diff options
| author | Michael Kuperstein <michael.m.kuperstein@intel.com> | 2014-12-04 13:49:51 +0000 |
|---|---|---|
| committer | Michael Kuperstein <michael.m.kuperstein@intel.com> | 2014-12-04 13:49:51 +0000 |
| commit | 0492bd2b9e4557b4547e5ed5e8fbad8bab38da4c (patch) | |
| tree | 316cf06c62ebdc8e4519f24ff7f2db275cd66d3b /llvm/lib/Support/MemoryBuffer.cpp | |
| parent | c9bcffd20111eff93cf1fe3fda905ea5aeddaf92 (diff) | |
| download | llvm-0492bd2b9e4557b4547e5ed5e8fbad8bab38da4c.zip llvm-0492bd2b9e4557b4547e5ed5e8fbad8bab38da4c.tar.gz llvm-0492bd2b9e4557b4547e5ed5e8fbad8bab38da4c.tar.bz2 | |
[X86] Improve a dag-combine that handles a vector extract -> zext sequence.
The current DAG combine turns a sequence of extracts from <4 x i32> followed by zexts into a store followed by scalar loads.
According to measurements by Martin Krastev (see PR 21269) for x86-64, a sequence of an extract, movs and shifts gives better performance. However, for 32-bit x86, the previous sequence still seems better.
Differential Revision: http://reviews.llvm.org/D6501
llvm-svn: 223360
Diffstat (limited to 'llvm/lib/Support/MemoryBuffer.cpp')
0 files changed, 0 insertions, 0 deletions