diff options
| author | Nadav Rotem <nrotem@apple.com> | 2012-10-30 18:36:45 +0000 |
|---|---|---|
| committer | Nadav Rotem <nrotem@apple.com> | 2012-10-30 18:36:45 +0000 |
| commit | e709f5b600fd630c4f58b5dba14c8069a03093ea (patch) | |
| tree | a62919ba572af1112d185ef1137cee94becc8d0b /test/Transforms/LoopVectorize/write-only.ll | |
| parent | c83b5dc625bd85276a23c36c1fbad193203d2bc7 (diff) | |
LoopVectorize: Add support for write-only loops when the write destination is a single pointer.
Speedup SciMark by 1%
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167035 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/LoopVectorize/write-only.ll')
| -rw-r--r-- | test/Transforms/LoopVectorize/write-only.ll | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/write-only.ll b/test/Transforms/LoopVectorize/write-only.ll new file mode 100644 index 0000000000..eb02760413 --- /dev/null +++ b/test/Transforms/LoopVectorize/write-only.ll @@ -0,0 +1,26 @@ +; 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-macosx10.8.0" + +;CHECK: @read_mod_write_single_ptr +;CHECK: load <4 x float> +;CHECK: ret i32 +define i32 @read_mod_write_single_ptr(float* nocapture %a, i32 %n) nounwind uwtable ssp { + %1 = icmp sgt i32 %n, 0 + br i1 %1, label %.lr.ph, label %._crit_edge + +.lr.ph: ; preds = %0, %.lr.ph + %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ] + %2 = getelementptr inbounds float* %a, i64 %indvars.iv + %3 = load float* %2, align 4 + %4 = fmul float %3, 3.000000e+00 + store float %4, float* %2, 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 + br i1 %exitcond, label %._crit_edge, label %.lr.ph + +._crit_edge: ; preds = %.lr.ph, %0 + ret i32 undef +} |