On Saturday 20 December 2008 03:54:01 Bill Hart wrote: > Hi jason, > > What hardware did you get a benchmark of 9000 on? The benchmark will
Sempron 1800Mhz > change depending on the speed of the processor and the type of > machine. > > It certainly sounds good in comparison with gmp. > > It is important not to increase the code size too much. It might make > one function faster, but eventually the code cache becomes overwhelmed > and slows everything down in practice. > I may try it sometime , to see what speedup I can get in the benchmarks , and then see what happens in the real world. > I have now finished working on FLINT 1.1 which was released today, so > officially I am now working on MPIR again. > > I'll create the mpir-0.9.0 directory in svn now. Then we can start > committing development code. > > Bill. > > 2008/12/18 <ja...@njkfrudils.plus.com>: > > I've tweeked some more speed from the mul_basecase function , and I now > > get a benchmark of 9000 (gmp-4.2.4 is 6000) . The current code is 1361 > > bytes long which includes 115 bytes for sizes <=2 . Further improvements > > can be made but they would increase the code size. We could separate out > > <=5 limbs , this would take an extra say 600? bytes , and save a branch > > in the outer loop , this should save a few cycles (say 2%?) in the real > > world. Another way is to pipeline the internal addmul_1's together , this > > would probably double the code size , and if I can get it to work , then > > we might get upto 10% more speed. > > While typing this I just had a thought , perhaps using CMOV would allow > > me to safely load the next limb ahead of the current iteration , have to > > see if it helps , if this can be made to work , then I wont need another > > "copy" for the last part of the pipeline. > > > > So any thoughts on how much code size would be too much , or does anyone > > have real world benchmarks. > > --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "mpir-devel" group. To post to this group, send email to mpir-devel@googlegroups.com To unsubscribe from this group, send email to mpir-devel+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/mpir-devel?hl=en -~----------~----~----~----~------~----~------~--~---
