maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
194,753 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

3 Commits

Author SHA1 Message Date
Simon Pilgrim b2c00f3286 [X86][SSE] Add SSE MOVQ instructions to SSEPackedInt domain 
Patch to explicitly add the SSE MOVQ (rr,mr,rm) instructions to SSEPackedInt domain - prevents a number of costly domain switches.

Differential Revision: http://reviews.llvm.org/D7600

llvm-svn: 229439
 2015-02-16 21:50:56 +00:00
Andrea Di Biagio 23df4e4a2d Teach the DAGCombiner how to fold 'vselect' dag nodes according 
to the following two rules:
  1) fold (vselect (build_vector AllOnes), A, B) -> A
  2) fold (vselect (build_vector AllZeros), A, B) -> B

llvm-svn: 198777
 2014-01-08 18:33:04 +00:00
Nadav Rotem 6652e22bad Add support for the vector-widening of vselect and vector-setcc 
llvm-svn: 142488
 2011-10-19 09:45:11 +00:00