-; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.9.0"
;CHECK: for.body.preheader:
;CHECK: br i1 %cmp.zero, label %middle.block, label %vector.memcheck
;CHECK: vector.memcheck:
-;CHECK: br i1 %found.conflict, label %middle.block, label %vector.ph
+;CHECK: br i1 %memcheck.conflict, label %middle.block, label %vector.ph
;CHECK: load <4 x float>
define i32 @foo(float* nocapture %a, float* nocapture %b, i32 %n) nounwind uwtable ssp {
entry:
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
- %arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv
- %0 = load float* %arrayidx, align 4, !tbaa !0
+ %arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv
+ %0 = load float, float* %arrayidx, align 4
%mul = fmul float %0, 3.000000e+00
- %arrayidx2 = getelementptr inbounds float* %a, i64 %indvars.iv
- store float %mul, float* %arrayidx2, align 4, !tbaa !0
+ %arrayidx2 = getelementptr inbounds float, float* %a, i64 %indvars.iv
+ store float %mul, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
ret i32 undef
}
-!0 = metadata !{metadata !"float", metadata !1}
-!1 = metadata !{metadata !"omnipotent char", metadata !2}
-!2 = metadata !{metadata !"Simple C/C++ TBAA"}
+; Make sure that we try to vectorize loops with a runtime check if the
+; dependency check fails.
+
+; CHECK-LABEL: test_runtime_check
+; CHECK: <4 x float>
+define void @test_runtime_check(float* %a, float %b, i64 %offset, i64 %offset2, i64 %n) {
+entry:
+ br label %for.body
+
+for.body:
+ %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+ %ind.sum = add i64 %iv, %offset
+ %arr.idx = getelementptr inbounds float, float* %a, i64 %ind.sum
+ %l1 = load float, float* %arr.idx, align 4
+ %ind.sum2 = add i64 %iv, %offset2
+ %arr.idx2 = getelementptr inbounds float, float* %a, i64 %ind.sum2
+ %l2 = load float, float* %arr.idx2, align 4
+ %m = fmul fast float %b, %l2
+ %ad = fadd fast float %l1, %m
+ store float %ad, float* %arr.idx, align 4
+ %iv.next = add nuw nsw i64 %iv, 1
+ %exitcond = icmp eq i64 %iv.next, %n
+ br i1 %exitcond, label %loopexit, label %for.body
+
+loopexit:
+ ret void
+}