Hi Brian, Nice graphs!!
Nothing there surprises me at all. I think it is clear that your mobile Core 2 has some architectural differences which we are consistently seeing. I would not be concerned about it. The results from Jeff seem ultra consistent with the other Core 2 results. It does surprise me that the core isn't identical, but perhaps for power consumption reasons they had to change a few things, such as cache latency, number of reservations stations, instruction fusion or pipeline length. Somehow I doubt the last three would be different, as the main architectural differences between Core Duo and Core 2 Duo consist in those, but I could believe the L2 cache latency was different. Obviously the Apple results are a bit slower due to the fact that we can't statically link. You certainly see that the Intel machines are better at shifting than the AMD's due to their better implementation of SSE2. And the AMD's are better at multiplication due to lower latencies for at least the first half of the multiplication. I'll bet the K10 would be better at both. I have to do some work on a K10, converting Jason's code, in a few minutes, so as I need to run speed for all the functions to make sure I don't botch anything, I'll send the results to you. Bill. 2009/3/4 Cactus <rieman...@googlemail.com>: > > Hi All, > > Jeff kindly sent me figures on the performance of the assembler code > on two kore architectures, both Core 2, one Linux and one Vista. So I > have uploaded a number of graphs giving the results for the six > architectures we now have reports on. I would be most grateful if you > folk who understand these architectures could take a look at these > graphs and let me know what you think. > > If any of you think that there are six processors listed and only five > graphs, it turns out that Jeffs Core 2 Vista figures and my Core2 > Vista figures are identical on most graphs and overlay each other. > > I am not sure what this means. It could mean that the code is working > differently on Windows and is sometimes slower. Or it could mean that > my port of speed is not working properly on Windows. Or it could mean > that the two processors in question really are close to identical in > performance. > > My thanks to everyine who has reported results. > > Brian > > > > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---