diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2023-08-26 10:47:54 -0400 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2023-09-01 08:22:16 -0400 |
| commit | deefda7074398b7e8b7dae9dace43a8c694a49c1 (patch) | |
| tree | 02246428cfb4aa9e6955eb7c412f39e7627465a1 /lldb/source/Plugins/ScriptInterpreter/Python/PythonDataObjects.cpp | |
| parent | dac8f974b51b076773ec49603df4e627f4d9089c (diff) | |
AMDGPU: Use exp2 and log2 intrinsics directly for f16/f32
These codegen correctly but f64 doesn't. This prevents losing fast
math flags on the way to the underlying intrinsic.
https://reviews.llvm.org/D158997
Diffstat (limited to 'lldb/source/Plugins/ScriptInterpreter/Python/PythonDataObjects.cpp')
0 files changed, 0 insertions, 0 deletions