a1fe17c9ad
AMDGPU: Change fdiv lowering based on !fpmath metadata
...
If 2.5 ulp is acceptable, denormals are not required, and
isn't a reciprocal which will already be handled, replace
with a faster fdiv.
Simplify the lowering tests by using per function
subtarget features.
llvm-svn: 276051
2016-07-19 23:16:53 +00:00
dfec5ce032
AMDGPU: Fix fdiv lowering when f32 denormals supported
...
Also fix test not actually using function labels.
llvm-svn: 274969
2016-07-09 07:48:11 +00:00
ed0f97fad2
AMDGPU/SI: Fix 32-bit fdiv lowering
...
We were using the fast fdiv lowering for all division, implementation of
IEEE754 fdiv is added.
http://reviews.llvm.org/D20557
llvm-svn: 272292
2016-06-09 19:17:15 +00:00
538d09d0dd
Revert "Differential Revision: http://reviews.llvm.org/D20557 "
...
Author: Wei Ding <wei.ding2@amd.com>
Date: Tue Jun 7 19:04:44 2016 +0000
Differential Revision: http://reviews.llvm.org/D20557
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@272044
91177308-0d34-0410-b5e6-96231b3b80d8
as it was breaking the bots.
This reverts commit r272044.
llvm-svn: 272056
2016-06-07 20:27:12 +00:00
a70216f1b3
Differential Revision: http://reviews.llvm.org/D20557
...
llvm-svn: 272044
2016-06-07 19:04:44 +00:00
6689abe632
AMDGPU: Run r600 tests last
...
llvm-svn: 268672
2016-05-05 20:07:37 +00:00
45bb48ea19
R600 -> AMDGPU rename
...
llvm-svn: 239657
2015-06-13 03:28:10 +00:00
Matt Arsenault