diff options
| author | Hal Finkel <hfinkel@anl.gov> | 2012-06-09 03:14:50 +0000 |
|---|---|---|
| committer | Hal Finkel <hfinkel@anl.gov> | 2012-06-09 03:14:50 +0000 |
| commit | eb50c2d4a49941b58711d98e7e0d7e30fbcd90d8 (patch) | |
| tree | 42aa201ecc4e99c5859916e4c7c3326235c886db /clang/lib/CodeGen/ModuleBuilder.cpp | |
| parent | 091b87bb9dc20e7c2cec4ee43bc0647e47bd557a (diff) | |
| download | llvm-eb50c2d4a49941b58711d98e7e0d7e30fbcd90d8.zip llvm-eb50c2d4a49941b58711d98e7e0d7e30fbcd90d8.tar.gz llvm-eb50c2d4a49941b58711d98e7e0d7e30fbcd90d8.tar.bz2 | |
Enable tail merging on PPC.
Tail merging had been disabled on PPC because it would disturb bundling decisions
made during pre-RA scheduling on the 970 cores. Now, however, all bundling decisions
are made during post-RA scheduling, and tail merging is generally beneficial (the
average test-suite speedup is insignificantly positive).
Largest test-suite speedups:
MultiSource/Benchmarks/mediabench/gsm/toast/toast - 30%
MultiSource/Benchmarks/BitBench/uuencode/uuencode - 23%
SingleSource/Benchmarks/Shootout-C++/ary - 21%
SingleSource/Benchmarks/Stanford/Queens - 17%
Largest slowdowns:
MultiSource/Benchmarks/MiBench/security-sha/security-sha - 24%
MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 22%
MultiSource/Applications/JM/ldecod/ldecod - 14%
MultiSource/Benchmarks/mediabench/g721/g721encode/encode - 9%
This is improved by using full (instead of just critical) anti-dependency breaking,
but doing so still causes miscompiles and so cannot yet be enabled by default.
llvm-svn: 158259
Diffstat (limited to 'clang/lib/CodeGen/ModuleBuilder.cpp')
0 files changed, 0 insertions, 0 deletions