diff options
| author | Nadav Rotem <nrotem@apple.com> | 2012-11-09 07:09:44 +0000 |
|---|---|---|
| committer | Nadav Rotem <nrotem@apple.com> | 2012-11-09 07:09:44 +0000 |
| commit | 1cfef3e9ee687d05b35127112bb58a5f1676407e (patch) | |
| tree | 1d080120fb2a436cbe51655647a3b1316dfc85f8 /llvm/test/Transforms/LoopVectorize | |
| parent | d1e906e1f1748d7daec90e167b5a1aa572af1302 (diff) | |
| download | bcm5719-llvm-1cfef3e9ee687d05b35127112bb58a5f1676407e.tar.gz bcm5719-llvm-1cfef3e9ee687d05b35127112bb58a5f1676407e.zip | |
Add support for memory runtime check. When we can, we calculate array bounds.
If the arrays are found to be disjoint then we run the vectorized version of
the loop. If they are not, we run the scalar code.
llvm-svn: 167608
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize')
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/runtime-check.ll | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/runtime-check.ll b/llvm/test/Transforms/LoopVectorize/runtime-check.ll new file mode 100644 index 00000000000..23933cf7c7d --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/runtime-check.ll @@ -0,0 +1,36 @@ +; RUN: opt < %s -loop-vectorize -force-vector-width=4 -dce -instcombine -licm -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" + +; Make sure we vectorize this loop: +; int foo(float *a, float *b, int n) { +; for (int i=0; i<n; ++i) +; a[i] = b[i] * 3; +; } + +;CHECK: load <4 x float> +define i32 @foo(float* nocapture %a, float* nocapture %b, i32 %n) nounwind uwtable ssp { +entry: + %cmp6 = icmp sgt i32 %n, 0 + br i1 %cmp6, label %for.body, label %for.end + +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 + %mul = fmul float %0, 3.000000e+00 + %arrayidx2 = getelementptr inbounds float* %a, i64 %indvars.iv + store float %mul, float* %arrayidx2, align 4, !tbaa !0 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret i32 undef +} + +!0 = metadata !{metadata !"float", metadata !1} +!1 = metadata !{metadata !"omnipotent char", metadata !2} +!2 = metadata !{metadata !"Simple C/C++ TBAA"} |
