maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
376,560 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

3 Commits

Author SHA1 Message Date
Jay Foad d28624a209 [AMDGPU] Stop adding an implicit def of vcc_hi for wave32 
This doesn't seem to be needed for anything.

Differential Revision: https://reviews.llvm.org/D92400
 2020-12-02 10:11:42 +00:00
Matt Arsenault dfce5fd50a AMDGPU/GlobalISel: Select VOP3P instructions 
This only handles the basic cases. More work is needed to make better
use of op_sel.
 2020-02-21 13:35:40 -05:00
Matt Arsenault 1b69fd275d AMDGPU/GlobalISel: Select G_SHL 
I think this manages to not break the DAG handling with the divergent
predicates because the stadalone divergent patterns end up with a
higher priority than the pattern on the instruction definition.

The 16-bit versions don't work yet.

llvm-svn: 366254
 2019-07-16 20:15:30 +00:00