diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2019-06-16 15:29:03 +0000 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2019-06-16 15:29:03 +0000 |
| commit | c8d88ad1a916d7e877f28bce752e8f63b73b164a (patch) | |
| tree | a8d00159554757b13b40c0ff29bf97c71014edc8 /lldb/packages/Python/lldbsuite/test | |
| parent | 33b46a6df0b0c781eb8c6b93b0aac55680a26eff (diff) | |
| download | llvm-c8d88ad1a916d7e877f28bce752e8f63b73b164a.zip llvm-c8d88ad1a916d7e877f28bce752e8f63b73b164a.tar.gz llvm-c8d88ad1a916d7e877f28bce752e8f63b73b164a.tar.bz2 | |
[CodeGenPrepare][x86] shift both sides of a vector select when profitable
This is based on the example/discussion in PR37428:
https://bugs.llvm.org/show_bug.cgi?id=37428
Proper vector shift instructions don't appear until AVX2, so we may generate several
extra instructions within a loop trying to compensate for that. It's difficult to
recover from that shift expansion later than this, so use the existing TLI hook and
splat analysis to enable better codegen.
This extends CGP functionality introduced with:
rL201655
Differential Revision: https://reviews.llvm.org/D63233
llvm-svn: 363511
Diffstat (limited to 'lldb/packages/Python/lldbsuite/test')
0 files changed, 0 insertions, 0 deletions