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
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
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
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
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
Matt Arsenault