diff options
| author | David Green <david.green@arm.com> | 2025-01-30 22:17:34 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-01-30 22:17:34 +0000 |
| commit | ac7c199a63ddb7ba675e9da76dd07ffdbf07153a (patch) | |
| tree | 3bf0d3a850bc22be050520d25448afe47d9e5596 /lldb/source/Interpreter/CommandObject.cpp | |
| parent | b3458fdec5e183b49c634b72b828630bb6972400 (diff) | |
| download | llvm-ac7c199a63ddb7ba675e9da76dd07ffdbf07153a.zip llvm-ac7c199a63ddb7ba675e9da76dd07ffdbf07153a.tar.gz llvm-ac7c199a63ddb7ba675e9da76dd07ffdbf07153a.tar.bz2 | |
[AArch64][GlobalISel] Legalize more G_VECREDUCE_ADD operations. (#123392)
Non-power-2 vectors will now be padded with zero elements, smaller
vectors will be widened using anyext, which I believe will be better in
many situations than padding with zeros, although some small types may
prefer being scalarized depending on the code. Padding with zeros may
not be best for all sizes (v5i8 being the worst), we can hopefully
improve that in the future but they no longer fall back. We scalarize
other types like i128.
Diffstat (limited to 'lldb/source/Interpreter/CommandObject.cpp')
0 files changed, 0 insertions, 0 deletions