diff options
| author | Andrea Di Biagio <Andrea_DiBiagio@sn.scee.net> | 2014-06-10 16:42:57 +0000 |
|---|---|---|
| committer | Andrea Di Biagio <Andrea_DiBiagio@sn.scee.net> | 2014-06-10 16:42:57 +0000 |
| commit | fa508af0fec7a6efda5ae1be2dac4c43b4a0dfc8 (patch) | |
| tree | cd64293521a1231c62cdff8717f2f506792b04d4 /llvm/lib/Object/Object.cpp | |
| parent | d172270c44ad57827539e04bc244aa07e10d37e9 (diff) | |
| download | llvm-fa508af0fec7a6efda5ae1be2dac4c43b4a0dfc8.zip llvm-fa508af0fec7a6efda5ae1be2dac4c43b4a0dfc8.tar.gz llvm-fa508af0fec7a6efda5ae1be2dac4c43b4a0dfc8.tar.bz2 | |
[X86] Improved target combine rules for selecting horizontal add/sub.
This patch slightly changes the algorithm introduced at revision 210477
to fix a problem where the algorithm was producing incorrect code for
the VEX.256 encoded versions of horizontal add/sub.
For these cases, we now try to split the two 256-bit vectors into
128-bit chunks before emitting horizontal add/sub dag nodes.
Added a new test case into haddsub-2.ll.
llvm-svn: 210545
Diffstat (limited to 'llvm/lib/Object/Object.cpp')
0 files changed, 0 insertions, 0 deletions