[PATCH] D132208: [LoopIntWrapPredication] Loop Integer Wrapping Predication Pass

[Florian Hahn via Phabricator via llvm-commits]

fhahn added a comment.

In D132208#3734597 <https://reviews.llvm.org/D132208#3734597>, @kachkov98 wrote:

> test-suite statistics:
>
>   Tests: 2428
>   Metric: loop-int-wrap-predication.NumPredicatedChains
>   
>   Program                                       loop-int-wrap-predication.NumPredicatedChains                              
>   MultiSourc.../Applications/JM/ldecod/ldecod    30.00                                       
>   MultiSourc...chmarks/Prolangs-C/agrep/agrep    18.00                                       
>   MultiSourc.../Applications/JM/lencod/lencod    11.00                                       
>   MultiSourc...ch/consumer-lame/consumer-lame     7.00                                       
>   MultiSourc...e/Applications/ClamAV/clamscan     6.00                                       
>   MultiSourc...reeBench/fourinarow/fourinarow     5.00                                       
>   MultiSourc...Benchmarks/7zip/7zip-benchmark     4.00                                       
>   MultiSourc.../DOE-ProxyApps-C++/CLAMR/CLAMR     4.00                                       
>   MultiSourc...nch/mpeg2/mpeg2dec/mpeg2decode     2.00                                       
>   MultiSourc...arks/Rodinia/backprop/backprop     2.00                                       
>   MultiSourc...ch/consumer-jpeg/consumer-jpeg     1.00                                       
>   MultiSourc.../mediabench/jpeg/jpeg-6a/cjpeg     1.00                                       
>   MultiSourc...enchmarks/mafft/pairlocalalign     1.00

Do you have also have numbers on impact of runtime performance on a wider range of benchmarks like SPEC & co?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D132208/new/

https://reviews.llvm.org/D132208