Yes, you are right. I somehow managed to confuse myself, even though I had noticed it was multiplications per second. Not sure how I managed that.
At any rate, the new MPIR FFT (coming in the next version) will hopefully help. It's easier to parallelise too. But eventually GPU will probably win out. I think CPU manufacturers might move in that direction and the two become one. Bill. On 16 March 2012 00:12, Dann Corbit <[email protected]> wrote: > -----Original Message----- > From: [email protected] [mailto:[email protected]] On > Behalf Of Bill Hart > Sent: Thursday, March 15, 2012 4:52 PM > To: [email protected] > Subject: Re: [mpir-devel] > > I was looking at table 2 where the scale is multiplications per second, i.e. > higher is better. But I might be misreading their data. > > I'm not sure if it is fair to compare a single CPU core with all cores of a > GPU. That might depend on the application. > > I wonder as well whether dedicated parallel code for the CPU might do better. >>> > They do perform this test. For instance, article page 374 > > Size in Core 2 Core i7 GTX 295 GTX > 295 GTX 480 > K bits Q6600 870 Old Code New > Code New Code > ---------------- --------- ---------- ----------- > ------------- ------------- > 16320 x 16320 12.81 17.01 2.59 > 35.92 103.45 > > Shows for 4 threads on Core i7, 16320 bit multiplication performs 17 > multiplications per second on Corei7 and 103 multiplications per second on > GTX 480 card. > That is where I came up with the figure of "6 times faster" in my original > email. > > Of course, at this point, it is nothing but angels dancing on pinheads for > the MPIR project because we do not know for sure how the figures would > translate to a different system. > << > > -- > You received this message because you are subscribed to the Google Groups > "mpir-devel" group. > To post to this group, send email to [email protected]. > To unsubscribe from this group, send email to > [email protected]. > For more options, visit this group at > http://groups.google.com/group/mpir-devel?hl=en. > -- You received this message because you are subscribed to the Google Groups "mpir-devel" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/mpir-devel?hl=en.
