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 -~----------~----~----~----~------~----~------~--~---
