Re: Mersenne: P-1 Puzzle
- Original Message - From: Brian J. Beesley [EMAIL PROTECTED] To: Daran [EMAIL PROTECTED]; [EMAIL PROTECTED]; Anurag Garg [EMAIL PROTECTED] Sent: Tuesday, June 11, 2002 8:23 PM Subject: Re: Mersenne: P-1 Puzzle On Tuesday 11 June 2002 06:13, Daran wrote: [... snip ... interesting but non-contentious] Very noticable is the proportion of exponents - in all three ranges - which are not getting a stage two effort at all. 26 out the 85 exponents between 795 and 796000, 24 out of 54 between 1550 and 15505000, 35 out of 57 between 33219000 and 33223000. I do not believe that large numbers of P4 systems are being shipped with just 8MB of RAM! This is true. However the philosophy of the project, correctly in my view, is that the software should not cause noticeable deterioration in the performance of a system when it is being run in the background to normal work. I agree. My remarks were intended to make the case for spinning P-1 off into a separate work type, (yeah, I know, it's difficult to change the server code), and to encourage other readers of this list to consider focussing on P-1 work. [...] The default has to be safe;... Again, I agree. While there will be some people who have made a deliberate decision not to allocate extra memory, in many cases people will simply have accepted the default, which means that some machines which could allocate more memory to stage 2 without adversely affecting the user won't be configured to do this. However that same tendency to accept defaults puts GIMPS programmers under an obligation to set those defaults conservatively. ...IMO the current default memory allowance of 8MB is entirely reasonable, even though it causes P-1 to run stage 1 only for any realistic assignment, and even though _new_ systems are usually delivered with at least 256 MB RAM. Against that is the observation that the basic memory footprint has barely changed in the over three years I've been with the project, while typical system memory has increased by a factor of four or more. A default set to 10% of available memory would allow a 256MB system to perform a modest stage 2 on low assignments in the test range, and on DC assignments, while still using proportionately less memory than three years ago. The effect of this could be further mitigated if the memory dialog included radio buttons to limit further the memory usage to 'minimum' (default), with other options being 'reasonable' and 'desireable', (as described in the helpfile) as well as 'maximum', and 'Do not run'. Thus the default would be to run a minimal stage 2 provided it could be done in 10% of system memory or less. I would consider this to be reasonable and conservative. Running P-1 on a 10 million digit exponent requires in excess of 64 MB memory to be allocated in order to run stage 2 at all. That's a lot to ask as a default! It is. OTOH if the box has 1GB installed, then it's not so much. Regards Brian Beesley Daran _ Unsubscribe list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Mersenne: Slow Pentium 4 question
I think my P4 is running like a P III, at one third speed doing Mersenne Prime testing. When I run Prime95v22 it reports my P4 as CPU features: RDTSC, CMOV, PREFETCH, MMX If I change the CPUtype to 12 (P4) and add SSE to the local.ini file, as in ... CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE nothing changes. If I change SSE to SSE2 the system crashes with an illegal instruction message. I am running Prime 95 on a 256 meg. P4-1600 with 8k L1 and 256K L2 on Windows 95A I'm entertaining these theories: Windows 95a without drivers? doesn't support a P4. (Is it being asked to?) I don't really have a P4. (I bought this system expecting P4 performance running Prime95) L1 cache too small. L2 cache too small Something else. Comments/theories/assertions/wild hairs are invited. My best times my P4 1600 256 meg 133SDRAM Best time for 256K FFT length: 57.218 ms. Best time for 320K FFT length: 71.299 ms. Best time for 384K FFT length: 86.423 ms. Best time for 448K FFT length: 102.487 ms. Best time for 512K FFT length: 115.680 ms. Best time for 640K FFT length: 148.042 ms. Best time for 768K FFT length: 184.596 ms. Best time for 892K FFT length: 214.233 ms. Best time for 1024K FFT length: 250.226 ms. Best time for 1280K FFT length: 320.198 ms. Best time for 1536K FFT length: 386.440 ms. Best time for 1792K FFT length: 467.666 ms. From the Benchmark site P4 1500 133SDRAM 256 Full 0.019 0.024 0.030 0.035 0.040 0.052 0.063 0.079 0.087 0.120 0.154 0.196 19 24 30 35 40 52 63 79 87 120 154 196 Mersenne benchmark times from http://www.mersenne.org\bench.htm P III 1 gig times are below Intel(R) Pentium(R) III processor CPU speed: 996.59 MHz CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE L1 cache size: 16 KB L2 cache size: 256 KB L1 cache line size: 32 bytes L2 cache line size: 32 bytes TLBS: 64 Prime95 version 22.3, RdtscTiming=1 Best time for 256K FFT length: 54.165 ms. Best time for 320K FFT length: 70.726 ms. Best time for 384K FFT length: 84.818 ms. Best time for 448K FFT length: 101.149 ms. Best time for 512K FFT length: 114.412 ms. Best time for 640K FFT length: 148.319 ms. Best time for 768K FFT length: 180.532 ms. Best time for 896K FFT length: 212.317 ms. Best time for 1024K FFT length: 243.061 ms. Best time for 1280K FFT length: 315.420 ms. Best time for 1536K FFT length: 377.044 ms. Best time for 1792K FFT length: 448.984 ms. _ Unsubscribe list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: Slow Pentium 4 question
tried WCPUID to identify the chip? http://www.h-oda.com/ http://hp.vector.co.jp/authors/VA002374/src/download.html -brian On Wed, Jun 12, 2002 at 04:53:18PM -0700, Bockhorst, Roland P HQISEC wrote: I think my P4 is running like a P III, at one third speed doing Mersenne Prime testing. When I run Prime95v22 it reports my P4 as CPU features: RDTSC, CMOV, PREFETCH, MMX If I change the CPUtype to 12 (P4) and add SSE to the local.ini file, as in ... CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE nothing changes. If I change SSE to SSE2 the system crashes with an illegal instruction message. I am running Prime 95 on a 256 meg. P4-1600 with 8k L1 and 256K L2 on Windows 95A I'm entertaining these theories: Windows 95a without drivers? doesn't support a P4. (Is it being asked to?) I don't really have a P4. (I bought this system expecting P4 performance running Prime95) L1 cache too small. L2 cache too small Something else. Comments/theories/assertions/wild hairs are invited. My best times my P4 1600 256 meg 133SDRAM Best time for 256K FFT length: 57.218 ms. Best time for 320K FFT length: 71.299 ms. Best time for 384K FFT length: 86.423 ms. Best time for 448K FFT length: 102.487 ms. Best time for 512K FFT length: 115.680 ms. Best time for 640K FFT length: 148.042 ms. Best time for 768K FFT length: 184.596 ms. Best time for 892K FFT length: 214.233 ms. Best time for 1024K FFT length: 250.226 ms. Best time for 1280K FFT length: 320.198 ms. Best time for 1536K FFT length: 386.440 ms. Best time for 1792K FFT length: 467.666 ms. From the Benchmark site P4 1500 133SDRAM 256 Full 0.019 0.024 0.030 0.035 0.040 0.052 0.063 0.079 0.087 0.120 0.154 0.196 19 24 30 35 40 52 63 79 87 120 154 196 Mersenne benchmark times from http://www.mersenne.org\bench.htm P III 1 gig times are below Intel(R) Pentium(R) III processor CPU speed: 996.59 MHz CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE L1 cache size: 16 KB L2 cache size: 256 KB L1 cache line size: 32 bytes L2 cache line size: 32 bytes TLBS: 64 Prime95 version 22.3, RdtscTiming=1 Best time for 256K FFT length: 54.165 ms. Best time for 320K FFT length: 70.726 ms. Best time for 384K FFT length: 84.818 ms. Best time for 448K FFT length: 101.149 ms. Best time for 512K FFT length: 114.412 ms. Best time for 640K FFT length: 148.319 ms. Best time for 768K FFT length: 180.532 ms. Best time for 896K FFT length: 212.317 ms. Best time for 1024K FFT length: 243.061 ms. Best time for 1280K FFT length: 315.420 ms. Best time for 1536K FFT length: 377.044 ms. Best time for 1792K FFT length: 448.984 ms. _ Unsubscribe list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers -- --===-===---=-=== bjp aka rbw| and did you exchange a walk on part in the war [EMAIL PROTECTED]| for a lead role in a cage? ===-=---===-===-- _ Unsubscribe list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: Slow Pentium 4 question
hello Roland, could the CPU be overheating? what is the ambient temperature in the room? have you verified cpu fan and other case fans are operating? is plenty of hot air exiting the power supply fan? P4 has thermal protection which will slow selected areas of the chip, whichever portions are overheating. your bios should be able to tell you cpu temp although the cpu will have already cooled somewhat if you reboot and enter bios setup. you could check windows/hardware menu to see what cpu/clockrate it identifies. also there are shareware programs that will probe benchmark your pc and report exact cpu type, step number, clock rate, whatever. and the motherboard probably has a CD rom with some applications such as a cpu temperature monitor . i'm not sure if this would have been packaged with your PC or not, but if not, the motherboard maker probably has the same apps downloadable on their web site. in my experience, i think a fine P4 cpu temp while running prime95 would be around 59C. /eli Bockhorst, == Bockhorst, Roland P HQISEC [EMAIL PROTECTED] writes: Bockhorst, I think my P4 is running like a P III, at one third Bockhorst, speed doing Mersenne Prime testing. Bockhorst, When I run Prime95v22 it reports my P4 as CPU Bockhorst, features: RDTSC, CMOV, PREFETCH, MMX Bockhorst, If I change the CPUtype to 12 (P4) and add SSE to the Bockhorst, local.ini file, as in ... CPU features: RDTSC, CMOV, Bockhorst, PREFETCH, MMX, SSE nothing changes. Bockhorst, If I change SSE to SSE2 the system crashes with an Bockhorst, illegal instruction message. Bockhorst, I am running Prime 95 on a 256 meg. P4-1600 with 8k L1 Bockhorst, and 256K L2 on Windows 95A Bockhorst, I'm entertaining these theories: Bockhorst, Windows 95a without drivers? doesn't support a P4. (Is Bockhorst, it being asked to?) I don't really have a P4. (I Bockhorst, bought this system expecting P4 performance running Bockhorst, Prime95) L1 cache too small. L2 cache too small Bockhorst, Something else. Bockhorst, Comments/theories/assertions/wild hairs are invited. Bockhorst, My best times my P4 1600 256 meg 133SDRAM Best time Bockhorst, for 256K FFT length: 57.218 ms. Best time for 320K Bockhorst, FFT length: 71.299 ms. Best time for 384K FFT length: Bockhorst, 86.423 ms. Best time for 448K FFT length: 102.487 ms. Bockhorst, Best time for 512K FFT length: 115.680 ms. Best time Bockhorst, for 640K FFT length: 148.042 ms. Best time for 768K Bockhorst, FFT length: 184.596 ms. Best time for 892K FFT Bockhorst, length: 214.233 ms. Best time for 1024K FFT length: Bockhorst, 250.226 ms. Best time for 1280K FFT length: 320.198 Bockhorst, ms. Best time for 1536K FFT length: 386.440 ms. Best Bockhorst, time for 1792K FFT length: 467.666 ms. From the Benchmark site Bockhorst, P4 1500 133SDRAM 256 Full 0.019 0.024 0.030 0.035 Bockhorst, 0.040 0.052 0.063 0.079 0.087 0.120 0.154 0.196 19 24 Bockhorst, 30 35 40 52 63 79 87 120 154 196 Mersenne benchmark Bockhorst, times from http://www.mersenne.org\bench.htm Bockhorst, P III 1 gig times are below Bockhorst, Intel(R) Pentium(R) III processor CPU speed: 996.59 Bockhorst, MHz CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE L1 Bockhorst, cache size: 16 KB L2 cache size: 256 KB L1 cache line Bockhorst, size: 32 bytes L2 cache line size: 32 bytes TLBS: 64 Bockhorst, Prime95 version 22.3, RdtscTiming=1 Best time for 256K Bockhorst, FFT length: 54.165 ms. Best time for 320K FFT length: Bockhorst, 70.726 ms. Best time for 384K FFT length: 84.818 ms. Bockhorst, Best time for 448K FFT length: 101.149 ms. Best time Bockhorst, for 512K FFT length: 114.412 ms. Best time for 640K Bockhorst, FFT length: 148.319 ms. Best time for 768K FFT Bockhorst, length: 180.532 ms. Best time for 896K FFT length: Bockhorst, 212.317 ms. Best time for 1024K FFT length: 243.061 Bockhorst, ms. Best time for 1280K FFT length: 315.420 ms. Best Bockhorst, time for 1536K FFT length: 377.044 ms. Best time for Bockhorst, 1792K FFT length: 448.984 ms. Bockhorst, _ Bockhorst, Unsubscribe list info -- Bockhorst, http://www.ndatech.com/mersenne/signup.htm Mersenne Bockhorst, 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
Re: Mersenne: Slow Pentium 4 question
At 04:53 PM 6/12/2002 -0700, Bockhorst, Roland P HQISEC wrote: I think my P4 is running like a P III, at one third speed doing Mersenne Prime testing. When I run Prime95v22 it reports my P4 as CPU features: RDTSC, CMOV, PREFETCH, MMX I'm pretty sure that Windows 95 does not support SSE and SSE2 (because the OS does not save the XMM registers on a task swap?) Get yourself Windows 98 - someone probably has an old copy lying around you can get free or cheap. _ Unsubscribe list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
