diff options
author | Nadav Rotem <nrotem@apple.com> | 2013-09-03 21:33:17 +0000 |
---|---|---|
committer | Nadav Rotem <nrotem@apple.com> | 2013-09-03 21:33:17 +0000 |
commit | 5d78dba6d9602bcf5b6fdc11de00477b125b45a7 (patch) | |
tree | 339564aca9618602fc4427cfe764dfd3971d280c /clang/lib/CodeGen/CodeGenModule.cpp | |
parent | e7d67f2e01c4a49b1f7821946b4b103a51bcc895 (diff) | |
download | bcm5719-llvm-5d78dba6d9602bcf5b6fdc11de00477b125b45a7.tar.gz bcm5719-llvm-5d78dba6d9602bcf5b6fdc11de00477b125b45a7.zip |
Enable late-vectorization by default.
This patch changes the default setting for the LateVectorization flag that controls where the loop-vectorizer is ran.
Perf gains:
SingleSource/Benchmarks/Shootout/matrix -37.33%
MultiSource/Benchmarks/PAQ8p/paq8p -22.83%
SingleSource/Benchmarks/Linpack/linpack-pc -16.22%
SingleSource/Benchmarks/Shootout-C++/ary3 -15.16%
MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt -10.34%
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl -7.12%
Regressions:
SingleSource/Benchmarks/Misc/lowercase 15.10%
MultiSource/Benchmarks/TSVC/Equivalencing-flt/Equivalencing-flt 13.18%
SingleSource/Benchmarks/Shootout-C++/matrix 8.27%
SingleSource/Benchmarks/CoyoteBench/lpbench 7.30%
llvm-svn: 189858
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions