dear R wizards: while extolling the virtues of R, one of my young econometrics colleagues told me that he still wants to run ox because [a] his code is written in it (good reason); [b] because ox seems to be faster than R in most benchmarks (huh?). this got me to wonder. language speed can't matter much, so it must be mostly the underlying matrix algebra by now. I presume that nowadays most of the plain matrix operation speed depends primarily on which hardware features the library accesses. (The basic algorithms aren't so different, so even though the algorithm may have mattered a long time ago, they are probably pretty similar nowadays. hmmm...maybe matrix inversion still is different, but multiplication and adding should not be.) On x86 architecture, I believe there is a hierarchy in terms of raw processing power: FPU < SSE* < GPU. is it even possible to use the GPU now for math processing (linux or windows), and specifically in R? assuming I compile everything with the proper SSE flags and atlas, is SSE* fully taken advantage of? regards, /ivo
You (and your colleague) might want to have a look at http://www.sciviews.org/benchmark/. It's a bit dated, but still may be a good starting point. Some months ago some one asked about working on getting R to use the GPU for computation on the R-devel list. Don't know if anything came of it. Cheers, Andy From: ivo welch> > dear R wizards: > > while extolling the virtues of R, one of my young > econometrics colleagues told me that he still wants to run ox > because [a] his code is written in it (good reason); [b] > because ox seems to be faster than R in most benchmarks (huh?). > > this got me to wonder. language speed can't matter much, so > it must be mostly the underlying matrix algebra by now. I > presume that nowadays most of the plain matrix operation > speed depends primarily on which hardware features the > library accesses. (The basic algorithms aren't so different, > so even though the algorithm may have mattered a long time > ago, they are probably pretty similar nowadays. hmmm...maybe > matrix inversion still is different, but multiplication and > adding should not be.) > > On x86 architecture, I believe there is a hierarchy in terms > of raw processing power: FPU < SSE* < GPU. > > is it even possible to use the GPU now for math processing > (linux or windows), and specifically in R? > > assuming I compile everything with the proper SSE flags and atlas, is > SSE* fully taken advantage of? > > regards, > > /ivo > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide! > http://www.R-project.org/posting-guide.html > >
The benchmark report is good stuff - I've been wondering about these speed issues recently myself. Has anyone tried something similar on 64-bit Linux or other OS? I'm contemplating switching to 64-bit Linux if I'll get some dramatic cycle time improvements. Anyone have any experience with this? Best, John -----Original Message----- From: r-help-bounces at stat.math.ethz.ch [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Liaw, Andy Sent: Friday, June 02, 2006 10:01 AM To: ivo welch; r-help at stat.math.ethz.ch Subject: Re: [R] speed? You (and your colleague) might want to have a look at http://www.sciviews.org/benchmark/. It's a bit dated, but still may be a good starting point. Some months ago some one asked about working on getting R to use the GPU for computation on the R-devel list. Don't know if anything came of it. Cheers, Andy From: ivo welch> > dear R wizards: > > while extolling the virtues of R, one of my young > econometrics colleagues told me that he still wants to run ox > because [a] his code is written in it (good reason); [b] > because ox seems to be faster than R in most benchmarks (huh?). > > this got me to wonder. language speed can't matter much, so > it must be mostly the underlying matrix algebra by now. I > presume that nowadays most of the plain matrix operation > speed depends primarily on which hardware features the > library accesses. (The basic algorithms aren't so different, > so even though the algorithm may have mattered a long time > ago, they are probably pretty similar nowadays. hmmm...maybe > matrix inversion still is different, but multiplication and > adding should not be.) > > On x86 architecture, I believe there is a hierarchy in terms > of raw processing power: FPU < SSE* < GPU. > > is it even possible to use the GPU now for math processing > (linux or windows), and specifically in R? > > assuming I compile everything with the proper SSE flags and atlas, is > SSE* fully taken advantage of? > > regards, > > /ivo > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide! > http://www.R-project.org/posting-guide.html > >______________________________________________ R-help at stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html