diff options
| author | alex-t <alexander.timofeev@amd.com> | 2021-12-24 17:40:49 +0300 |
|---|---|---|
| committer | alex-t <alexander.timofeev@amd.com> | 2022-01-26 15:33:10 +0300 |
| commit | 5157f984ae2c5e6fe9a8bd3a5dae99d5a96a276d (patch) | |
| tree | d27aa75de49740b31d8152eb51d095ad7f0df986 /llvm/lib/TextAPI/Architecture.cpp | |
| parent | bfd5696b55cb80011162346ce7e234ebfe0447c3 (diff) | |
| download | llvm-5157f984ae2c5e6fe9a8bd3a5dae99d5a96a276d.zip llvm-5157f984ae2c5e6fe9a8bd3a5dae99d5a96a276d.tar.gz llvm-5157f984ae2c5e6fe9a8bd3a5dae99d5a96a276d.tar.bz2 | |
[AMDGPU] Enable divergence-driven XNOR selection
Currently not (xor_one_use) pattern is always selected to S_XNOR irrelative od the node divergence.
This relies on further custom selection pass which converts to VALU if necessary and replaces with V_NOT_B32 ( V_XOR_B32)
on those targets which have no V_XNOR.
Current change enables the patterns which explicitly select the not (xor_one_use) to appropriate form.
We assume that xor (not) is already turned into the not (xor) by the combiner.
Reviewed By: rampitec
Differential Revision: https://reviews.llvm.org/D116270
Diffstat (limited to 'llvm/lib/TextAPI/Architecture.cpp')
0 files changed, 0 insertions, 0 deletions