diff options
| author | peterbell10 <peterbell10@openai.com> | 2025-03-29 01:31:33 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-03-29 01:31:33 +0000 |
| commit | 55430f8673b9f8b27779faad3fe9c59954d539df (patch) | |
| tree | 25fdcf996c86e5b4483a95d80d2742c55a9eebc2 /llvm/lib/Target/RISCV/Disassembler/RISCVDisassembler.cpp | |
| parent | 22a11be8ab6f31cd3621f37d675e44988218f314 (diff) | |
| download | llvm-55430f8673b9f8b27779faad3fe9c59954d539df.zip llvm-55430f8673b9f8b27779faad3fe9c59954d539df.tar.gz llvm-55430f8673b9f8b27779faad3fe9c59954d539df.tar.bz2 | |
[NVPTX] Customize getScalarizationOverhead (#128077)
We've observed that the SLPVectorizer is too conservative on NVPTX
because it over-estimates the cost to build a vector. PTX has a single
`mov` instruction that can build e.g. `<2 x half>` vectors from scalars,
however the SLPVectorizer over-estimates it as the cost of 2 insert
elements.
To fix this I customize `getScalarizationOverhead` to lower the cost for
building 2x16 types.
Diffstat (limited to 'llvm/lib/Target/RISCV/Disassembler/RISCVDisassembler.cpp')
0 files changed, 0 insertions, 0 deletions