diff options
| author | Artem Kroviakov <71938912+akroviakov@users.noreply.github.com> | 2024-05-28 14:54:37 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-28 14:54:37 +0200 |
| commit | 01fbc5658cdfa152519e2d0842ccf7d91aaeaeaf (patch) | |
| tree | eff853ca054be796f115441a47734b6b1854a97a /utils | |
| parent | 1da52caf2946e56f69eae75a60088a54edda1db5 (diff) | |
| download | llvm-01fbc5658cdfa152519e2d0842ccf7d91aaeaeaf.zip llvm-01fbc5658cdfa152519e2d0842ccf7d91aaeaeaf.tar.gz llvm-01fbc5658cdfa152519e2d0842ccf7d91aaeaeaf.tar.bz2 | |
[mlir][vector] Add support for linearizing Insert VectorOp in VectorLinearize (#92370)
Building on top of
[#88204](https://github.com/llvm/llvm-project/pull/88204), this PR adds
support for converting `vector.insert` into an equivalent
`vector.shuffle` operation that operates on linearized (1-D) vectors.
Diffstat (limited to 'utils')
0 files changed, 0 insertions, 0 deletions