OK, I see there is now a K8-experimental, so I'll hold off on making another copy for now. Once Jason Martin has finished with the GCD patches I/someone will make the copy.
Bill. 2008/12/20 Bill Hart <goodwillh...@googlemail.com>: > Hi jason, > > What hardware did you get a benchmark of 9000 on? The benchmark will > 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 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 -~----------~----~----~----~------~----~------~--~---