXT: [[TMP17:%.*]] = extractelement <2 x float> [[TMP15]], i32 1 |
| ; CHECK-NEXT: [[ADD13]] = fadd float [[TMP16]], [[TMP17]] |
| ; CHECK-NEXT: [[TMP18:%.*]] = insertelement <2 x float> undef, float [[TMP17]], i32 0 |
| ; CHECK-NEXT: [[TMP19:%.*]] = insertelement <2 x float> [[TMP18]], float [[ADD13]], i32 1 |
| ; CHECK-NEXT: [[TMP20:%.*]] = fcmp olt <2 x float> [[TMP19]], <float 1.000000e+00, float 1.000000e+00> |
| ; CHECK-NEXT: [[TMP21:%.*]] = select <2 x i1> [[TMP20]], <2 x float> [[TMP19]], <2 x float> <float 1.000000e+00, float 1.000000e+00> |
| ; CHECK-NEXT: [[TMP22:%.*]] = fcmp olt <2 x float> [[TMP21]], <float -1.000000e+00, float -1.000000e+00> |
| ; CHECK-NEXT: [[TMP23]] = select <2 x i1> [[TMP22]], <2 x float> <float -1.000000e+00, float -1.000000e+00>, <2 x float> [[TMP21]] |
| ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 32 |
| ; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]] |
| ; CHECK: for.end: |
| ; CHECK-NEXT: ret void |
| ; |
| entry: |
| br label %for.body |
| |
| for.body: |
| %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] |
| %acc1.056 = phi float [ 0.000000e+00, %entry ], [ %add13, %for.body ] |
| %s1.055 = phi float [ 0.000000e+00, %entry ], [ %cond.i40, %for.body ] |
| %s0.054 = phi float [ 0.000000e+00, %entry ], [ %cond.i44, %for.body ] |
| %arrayidx = getelementptr inbounds float, float* %src, i64 %indvars.iv |
| %0 = load float, float* %arrayidx, align 4 |
| %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 |
| %arrayidx2 = getelementptr inbounds float, float* %dest, i64 %indvars.iv |
| store float %acc1.056, float* %arrayidx2, align 4 |
| %add = fadd float %s0.054, %0 |
| %add3 = fadd float %s1.055, %0 |
| %mul = fmul float %s0.054, 0.000000e+00 |
| %add4 = fadd float %mul, %add3 |
| %mul5 = fmul float %s1.055, 0.000000e+00 |
| %add6 = fadd float %mul5, %add |
| %cmp.i = fcmp olt float %add6, 1.000000e+00 |
| %cond.i = select i1 %cmp.i, float %add6, float 1.000000e+00 |
| %cmp.i51 = fcmp olt float %cond.i, -1.000000e+00 |
| %cmp.i49 = fcmp olt float %add4, 1.000000e+00 |
| %cond.i50 = select i1 %cmp.i49, float %add4, float 1.000000e+00 |
| %cmp.i47 = fcmp olt float %cond.i50, -1.000000e+00 |
| %cond.i.op = fmul float %cond.i, 0.000000e+00 |
| %mul10 = select i1 %cmp.i51, float -0.000000e+00, float %cond.i.op |
| %cond.i50.op = fmul float %cond.i50, 0.000000e+00 |
| %mul11 = select i1 %cmp.i47, float -0.000000e+00, float %cond.i50.op |
| %add13 = fadd float %mul10, %mul11 |
| |
| ; The SLPVectorizer crashed in vectorizeChainsInBlock() because it tried |
| ; to access the second operand of the following cmp after the cmp itself |
| ; was already vectorized and deleted. |
| %cmp.i45 = fcmp olt float %add13, 1.000000e+00 |
| |
| %cond.i46 = select i1 %cmp.i45, float %add13, float 1.000000e+00 |
| %cmp.i43 = fcmp olt float %cond.i46, -1.000000e+00 |
| %cond.i44 = select i1 %cmp.i43, float -1.000000e+00, float %cond.i46 |
| %cmp.i41 = fcmp olt float %mul11, 1.000000e+00 |
| %cond.i42 = select i1 %cmp.i41, float %mul11, float 1.000000e+00 |
| %cmp.i39 = fcmp olt float %cond.i42, -1.000000e+00 |
| %cond.i40 = select i1 %cmp.i39, float -1.000000e+00, float %cond.i42 |
| %exitcond = icmp eq i64 %indvars.iv.next, 32 |
| br i1 %exitcond, label %for.end, label %for.body |
| |
| for.end: |
| ret void |
| } |
| |