diff options
| author | Alexey Bataev <a.bataev@outlook.com> | 2021-11-17 08:42:33 -0800 |
|---|---|---|
| committer | Alexey Bataev <a.bataev@outlook.com> | 2021-11-26 06:38:02 -0800 |
| commit | fc0aacf324b172309ee10334e2213e1b3df8ea45 (patch) | |
| tree | 2ddad1ea5a715fdcdbcbc8e6326986901f93e325 /lldb/source/Plugins/Process/gdb-remote/ProcessGDBRemote.h | |
| parent | f824bb0e36fc7099923f583e4eea4aaa7d296957 (diff) | |
| download | llvm-fc0aacf324b172309ee10334e2213e1b3df8ea45.zip llvm-fc0aacf324b172309ee10334e2213e1b3df8ea45.tar.gz llvm-fc0aacf324b172309ee10334e2213e1b3df8ea45.tar.bz2 | |
[SLP]Improve analysis/emission of vector operands for alternate nodes.
Compiler has an analysis for perfect diamond matching but it does not
support nodes with main/alternate opcodes. The problem is that the
scalars themselves are different and might not match directly with other
nodes, but operands and main/alternate opcodes might match and compiler
might reuse some previously emitted vector instructions. Need to include
this analysis in the cost model and actual vector instructions emission
process.
Differential Revision: https://reviews.llvm.org/D114101
Diffstat (limited to 'lldb/source/Plugins/Process/gdb-remote/ProcessGDBRemote.h')
0 files changed, 0 insertions, 0 deletions