diff options
| author | Nadav Rotem <nrotem@apple.com> | 2013-05-10 22:55:44 +0000 |
|---|---|---|
| committer | Nadav Rotem <nrotem@apple.com> | 2013-05-10 22:55:44 +0000 |
| commit | ef3e423e2313ee05ba136aafc1e34c45a2702577 (patch) | |
| tree | 2760da9dd9fec82f7880a8095c4bc3fd3ccc36a3 /test | |
| parent | 46090914b783b632618268f2a5c99aab83732688 (diff) | |
| download | external_llvm-ef3e423e2313ee05ba136aafc1e34c45a2702577.zip external_llvm-ef3e423e2313ee05ba136aafc1e34c45a2702577.tar.gz external_llvm-ef3e423e2313ee05ba136aafc1e34c45a2702577.tar.bz2 | |
Add an additional testcase for PR15882.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181646 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
| -rw-r--r-- | test/Transforms/LoopVectorize/reverse_iter.ll | 45 |
1 files changed, 45 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/reverse_iter.ll b/test/Transforms/LoopVectorize/reverse_iter.ll new file mode 100644 index 0000000..6ff4f1f --- /dev/null +++ b/test/Transforms/LoopVectorize/reverse_iter.ll @@ -0,0 +1,45 @@ +; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -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" + +; Make sure that the reverse iterators are calculated using 64bit arithmetic, not 32. +; +; int foo(int n, int *A) { +; int sum; +; for (int i=n; i > 0; i--) +; sum += A[i*2]; +; return sum; +; } +; + +;CHECK: @foo +;CHECK: <i64 0, i64 -1, i64 -2, i64 -3> +;CHECK: ret +define i32 @foo(i32 %n, i32* nocapture %A) { + %1 = icmp sgt i32 %n, 0 + br i1 %1, label %.lr.ph, label %._crit_edge + +.lr.ph: ; preds = %0 + %2 = sext i32 %n to i64 + br label %3 + +; <label>:3 ; preds = %.lr.ph, %3 + %indvars.iv = phi i64 [ %2, %.lr.ph ], [ %indvars.iv.next, %3 ] + %sum.01 = phi i32 [ undef, %.lr.ph ], [ %9, %3 ] + %4 = trunc i64 %indvars.iv to i32 + %5 = shl nsw i32 %4, 1 + %6 = sext i32 %5 to i64 + %7 = getelementptr inbounds i32* %A, i64 %6 + %8 = load i32* %7, align 4 + %9 = add nsw i32 %8, %sum.01 + %indvars.iv.next = add i64 %indvars.iv, -1 + %10 = trunc i64 %indvars.iv.next to i32 + %11 = icmp sgt i32 %10, 0 + br i1 %11, label %3, label %._crit_edge + +._crit_edge: ; preds = %3, %0 + %sum.0.lcssa = phi i32 [ undef, %0 ], [ %9, %3 ] + ret i32 %sum.0.lcssa +} + |