b133fbb9a4
AMDGPU/SI: Handle hazard with > 8 byte VMEM stores
...
Reviewers: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, tony-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D25577
llvm-svn: 285359
2016-10-27 23:05:31 +00:00
73f1ab28cd
[AMDGPU][mc] Add support for buffer_load_dwordx3, buffer_store_dwordx3.
...
Partially fixes Bug 28232.
Lit tests added.
Differential Revision: https://reviews.llvm.org/D25367
llvm-svn: 283567
2016-10-07 15:53:16 +00:00
2261d78cd2
Target: Remove unused patterns and transforms. NFC.
...
llvm-svn: 283515
2016-10-07 00:30:49 +00:00
10c17ca6c6
AMDGPU: Partially fix reported code size for some instructions
...
These ones need to have the size on the pseudo instruction set for
getInstSizeInBytes to work correctly. These also have a statically
known size.
llvm-svn: 283437
2016-10-06 10:13:23 +00:00
fbf2d93f73
[AMDGPU] Fix for bz30427: wrong MTBUF encoding on VI
...
Differential revision: https://reviews.llvm.org/D24875
llvm-svn: 282296
2016-09-23 21:21:21 +00:00
b66e5eb612
[AMDGPU] Refactor MUBUF/MTBUF instructions
...
Differential revision: https://reviews.llvm.org/D24295
llvm-svn: 281137
2016-09-10 13:09:16 +00:00
Tom Stellard