maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
306,982 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

3 Commits

Author SHA1 Message Date
Alexander Timofeev db7ee7660a [AMDGPU] Preliminary patch for divergence driven instruction selection. Immediate selection predicate changed 
Differential revision: https://reviews.llvm.org/D51734
Reviewers: rampitec

llvm-svn: 341928
 2018-09-11 11:56:50 +00:00
Stanislav Mekhanoshin 298a61590a [AMDGPU] Overload llvm.amdgcn.fmad.ftz to support f16 
Differential Revision: https://reviews.llvm.org/D48677

llvm-svn: 335866
 2018-06-28 15:24:46 +00:00
Stanislav Mekhanoshin dacda79ee6 [AMDGPU] Add llvm.amdgcn.fmad.ftz intrinsic 
This intrinsic selects v_mad_f32 regardless of fp32 denorm support.

Differential Revision: https://reviews.llvm.org/D48573

llvm-svn: 335654
 2018-06-26 20:04:19 +00:00