diff options
| author | Hal Finkel <hfinkel@anl.gov> | 2012-02-04 04:14:04 +0000 |
|---|---|---|
| committer | Hal Finkel <hfinkel@anl.gov> | 2012-02-04 04:14:04 +0000 |
| commit | edc8db87dc2ed4d2971e7f50464f5f4d0fead537 (patch) | |
| tree | c2bf019957e2be6546e701066071bd0b6b65c627 /test/Transforms/BBVectorize | |
| parent | fd4b8e2bac9db13abfb2951b4f9ec5b1b56bd23c (diff) | |
Boost the effective chain depth of loads and stores.
By default, boost the chain depth contribution of loads and stores. This will allow a load/store pair to vectorize even when it would not otherwise be long enough to satisfy the chain depth requirement.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149761 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/BBVectorize')
| -rw-r--r-- | test/Transforms/BBVectorize/mem-op-depth.ll | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/test/Transforms/BBVectorize/mem-op-depth.ll b/test/Transforms/BBVectorize/mem-op-depth.ll new file mode 100644 index 0000000000..84f16bd2f4 --- /dev/null +++ b/test/Transforms/BBVectorize/mem-op-depth.ll @@ -0,0 +1,22 @@ +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" +target triple = "x86_64-unknown-linux-gnu" +; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=6 -instcombine -gvn -S | FileCheck %s + +@A = common global [1024 x float] zeroinitializer, align 16 +@B = common global [1024 x float] zeroinitializer, align 16 + +define i32 @test1() nounwind { +; CHECK: @test1 + %V1 = load float* getelementptr inbounds ([1024 x float]* @A, i64 0, i64 0), align 16 + %V2 = load float* getelementptr inbounds ([1024 x float]* @A, i64 0, i64 1), align 4 + %V3= load float* getelementptr inbounds ([1024 x float]* @A, i64 0, i64 2), align 8 + %V4 = load float* getelementptr inbounds ([1024 x float]* @A, i64 0, i64 3), align 4 +; CHECK: %V1 = load <4 x float>* bitcast ([1024 x float]* @A to <4 x float>*), align 16 + store float %V1, float* getelementptr inbounds ([1024 x float]* @B, i64 0, i64 0), align 16 + store float %V2, float* getelementptr inbounds ([1024 x float]* @B, i64 0, i64 1), align 4 + store float %V3, float* getelementptr inbounds ([1024 x float]* @B, i64 0, i64 2), align 8 + store float %V4, float* getelementptr inbounds ([1024 x float]* @B, i64 0, i64 3), align 4 +; CHECK-NEXT: store <4 x float> %V1, <4 x float>* bitcast ([1024 x float]* @B to <4 x float>*), align 16 + ret i32 0 +; CHECK-NEXT: ret i32 0 +} |