diff options
| author | Florian Hahn <flo@fhahn.com> | 2025-07-03 09:49:32 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-03 08:49:32 +0100 |
| commit | 4acdb8e14ef7e72d5f56b45d51de72c7b797be03 (patch) | |
| tree | 83963fb74bb55747a02555bde5244a62352e167e /llvm/lib/Target/RISCV/Disassembler/RISCVDisassembler.cpp | |
| parent | 3efa461d45a1867cf03d30bd4b6caf1ed2260475 (diff) | |
| download | llvm-4acdb8e14ef7e72d5f56b45d51de72c7b797be03.zip llvm-4acdb8e14ef7e72d5f56b45d51de72c7b797be03.tar.gz llvm-4acdb8e14ef7e72d5f56b45d51de72c7b797be03.tar.bz2 | |
[VectorCombine] Scalarize extracts of ZExt if profitable. (#142976)
Add a new scalarization transform that tries to convert extracts of a
vector ZExt to a set of scalar shift and mask operations. This can be
profitable if the cost of extracting is the same or higher than the cost
of 2 scalar ops. This is the case on AArch64 for example.
For AArch64,this shows up in a number of workloads, including av1aom,
gmsh, minizinc and astc-encoder.
PR: https://github.com/llvm/llvm-project/pull/142976
Diffstat (limited to 'llvm/lib/Target/RISCV/Disassembler/RISCVDisassembler.cpp')
0 files changed, 0 insertions, 0 deletions