diff options
| author | Ahmed Bougacha <ahmed.bougacha@gmail.com> | 2017-02-10 19:51:47 +0000 |
|---|---|---|
| committer | Ahmed Bougacha <ahmed.bougacha@gmail.com> | 2017-02-10 19:51:47 +0000 |
| commit | 2e275e272f09e85e393058a885625ffa3f2502a6 (patch) | |
| tree | a6c3c5d9ab40dd532f2658beef2a16f5eedeb36a /llvm/lib/CodeGen/DeadMachineInstructionElim.cpp | |
| parent | 3817e4a40c90883a34be5257c1c7e42b5825e124 (diff) | |
| download | bcm5719-llvm-2e275e272f09e85e393058a885625ffa3f2502a6.tar.gz bcm5719-llvm-2e275e272f09e85e393058a885625ffa3f2502a6.zip | |
[X86] Bitcast subvector before broadcasting it.
Since r274013, we've been looking through bitcasts on broadcast inputs.
In the scalar-folding case (from a load, build_vector, or sc2vec),
the input type didn't matter, as we'd simply bitcast the resulting
scalar back.
However, when broadcasting a 128-bit-lane-aligned element, we create an
EXTRACT_SUBVECTOR. Use proper types, by creating an extract_subvector
of the original input type.
llvm-svn: 294774
Diffstat (limited to 'llvm/lib/CodeGen/DeadMachineInstructionElim.cpp')
0 files changed, 0 insertions, 0 deletions
