diff options
| author | Evan Cheng <evan.cheng@apple.com> | 2010-05-20 06:13:19 +0000 |
|---|---|---|
| committer | Evan Cheng <evan.cheng@apple.com> | 2010-05-20 06:13:19 +0000 |
| commit | bdd062dae0f27953ec77039a171d0f2b8fe72dfc (patch) | |
| tree | 4622fd6ccaeacd89ac38f69a12a317d31cf3f31e /clang/lib/CodeGen/CGExpr.cpp | |
| parent | aa2ac80eaaaea7d99e1efecf52abb4b167dc11c8 (diff) | |
| download | bcm5719-llvm-bdd062dae0f27953ec77039a171d0f2b8fe72dfc.tar.gz bcm5719-llvm-bdd062dae0f27953ec77039a171d0f2b8fe72dfc.zip | |
Add a hybrid bottom up scheduler that reduce register usage while avoiding
pipeline stall. It's useful for targets like ARM cortex-a8. NEON has a lot
of long latency instructions so a strict register pressure reduction
scheduler does not work well.
Early experiments show this speeds up some NEON loops by over 30%.
llvm-svn: 104216
Diffstat (limited to 'clang/lib/CodeGen/CGExpr.cpp')
0 files changed, 0 insertions, 0 deletions
