On 27/02/2014 21:48, Bill Hart wrote: > I've updated the code that is relevant for mpz_fac_ui from GMP 5.1.3. > > The new files associated with this are: > > mpn/generic/comb_tables.c > mpz/oddfac_1.c > mpz/prodlimbs.c > nextprime.c > primesieve.c > > Brian, you might like to add these to the Windows build.
Done. > There is more to come I think. There seem to be some additional > factorial functions, double factorial, binomial central series, > primorial, etc. I'll work on them tomorrow. > > Everything should vaguely work at this point though. If not, please let > me know. > > On Penryn, the fac_ui benchmark now shows that we have pretty much > caught up to GMP (sometimes beating it) for this part of the benchmark. > > I think our overall bench on the base functions is now just higher than > GMP's on penryn, though there are still some points where I need to make > some improvements, such as very unbalanced multiplication and > asymptotically fast division. I tried tuning this on Windows but it didn't doo to well. But tuning is supect on Windows so I will try the linux tuning for SandyBridge/Ivy Bridge when this is available. Brian -- You received this message because you are subscribed to the Google Groups "mpir-devel" group. To unsubscribe from this group and stop receiving emails from it, send an email to mpir-devel+unsubscr...@googlegroups.com. To post to this group, send email to mpir-devel@googlegroups.com. Visit this group at http://groups.google.com/group/mpir-devel. For more options, visit https://groups.google.com/groups/opt_out.