diff options
author | Adam Nemet <anemet@apple.com> | 2016-03-09 20:47:55 +0000 |
---|---|---|
committer | Adam Nemet <anemet@apple.com> | 2016-03-09 20:47:55 +0000 |
commit | 660748ca8c70e3afd8414ff45ef99feeca3f3d3c (patch) | |
tree | 80bbb245e18cc7916629cb8afe62290d899cea67 /llvm/test/Transforms/LoopLoadElim/non-consecutive.ll | |
parent | c43ec673b9b579572af5eb414a335d7d4f2d929f (diff) | |
download | bcm5719-llvm-660748ca8c70e3afd8414ff45ef99feeca3f3d3c.tar.gz bcm5719-llvm-660748ca8c70e3afd8414ff45ef99feeca3f3d3c.zip |
[LLE] Add missing check for unit stride
I somehow missed this. The case in GCC (global_alloc) was similar to
the new testcase except it had an array of structs rather than a two
dimensional array.
Fixes RP26885.
llvm-svn: 263058
Diffstat (limited to 'llvm/test/Transforms/LoopLoadElim/non-consecutive.ll')
-rw-r--r-- | llvm/test/Transforms/LoopLoadElim/non-consecutive.ll | 43 |
1 files changed, 43 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopLoadElim/non-consecutive.ll b/llvm/test/Transforms/LoopLoadElim/non-consecutive.ll new file mode 100644 index 00000000000..43751a8ff60 --- /dev/null +++ b/llvm/test/Transforms/LoopLoadElim/non-consecutive.ll @@ -0,0 +1,43 @@ +; RUN: opt -loop-load-elim -S < %s | FileCheck %s + +; The accesses to A are independent here but LAA reports it as a loop-carried +; forward dependence. Check that we don't perform st->ld forwarding between +; them. +; +; for (unsigned i = 0; i < 100; i++) { +; A[i][1] = B[i] + 2; +; C[i] = A[i][0] * 2; +; } + +target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" + +define void @f([2 x i32]* noalias %A, i32* noalias %B, i32* noalias %C, i64 %N) { + +entry: + br label %for.body + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + + %A1idx = getelementptr inbounds [2 x i32], [2 x i32]* %A, i64 %indvars.iv, i32 1 + %Bidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv + %Cidx = getelementptr inbounds i32, i32* %C, i64 %indvars.iv + %A0idx = getelementptr inbounds [2 x i32], [2 x i32]* %A, i64 %indvars.iv, i32 0 + + %b = load i32, i32* %Bidx, align 4 + %a_p1 = add i32 %b, 2 + store i32 %a_p1, i32* %A1idx, align 4 + +; CHECK: %a = load i32, i32* %A0idx, align 4 + %a = load i32, i32* %A0idx, align 4 +; CHECK: %c = mul i32 %a, 2 + %c = mul i32 %a, 2 + store i32 %c, i32* %Cidx, align 4 + + %exitcond = icmp eq i64 %indvars.iv.next, %N + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +} |