| commit | 55306bdea5d2d53be39f3ac59fadf5220ee6b5d0 | [log] [tgz] |
|---|---|---|
| author | Nadav Rotem <nrotem@apple.com> | Fri Dec 21 00:07:35 2012 +0000 |
| committer | Nadav Rotem <nrotem@apple.com> | Fri Dec 21 00:07:35 2012 +0000 |
| tree | f8f8d9f0290bd9e8131d1669ca290f86bac18509 | |
| parent | 71a9c2137b590467fabfcde1ef9f87bcb8059c92 [diff] |
Fix a bug in the code that checks if we can vectorize loops while using dynamic memory bound checks. Before the fix we were able to vectorize this loop from the Livermore Loops benchmark: for ( k=1 ; k<n ; k++ ) x[k] = x[k-1] + y[k]; git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170811 91177308-0d34-0410-b5e6-96231b3b80d8