Mersenne Digest Monday, January 5 2004 Volume 01 : Number 1102
---------------------------------------------------------------------- Date: Sat, 3 Jan 2004 08:09:03 +0000 From: "Brian J. Beesley" <[EMAIL PROTECTED]> Subject: Re: Mersenne: Hyperthreading & ABIT IS7 On Saturday 03 January 2004 04:23, Terry S. Arnold wrote: > I just brought up a new box with P4 3.0 on an ABIT IS& MB. I only appear to > be getting 50% of the cycles for Prime95. I am running XP Pro SP1. > > How do I get the full power available to Prime95? Errm - are you sure the OS isn't counting cycles in the "virtual" processor as well as the real one? If you're getting reasonable iteration times (similar to those on the benchmarks page - well actually they should be a bit better if you're using the current version of prime95) then your system is working OK. If you really are getting only half the cycles then your iteration time will be about 2x those on the benchmarks page. Alternatively temporarily disable HTT in the BIOS & see how much your iteration time changes. Even so you should probably leave HTT on since it should improve interactive response when Prime95 is running in the background. Regards Brian Beesley _________________________________________________________________________ Unsubscribe & list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers ------------------------------ Date: Sat, 3 Jan 2004 08:09:03 +0000 From: "Brian J. Beesley" <[EMAIL PROTECTED]> Subject: Re: Mersenne: Hyperthreading & ABIT IS7 On Saturday 03 January 2004 04:23, Terry S. Arnold wrote: > I just brought up a new box with P4 3.0 on an ABIT IS& MB. I only appear to > be getting 50% of the cycles for Prime95. I am running XP Pro SP1. > > How do I get the full power available to Prime95? Errm - are you sure the OS isn't counting cycles in the "virtual" processor as well as the real one? If you're getting reasonable iteration times (similar to those on the benchmarks page - well actually they should be a bit better if you're using the current version of prime95) then your system is working OK. If you really are getting only half the cycles then your iteration time will be about 2x those on the benchmarks page. Alternatively temporarily disable HTT in the BIOS & see how much your iteration time changes. Even so you should probably leave HTT on since it should improve interactive response when Prime95 is running in the background. Regards Brian Beesley _________________________________________________________________________ Unsubscribe & list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers _________________________________________________________________________ Unsubscribe & list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers ------------------------------ Date: Sat, 3 Jan 2004 09:01:16 -0800 From: "Aaron" <[EMAIL PROTECTED]> Subject: RE: Mersenne: Hyperthreading & ABIT IS7 This is a question that has come up before. In a multi-processor system, the CPU graph in Task Manager will count *ALL* the processors as being equal to 100%. You can set Task Manager to show one graph per CPU which should help. *** Also, be sure you set the "Affinity" of Prime95 to run on ONLY the first CPU (the "real" one)! *** Otherwise the task scheduler could be switching your process between the real and virtual processor and that will seriously gum up how well it runs, especially for CPU intensive tasks like P95 is. In the P4's with the virtual processor, it will appear to the OS as 2 processors, but trust me, running 2 instances of Prime95 will not help. It does help out though when you run Prime95 and are using your machine for other things... You'll get more Prime95 cycles going and your other tasks can run in the virtual processor pretty well without robbing cycles from the LL tests. Aaron > -----Original Message----- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of > Terry S. Arnold > Sent: Friday, January 02, 2004 8:24 PM > To: [EMAIL PROTECTED] > Subject: Mersenne: Hyperthreading & ABIT IS7 > > I just brought up a new box with P4 3.0 on an ABIT IS& MB. I > only appear to be getting 50% of the cycles for Prime95. I am > running XP Pro SP1. > > How do I get the full power available to Prime95? > > Terry > > _Terry S. Arnold 2975 B Street San Diego, CA 92102 USA > [EMAIL PROTECTED] (619) 235-8181 (voice) (619) 235-0016 (fax) > > > ______________________________________________________________ > ___________ > Unsubscribe & list info -- http://www.ndatech.com/mersenne/signup.htm > Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers _________________________________________________________________________ Unsubscribe & list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers ------------------------------ Date: Mon, 05 Jan 2004 11:49:15 +0100 From: Matthias Waldhauer <[EMAIL PROTECTED]> Subject: Mersenne: Re: Different word sizes/accuracy for forward/inverse transform Colin Percival wrote: > At 21:46 +0100, 29 Dec 2003, Matthias Waldhauer wrote: > >> During my studies of FFT+NTT I got following idea: >> >> In case of FFT we have to provide enough bits per word to safely hold >> the squares of the values in frequency space without getting rounding >> errors during the inverse transform. But actually we don't need that >> many bits during the forward transform. > > > Sorry. Those bits are necessary; without them, the values being > squared aren't computed with sufficient precision. > > Colin Percival Thanks. I came to the same conclusion while visualizing the schoolboy method of multiplication. One shouldn't think about math problems during holidays ;) But what about the NTT variant of this idea? Would a mapping of one field or modular ring to another one be possible while using a DWT? Matthias Waldhauer _________________________________________________________________________ Unsubscribe & list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers ------------------------------ End of Mersenne Digest V1 #1102 *******************************