maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
378,797 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

6 Commits

Author SHA1 Message Date
Cameron McInally 92be640bd7 [FPEnv][AMDGPU] Disable FSUB(-0,X)->FNEG(X) DAGCombine when subnormals are flushed 
This patch disables the FSUB(-0,X)->FNEG(X) DAG combine when we're flushing subnormals. It requires updating the existing AMDGPU tests to use the fneg IR instruction, in place of the old fsub(-0,X) canonical form, since AMDGPU is the only backend currently checking the DenormalMode flags.

Note that this will require follow-up optimizations to make sure the FSUB(-0,X) form is handled appropriately

Differential Revision: https://reviews.llvm.org/D93243
 2021-01-04 14:44:10 -06:00
Matt Arsenault 5660bb6bc9 AMDGPU: Remove denormal subtarget features 
Switch to using the denormal-fp-math/denormal-fp-math-f32 attributes.
 2020-04-02 17:17:12 -04:00
Matt Arsenault 200b20639a AMDGPU: Use V_MAC_F32 for fmad.ftz 
This avoids regressions in a future patch. I'm confused by the use of
the gfx9 usage legacy_mad. Was this a pointless instruction rename, or
uses fmul_legacy handling? Why is regular mac avilable in that case?
 2020-03-10 14:41:06 -07:00
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