diff options
author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2019-01-31 11:15:05 +0000 |
---|---|---|
committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2019-01-31 11:15:05 +0000 |
commit | 51c2efc104d14f763dbcaf5cd95fe4a3eb9561ac (patch) | |
tree | ad7772aac0bbe538a61bca4eb8971998e244c7c6 /llvm/lib/Support/CommandLine.cpp | |
parent | 9b127421b627a0e2dd0fa46fb327fb051fae918b (diff) | |
download | llvm-51c2efc104d14f763dbcaf5cd95fe4a3eb9561ac.zip llvm-51c2efc104d14f763dbcaf5cd95fe4a3eb9561ac.tar.gz llvm-51c2efc104d14f763dbcaf5cd95fe4a3eb9561ac.tar.bz2 |
[X86][AVX] Fold vt1 concat_vectors(vt2 undef, vt2 broadcast(x)) --> vt1 broadcast(x)
If we're not inserting the broadcast into the lowest subvector then we can avoid the insertion by just performing a larger broadcast.
Avoids a regression when we enable AVX1 broadcasts in shuffle combining
llvm-svn: 352742
Diffstat (limited to 'llvm/lib/Support/CommandLine.cpp')
0 files changed, 0 insertions, 0 deletions