diff options
author | Jay Foad <jay.foad@amd.com> | 2020-09-24 16:52:41 +0100 |
---|---|---|
committer | Jay Foad <jay.foad@amd.com> | 2020-09-28 10:16:51 +0100 |
commit | 2806f586dca78756cc2fbadf09c0859dda4a760e (patch) | |
tree | 506e977544b851d78ddd33ad90167a040b990b2c /lldb/unittests/ScriptInterpreter/Python | |
parent | 286d3fc7500dfa6a947b217d0e87d1764d2242b8 (diff) | |
download | llvm-2806f586dca78756cc2fbadf09c0859dda4a760e.zip llvm-2806f586dca78756cc2fbadf09c0859dda4a760e.tar.gz llvm-2806f586dca78756cc2fbadf09c0859dda4a760e.tar.bz2 |
[AMDGPU] Make bfi patterns divergence-aware
This tends to increase code size but more importantly it reduces vgpr
usage, and could avoid costly readfirstlanes if the result needs to be
in an sgpr.
Differential Revision: https://reviews.llvm.org/D88245
Diffstat (limited to 'lldb/unittests/ScriptInterpreter/Python')
0 files changed, 0 insertions, 0 deletions