2015-04-02 20:59 GMT+08:00 Maciej W. Rozycki <macro@xxxxxxxxxxxxxx>: > I'm not sure if any such other superscalar MIPS pipeline implementation > exists, but if written correctly then at worst it won't hurt anyone else, > so just make sure your change does not regress scalar MIPS pipelines. I > hope you have a way to verify it. > > Maciej It seems the P-Class of Warrior generation of MIPS CPU has a superscalar MIPS pipeline(http://imgtec.com/mips/warrior/pclass.asp). Anyway, I've written a small benchmark at http://dev.lemote.com/files/upload/software/csum-opti/csum-test.tar.gz Someone can download and modify it: 1. config.h 2. change NR_ITERATION to a proper value in bench.c And run 'make run_bench', which will: 1) run a benchmark; 2) generate the result of `before-opti vs after-opti'; 3) invoke a python script(parse.py) to preprocess the result. Then paste the content of benchresult.txt to Calc / Excel / Numeric, etc and analyze it. -- Regards, - cee1
