diff options
| author | Joe Ellis <joe.ellis@arm.com> | 2020-12-16 09:01:28 +0000 |
|---|---|---|
| committer | Joe Ellis <joe.ellis@arm.com> | 2020-12-16 12:24:32 +0000 |
| commit | dad07baf123e672b1d5d5e7c21e73b92399d5a0c (patch) | |
| tree | 0df608812c948e217df4ca1c1f25e02e443779f5 /llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp | |
| parent | 9322e571d7356a9a0e86aab954c3a916f0f07855 (diff) | |
| download | llvm-dad07baf123e672b1d5d5e7c21e73b92399d5a0c.zip llvm-dad07baf123e672b1d5d5e7c21e73b92399d5a0c.tar.gz llvm-dad07baf123e672b1d5d5e7c21e73b92399d5a0c.tar.bz2 | |
[clang][AArch64][SVE] Avoid going through memory for VLAT <-> VLST casts
This change makes use of the llvm.vector.extract intrinsic to avoid
going through memory when performing bitcasts between vector-length
agnostic types and vector-length specific types.
Depends on D91362
Reviewed By: c-rhodes
Differential Revision: https://reviews.llvm.org/D92761
Diffstat (limited to 'llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp')
0 files changed, 0 insertions, 0 deletions