diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2025-06-10 15:48:37 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-06-10 15:48:37 +0100 |
| commit | e74d834cb155a894fa0f9dbd1483b7fef53a79ae (patch) | |
| tree | b7dd58f0537aacf4afbb195d3d1b036a009db72a /llvm/lib/Transforms/Utils/LoopUtils.cpp | |
| parent | 007d29e30c6e311501ed97b7a368521622319620 (diff) | |
| download | llvm-e74d834cb155a894fa0f9dbd1483b7fef53a79ae.zip llvm-e74d834cb155a894fa0f9dbd1483b7fef53a79ae.tar.gz llvm-e74d834cb155a894fa0f9dbd1483b7fef53a79ae.tar.bz2 | |
[X86] combineConcatVectorOps - concat mixed v2f64/v4f64 faux shuffles into v4f64/v8f64 vshufpd (#143521)
Replace getTargetShuffleMask call (only permitted for target shuffles)
and use getTargetShuffleInputs instead to match various faux shuffles
(insert+extract sequences in particular).
This does mean we have to explicitly bail out with undef/zero mask
elements, where before getTargetShuffleMask would handle them.
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUtils.cpp')
0 files changed, 0 insertions, 0 deletions