diff options
| author | Konstantin Zhuravlyov <kzhuravl_dev@outlook.com> | 2018-02-27 21:48:05 +0000 |
|---|---|---|
| committer | Konstantin Zhuravlyov <kzhuravl_dev@outlook.com> | 2018-02-27 21:48:05 +0000 |
| commit | d6b3453bdb30cbef3e03f820df3125f9a409308c (patch) | |
| tree | 18b193975ebab7f75cf390f6eacff0a336995431 /lldb/packages/Python/lldbsuite/test/sample_test/TestSampleTest.py | |
| parent | 22d838cd31aa78c250034ad03c5f8ba3541427e4 (diff) | |
| download | bcm5719-llvm-d6b3453bdb30cbef3e03f820df3125f9a409308c.tar.gz bcm5719-llvm-d6b3453bdb30cbef3e03f820df3125f9a409308c.zip | |
AMDGPU: Define FP_FAST_FMA{F} macros for amdgcn
- Expand GK_*s (i.e. GFX6 -> GFX600, GFX601, etc.)
- This allows us to choose features correctly in some cases (for example, fast fmaf is available on gfx600, but not gfx601)
- Move HasFMAF, HasFP64, HasLDEXPF to GPUInfo tables
- Add HasFastFMA, HasFastFMAF to GPUInfo tables
- Add missing tests
llvm-svn: 326254
Diffstat (limited to 'lldb/packages/Python/lldbsuite/test/sample_test/TestSampleTest.py')
0 files changed, 0 insertions, 0 deletions
