diff options
| author | Jiangning Liu <jiangning.liu@arm.com> | 2014-04-18 07:57:54 +0000 |
|---|---|---|
| committer | Jiangning Liu <jiangning.liu@arm.com> | 2014-04-18 07:57:54 +0000 |
| commit | a1da81989635ff37284c1c471f06af7da2a1a71d (patch) | |
| tree | e6ed2f2356b7f951e5361a1d03d5773f28f3ee6c /test | |
| parent | 1b16515971d90f36b247191731b0c310a5c338bc (diff) | |
| download | llvm-a1da81989635ff37284c1c471f06af7da2a1a71d.tar.gz llvm-a1da81989635ff37284c1c471f06af7da2a1a71d.tar.bz2 llvm-a1da81989635ff37284c1c471f06af7da2a1a71d.tar.xz | |
This commit allows vectorized loops to be unrolled by a factor of 2 for AArch64.
A new test case is also added for ARM64.
Patched by Z.Zheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206563 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
| -rw-r--r-- | test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll | 42 | ||||
| -rw-r--r-- | test/Transforms/LoopVectorize/ARM64/arm64-unroll.ll | 42 |
2 files changed, 84 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll b/test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll new file mode 100644 index 0000000000..9962c3d76a --- /dev/null +++ b/test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll @@ -0,0 +1,42 @@ +; RUN: opt < %s -loop-vectorize -mtriple=aarch64-none-linux-gnu -mattr=+neon -S | FileCheck %s +target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128" + +; Function Attrs: nounwind +define i32* @array_add(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* %c, i32 %size) { +;CHECK-LABEL: array_add +;CHECK: load <4 x i32> +;CHECK: load <4 x i32> +;CHECK: load <4 x i32> +;CHECK: load <4 x i32> +;CHECK: add nsw <4 x i32> +;CHECK: add nsw <4 x i32> +;CHECK: store <4 x i32> +;CHECK: store <4 x i32> +;CHECK: ret +entry: + %cmp10 = icmp sgt i32 %size, 0 + br i1 %cmp10, label %for.body.preheader, label %for.end + +for.body.preheader: ; preds = %entry + br label %for.body + +for.body: ; preds = %for.body.preheader, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ] + %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %arrayidx2 = getelementptr inbounds i32* %b, i64 %indvars.iv + %1 = load i32* %arrayidx2, align 4 + %add = add nsw i32 %1, %0 + %arrayidx4 = getelementptr inbounds i32* %c, i64 %indvars.iv + store i32 %add, i32* %arrayidx4, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %size + br i1 %exitcond, label %for.end.loopexit, label %for.body + +for.end.loopexit: ; preds = %for.body + br label %for.end + +for.end: ; preds = %for.end.loopexit, %entry + ret i32* %c +} diff --git a/test/Transforms/LoopVectorize/ARM64/arm64-unroll.ll b/test/Transforms/LoopVectorize/ARM64/arm64-unroll.ll new file mode 100644 index 0000000000..f8eb3ed1f3 --- /dev/null +++ b/test/Transforms/LoopVectorize/ARM64/arm64-unroll.ll @@ -0,0 +1,42 @@ +; RUN: opt < %s -loop-vectorize -mtriple=arm64-none-linux-gnu -mattr=+neon -S | FileCheck %s +target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128" + +; Function Attrs: nounwind +define i32* @array_add(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* %c, i32 %size) { +;CHECK-LABEL: array_add +;CHECK: load <4 x i32> +;CHECK: load <4 x i32> +;CHECK: load <4 x i32> +;CHECK: load <4 x i32> +;CHECK: add nsw <4 x i32> +;CHECK: add nsw <4 x i32> +;CHECK: store <4 x i32> +;CHECK: store <4 x i32> +;CHECK: ret +entry: + %cmp10 = icmp sgt i32 %size, 0 + br i1 %cmp10, label %for.body.preheader, label %for.end + +for.body.preheader: ; preds = %entry + br label %for.body + +for.body: ; preds = %for.body.preheader, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ] + %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %arrayidx2 = getelementptr inbounds i32* %b, i64 %indvars.iv + %1 = load i32* %arrayidx2, align 4 + %add = add nsw i32 %1, %0 + %arrayidx4 = getelementptr inbounds i32* %c, i64 %indvars.iv + store i32 %add, i32* %arrayidx4, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %size + br i1 %exitcond, label %for.end.loopexit, label %for.body + +for.end.loopexit: ; preds = %for.body + br label %for.end + +for.end: ; preds = %for.end.loopexit, %entry + ret i32* %c +} |