diff options
author | Benjamin Kramer <benny.kra@googlemail.com> | 2013-11-01 14:09:50 +0000 |
---|---|---|
committer | Benjamin Kramer <benny.kra@googlemail.com> | 2013-11-01 14:09:50 +0000 |
commit | 7208b0763c9fca2c6364c642d28fd014a496cc37 (patch) | |
tree | 1dc0c78f1ac0c28e9bff57c26e8cdb698961b489 /test | |
parent | 6186de5c54b580414b2d162e0f335b62b3d9812c (diff) | |
download | llvm-7208b0763c9fca2c6364c642d28fd014a496cc37.tar.gz llvm-7208b0763c9fca2c6364c642d28fd014a496cc37.tar.bz2 llvm-7208b0763c9fca2c6364c642d28fd014a496cc37.tar.xz |
LoopVectorize: Look for consecutive acces in GEPs with trailing zero indices
If we have a pointer to a single-element struct we can still build wide loads
and stores to it (if there is no padding).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193860 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
-rw-r--r-- | test/Transforms/LoopVectorize/struct_access.ll | 42 |
1 files changed, 42 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/struct_access.ll b/test/Transforms/LoopVectorize/struct_access.ll index 0cfaabe177..75beae82f1 100644 --- a/test/Transforms/LoopVectorize/struct_access.ll +++ b/test/Transforms/LoopVectorize/struct_access.ll @@ -44,3 +44,45 @@ for.end: ; preds = %for.body, %entry %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ] ret i32 %sum.0.lcssa } + +%struct.lit = type { i32 } + +; Verify that we still vectorize the access if the struct has the same size as +; the loaded element. +; struct lit { +; int x; +; }; +; +; +; int bar(struct lit *A, int n) { +; +; int sum = 0; +; for (int i = 0; i < n; ++i) +; sum += A[i].x; +; +; return sum; +; } + +;CHECK-LABEL: @bar( +;CHECK: load <4 x i32> +;CHECK: ret +define i32 @bar(%struct.lit* nocapture %A, i32 %n) nounwind uwtable readonly ssp { +entry: + %cmp4 = icmp sgt i32 %n, 0 + br i1 %cmp4, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %sum.05 = phi i32 [ %add, %for.body ], [ 0, %entry ] + %x = getelementptr inbounds %struct.lit* %A, i64 %indvars.iv, i32 0 + %0 = load i32* %x, align 4 + %add = add nsw i32 %0, %sum.05 + %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 + %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ] + ret i32 %sum.0.lcssa +} |