a8fcfadf46
AMDGPU: Check if users of fneg can fold mods
...
In multi-use cases this can save a few instructions.
llvm-svn: 293962
2017-02-02 23:21:23 +00:00
7aad8fd8f4
Enable FeatureFlatForGlobal on Volcanic Islands
...
This switches to the workaround that HSA defaults to
for the mesa path.
This should be applied to the 4.0 branch.
Patch by Vedran Miletić <vedran@miletic.net>
llvm-svn: 292982
2017-01-24 22:02:15 +00:00
a6867fd441
AMDGPU: Combine fp16/fp64 subtarget features
...
The same control register controls both, and are set to
the same defaults. Keep the old names around as aliases.
llvm-svn: 292837
2017-01-23 22:31:03 +00:00
4103a81d6d
AMDGPU: Fold fneg into fmul
...
Patch mostly by Fiona Glaser
llvm-svn: 291732
2017-01-12 00:23:20 +00:00
2a04ff97ad
AMDGPU: Pull fneg/fabs out of a select
...
Allows better source modifier usage.
llvm-svn: 291729
2017-01-11 23:57:38 +00:00
e7d8ed32f9
AMDGPU: Swap order of operands in fadd/fsub combine
...
FMA is canonicalized to constant in the middle operand. Do
the same so fmad matches and avoid an extra combine step.
llvm-svn: 290313
2016-12-22 04:03:40 +00:00
ef82ad94ea
AMDGPU: Enable some f32 fadd/fsub combines for f16
...
llvm-svn: 290308
2016-12-22 03:40:39 +00:00
d1ceffcd5a
AMDGPU: Run fp combine tests on VI
...
llvm-svn: 290192
2016-12-20 18:55:11 +00:00
bbb47da8a1
AMDGPU: Support commuting with immediate in src0
...
llvm-svn: 280970
2016-09-08 17:19:29 +00:00
44e5483ada
AMDGPU: Add volatile to test loads and stores
...
When the memory vectorizer is enabled, these tests break.
These tests don't really care about the memory instructions,
and it's easier to write check lines with the unmerged loads.
llvm-svn: 266071
2016-04-12 13:38:18 +00:00
cabe02e141
Only do fmul (fadd x, x), c combine if the fadd only has one use
...
This was increasing the instruction count if the fadd has multiple uses.
llvm-svn: 242498
2015-07-17 01:14:35 +00:00
Matt Arsenault