diff options
| author | Arnold Schwaighofer <aschwaighofer@apple.com> | 2013-10-04 20:39:16 +0000 |
|---|---|---|
| committer | Arnold Schwaighofer <aschwaighofer@apple.com> | 2013-10-04 20:39:16 +0000 |
| commit | af57bdf7d673a3731fb887218e7a9ccd1576ab4f (patch) | |
| tree | 0c904746bc10108be370353aa7cbd9831bd79a1e /lib/MC/MCParser | |
| parent | e3fd646e178f92dbe2737a5230d73577090d9d0e (diff) | |
| download | external_llvm-af57bdf7d673a3731fb887218e7a9ccd1576ab4f.zip external_llvm-af57bdf7d673a3731fb887218e7a9ccd1576ab4f.tar.gz external_llvm-af57bdf7d673a3731fb887218e7a9ccd1576ab4f.tar.bz2 | |
SLPVectorizer: Sort inputs to commutative binary operations
Sort the operands of the other entries in the current vectorization root
according to the first entry's operands opcodes.
%conv0 = uitofp ...
%load0 = load float ...
= fmul %conv0, %load0
= fmul %load0, %conv1
= fmul %load0, %conv2
Make sure that we recursively vectorize <%conv0, %conv1, %conv2> and <%load0,
%load0, %load0>.
This makes it more likely to obtain vectorizable trees. We have to be careful
when we sort that we don't destroy 'good' existing ordering implied by source
order.
radar://15080067
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191977 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/MC/MCParser')
0 files changed, 0 insertions, 0 deletions