diff options
| author | Nadav Rotem <nrotem@apple.com> | 2012-10-31 20:52:26 +0000 |
|---|---|---|
| committer | Nadav Rotem <nrotem@apple.com> | 2012-10-31 20:52:26 +0000 |
| commit | 0dba9a9a26f45119a82200d1db37b734b3e1bb22 (patch) | |
| tree | 61fd5d2c6c9996b155713c95cb354026473216e2 /test | |
| parent | 2932284f045005bc3ed850f9c42524fadf3ae3d8 (diff) | |
| download | llvm-0dba9a9a26f45119a82200d1db37b734b3e1bb22.tar.gz llvm-0dba9a9a26f45119a82200d1db37b734b3e1bb22.tar.bz2 llvm-0dba9a9a26f45119a82200d1db37b734b3e1bb22.tar.xz | |
Fix a bug in the cost calculation of vector casts. Detect situations where bitcasts cost zero.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167170 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
| -rw-r--r-- | test/Transforms/LoopVectorize/X86/conversion-cost.ll | 48 |
1 files changed, 48 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/X86/conversion-cost.ll b/test/Transforms/LoopVectorize/X86/conversion-cost.ll new file mode 100644 index 0000000000..8582613617 --- /dev/null +++ b/test/Transforms/LoopVectorize/X86/conversion-cost.ll @@ -0,0 +1,48 @@ +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -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: @conversion_cost1 +;CHECK: store <8 x i8> +;CHECK: ret +define i32 @conversion_cost1(i32 %n, i8* nocapture %A, float* nocapture %B) nounwind uwtable ssp { + %1 = icmp sgt i32 %n, 3 + br i1 %1, label %.lr.ph, label %._crit_edge + +.lr.ph: ; preds = %0, %.lr.ph + %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 3, %0 ] + %2 = trunc i64 %indvars.iv to i8 + %3 = getelementptr inbounds i8* %A, i64 %indvars.iv + store i8 %2, i8* %3, align 1 + %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 +} + +;CHECK: @conversion_cost2 +;CHECK: store <8 x float> +;CHECK: ret +define i32 @conversion_cost2(i32 %n, i8* nocapture %A, float* nocapture %B) nounwind uwtable ssp { + %1 = icmp sgt i32 %n, 9 + br i1 %1, label %.lr.ph, label %._crit_edge + +.lr.ph: ; preds = %0, %.lr.ph + %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 9, %0 ] + %2 = add nsw i64 %indvars.iv, 3 + %3 = trunc i64 %2 to i32 + %4 = sitofp i32 %3 to float + %5 = getelementptr inbounds float* %B, i64 %indvars.iv + store float %4, float* %5, 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 +} |