SV: Mersenne: Re: Mersenne Digest V1 #895
Hello, I'm fairly nuew to this group and this is actually my first message here. :-) Can I use wintop on Windows 98 or windows Me? The download page says that NOTE: This download is not intended for use on computers running MicrosoftR WindowsR 98 or is there another version of wintop for Windows 98 or Windows Me? (I have Thanks in advance /Magnus --- It's actually a Microsoft program and is one of their kernel toys package. http://www.microsoft.com/windows95/downloads/contents/wutoys/w95kerneltoy/ I'll answer to the group as well since this is a very useful tool for prime95 users. It allows you to spot processes that go into busy waits and the like which waste CPU time. Try holding the mouse button down on the desktop - went to 100% CPU on my Win95 system, but I haven't used that in over a year now! [EMAIL PROTECTED] wrote: Hi group This question was asked before but I lost the info. What is the website to obtain a copy of WINTOP, the memory usage program. Also, what is the site for the archives of this list. Please answer this directly to me. Thanks Irv Rosenfeld -- === Gareth Randall === _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers _ Do You Yahoo!? Get your free @yahoo.com address at http://mail.yahoo.com _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Mersenne: Statistics
Hi all, I mentioned that we lost about 9000 machines during the past 7 months. One year ago I started collecting data about numbers of machines, accounts and so on. Please find this information at the bottom of may mail. GIMPS has now as many contributing machines as it had 13 months ago. In the meantime there was a peak of 38950 machines (26 March 2001). After that date we lost about 9000 machines which we had gained between September 2000 and March 2001. As I pointed out earlier, the number of participating P4-machines is still unknown. Source of information is http://www.mersenne.org/primenet/ Though we lost many machines since March 2001 CPU-power is now higher than ever before. +26% since March 2001 and +57% since September 2000 Regards Achim date time CPU Acco. GFlops CPU-yrs dd.mm. 29.10.2001 0500 UTC 30191 15683 2043,646 169,770 22.10.2001 0500 UTC 30307 15642 2008,321 166,836 15.10.2001 0600 UTC 30431 15730 1901,848 157,991 08.10.2001 0500 UTC 30566 15727 1857,497 154,307 24.09.2001 0600 UTC 30653 15766 1864,789 154,912 18.09.2001 0500 UTC 30790 15857 1785,983 148,366 11.09.2001 0500 UTC 31520 16261 1756,467 145,914 03.09.2001 0500 UTC 31609 16333 1736,277 144,237 27.08.2001 0500 UTC 31711 16435 1690,763 140,456 20.08.2001 0500 UTC 31945 16548 1581,901 131,412 13.08.2001 0500 UTC 32196 16751 1576,293 130,946 06.08.2001 0500 UTC 32362 16907 1620,202 134,594 30.07.2001 0500 UTC 32701 17110 1487,373 123,560 23.07.2001 0500 UTC 33261 17458 1606,075 133,420 16.07.2001 0500 UTC 33733 17811 1637,079 135,996 09.07.2001 0600 UTC 34270 18188 1652,384 137,267 02.07.2001 0500 UTC 34812 18562 1639,516 136,198 25.06.2001 0500 UTC 35156 18840 1600,189 132,931 18.06.2001 0700 UTC 35117 18841 1675,095 139,154 22.05.2001 0500 UTC 37275 20269 1628,585 135,290 14.05.2001 0500 UTC 37713 20544 1633,160 135,670 07.05.2001 0500 UTC 38025 20785 1666,983 138,480 30.04.2001 0500 UTC 38084 20747 1692,778 140,623 23.04.2001 0500 UTC 38199 20729 1586,019 131,754 16.04.2001 0600 UTC 38383 20813 1662,104 138,075 09.04.2001 0500 UTC 38474 20842 1598,232 132,769 02.04.2001 0500 UTC 38652 20983 1615,256 134,183 26.03.2001 0500 UTC 38950 21141 1622,482 134,783 * 19.03.2001 0600 UTC 38646 20929 1467,637 121,920 12.03.2001 0600 UTC 38565 20901 1563,653 129,896 05.03.2001 0600 UTC 38426 20857 1547,440 128,549 26.02.2001 0600 UTC 37867 20534 1474,404 122,482 19.02.2001 0700 UTC 37045 20077 1540,198 127,948 12.02.2001 0600 UTC 36546 19786 1464,081 121,625 05.02.2001 0600 UTC 36017 19496 1510,121 125,449 29.01.2001 0600 UTC 35619 19300 1477,466 122,737 22.01.2001 0600 UTC 35149 19039 1541,203 128,031 15.01.2001 0600 UTC 34693 18721 1509,874 125,429 08.01.2001 0600 UTC 34295 18493 1402,836 116,537 02.01.2001 0700 UTC 33644 18136 1288,028 106,999 18.12.2000 0600 UTC 32755 17520 1400,193 116,317 11.12.2000 0600 UTC 32773 17525 1396,369 116,000 04.12.2000 0600 UTC 32755 17532 1472,300 122,307 27.11.2000 0600 UTC 32970 17653 1413,927 117,458 20.11.2000 0600 UTC 32815 17557 1351,143 112,243 13.11.2000 0700 UTC 32420 17318 1378,667 114,529 06.11.2000 0600 UTC 32193 17166 1357,534 112,774 30.10.2000 0600 UTC 31766 16900 1278,675 106,223 23.10.2000 0500 UTC 31507 16717 1312,163 109,004 16.10.2000 0500 UTC 3 16463 1275,128 105,928 06.10.2000 1200 UTC 30521 15954 1291,741 107,308 29.09.2000 1200 UTC 30154 15699 1297,677 107,801 _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: number of processors participating
Hi all, One thing to remember ppl, A LOT of system testers tend to use Prime95 to test overclocking/cooling. I'm sure that *many* abandoned assignments are due to this fact. Due to this usage (which I don't mind BTW, maybe a few will stay on and contribute, I did) I suggest that there be a switch added so that ppl can use Prime95 as a processor test but without ever getting real assignments, thus slowing down the project. Just my two cents. Alan On 27 Oct 2001, at 18:54, Henk Stokhorst wrote: Date sent: Sat, 27 Oct 2001 18:54:24 +0100 From: Henk Stokhorst [EMAIL PROTECTED] To: [EMAIL PROTECTED] Subject:Mersenne: number of processors participating L.S., I read a message some time ago on this list that claimed that the number of processors had gone down by about 9000. I don't have stats on this other than the actual available from the status pages. Does anyone have stats over the last year, like numer of pc's and/or processor types, processor speeds? If there would really have been a decrease in participating processors, (I don't think so) an updated graph of Primenet throughput would show by now, is there any update in the pipeline? I went through the status.txt file to see if the new 'stress test' button could have played a significant role, I don't think so. By the way if one runs prime95 without a user name the application fills in an S0 as user name. I found 3170 entries with a name '.' (only a dot) The fast majority of these entries seem to be have been abandoned. They have been reserved over a long time with a constant daily flow. Does anyone know more about this? YotN, Henk Stokhorst _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers A programmer is a person who turns coffee into software. Alan R. Vidmar Assistant Director of IT Office of Financial AidUniversity of Colorado [EMAIL PROTECTED](303)492-3598 *** This message printed with 100% recycled electrons *** _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: number of processors participating
On Mon, 29 Oct 2001 09:35:40 -0700, Alan Vidmar [EMAIL PROTECTED] wrote: Hi all, One thing to remember ppl, A LOT of system testers tend to use Prime95 to test overclocking/cooling. I'm sure that *many* abandoned assignments are due to this fact. Due to this usage (which I don't mind BTW, maybe a few will stay on and contribute, I did) I suggest that there be a switch added so that ppl can use Prime95 as a processor test but without ever getting real assignments, thus slowing down the project. This is already the case as of the latest version, IIRC. Nathan _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: number of processors participating
Alan Vidmar wrote: I suggest that there be a switch added so that ppl can use Prime95 as a processor test but without ever getting real assignments,... This is a VERY good suggestion. However it has already been implemented in the latest version (v21). That version contains more improvements so I wondered if it wouldn't be a good idea to inform users through the occasional newsletter. Particulary because it gives a 10% improvement for Pentium I, II and III users and it skips P-1 if it has been done. YotN, Henk Stokhorst. PS those abandoned assignments do't slow down the project. They just scatter the work over a larger range. _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
SV: Mersenne: number of processors participating
I admit I'm not that good in telling primenet what computers I have and what throughput rate to expect. eg.: I made 14 accounts all using the same 150 Mhz machine, though I knew none or only few would be 150 Mhz. These accounts all run occassionally, eg. in company holiday around the clock, outside of holiday more random. Over time I have been wiser to use more power of those machines staying awake all night anyway. :-) I would like to use the servers; but I haven't been able to persuade George to make a Quit function like quit_at: 06:00 to terminate the program when users arrives and optimum performance is needed (with no question what so ever about serverperformance); And I don't wake up at 6 to turn prime95 or anything else off unless there is a severe error reported by users. Happy hunting tsc -Oprindelig meddelelse- Fra: Henk Stokhorst Sendt: ma 29-10-2001 19:30 Til: Alan Vidmar; [EMAIL PROTECTED] Cc: Emne: Re: Mersenne: number of processors participating Alan Vidmar wrote: I suggest that there be a switch added so that ppl can use Prime95 as a processor test but without ever getting real assignments,... This is a VERY good suggestion. However it has already been implemented in the latest version (v21). That version contains more improvements so I wondered if it wouldn't be a good idea to inform users through the occasional newsletter. Particulary because it gives a 10% improvement for Pentium I, II and III users and it skips P-1 if it has been done. YotN, Henk Stokhorst. PS those abandoned assignments do't slow down the project. They just scatter the work over a larger range. _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: Statistics
[EMAIL PROTECTED] wrote: I mentioned that we lost about 9000 machines during the past 7 months. One year ago I started collecting data about numbers of machines, accounts and so on. Please find this information at the bottom of may mail. GIMPS has now as many contributing machines as it had 13 months ago. In the meantime there was a peak of 38950 machines (26 March 2001). After that date we lost about 9000 machines which we had gained between September 2000 and March 2001. As Since March 2001? Isn't that about when California's power crisis started warning about summer blackouts? Maybe a lot of the missing machines were CA users shutting down their pcs. I left mine on. Cheers... Russ (in San Jose) _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
SV: SV: Mersenne: number of processors participating
Yep! But the time entry only allows the program to sleep (still eating all CPU cycles even when running at zero priority). Take any NT 4.0 or W2K machine and you will see the system idle time doesn't add seconds while Prime95 still eats them (and doing nothing). For my servers to become prime95's I need to be sure they only run what I have planned at anytime. I can start Prime95 scheduled. I don't mind! But the users should never have one chance of claiming servers aren't available or even running slow. I know you are certain and I know you gotta be damn good at this (very far beyond anything I will ever manage); but still any doubt will become my users advantage. Make the sleepy nights for my servers glorius. I make them start prime95 by a schedule and You make prime95 die by harikiri - and I decide when everything happens. :-) Tnx in advance. Still happy hunting tsc -Oprindelig meddelelse- Fra: George Woltman Sendt: ma 29-10-2001 22:47 Til: Torben Schlüntz Cc: Emne: Re: SV: Mersenne: number of processors participating Hi, At 10:01 PM 10/29/2001 +0100, you wrote: I would like to use the servers; but I haven't been able to persuade George to make a Quit function like quit_at: 06:00 to terminate the program when users arrives and optimum performance is needed Look in readme.txt for the Time= entry in prime.ini This feature can be used to make prime95 go dormant at a specified time. Hope that helps, George _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: number of processors participating
On 28 Oct 2001, at 0:28, Terry S. Arnold wrote: Another consideration is that many system/network administrators have gotten ludicrous about what they will allow on their networks. They think that Prime95 just might let in a virus or even worse spill company secrets. By and large they are totally ignorant of the real issues involved with securing networks. All most of them know about the implications of the various protocols in the TCP/IP suite was what it took get their MCSE if they have even that much training. As a system/network administrator specialising in security matters I just _have_ to answer this one. 1) It's perfectly true that there are a large proportion of sites with incompetent sysadmins - especially from the point of view of networking. Especially in small companies, where the sysadmin function tends to be bolted onto another job as a low-priority extra task. 2) AFAIK none of the MSCE courses cover security in any depth at all. In fact the approach seems to be the _reverse_ i.e. teach people how to set up administer systems in an unduly risky way, without even bothering to mention basic security tools or methodology because they're not essential to _Microsoft_ networking in a laboratory/classroom environment. Based on recent experiences with Code Red Nimda, 95% of the problems on our site came from the 1% of the systems located in business incubator centres attatched to the University but administered by the businesses themselves. Basically it's rare for these people even to be aware of most of the services running on their systems (anything that comes preloaded on the system gets run, irrespective of whether it's absolutely neccessary or absolutely unneccessary); as for applying critical updates, they seem to be trained to think one of (a) it's much too hard, (b) it will break the functionality, (c) they simply don't understand why they need to bother with such things. _Despite_ how easy it is to run Windows Update. The only way I've been able to get these people to apply updates is to get sanctioned to scan their systems for vulnerability to Code Red Nimda, block _all_ access to vulnerable systems until they get patched (or take down the IIS service). To my knowledge, many ISPs had to take similar action. At least _some_ universities Fortune 500 companies have competent sysadmins, but there are a whole lot of mom pop businesses out there; a high percentage of them would be an absolute pushover to anyone wearing a black hat, even if IIS installations have now mostly been patched to a reasonable level. As for distributed computing projects being a security risk - basically I think in many cases _management_ may be misusing security as a screen for filtering out anything _they_ don't understand. In my experience few of these people are aware of the scale of network _abuse_ (note, not _neccessarily_ a threat to security) that goes on by way of end users installing peer-to-peer file sharing software on their workstations; probably 99% of the files shared over these P2P networks are in effect illegal distributions of copyrighted material. They're certainly _not_ aware that Windows systems with e.g. Kazaa clients are quite capable of sharing not just the offending copyrighted material but also everything else on the system - or attatched to it through open LAN shares. Yes, including company secrets. Quite apart from that, the volume of traffic involved with these P2P networks can be huge, certainly enough to seriously impact network links. (Before anyone takes me to task on the above paragraph, quite frankly I am totally opposed to the DMCA, the proposed SSSCA and all similar legislation. But I am also opposed to unauthorized distribution of copyrighted material. IMO the force of the law should be applied against those individuals making the copies, not against those who write software or the posession of hardware which might possibly be used to make illegal copies.) Under these circumstances I find it hard to understand how anyone can think that compute-intensive, network-friendly applications can be a problem. As for letting in a virus - if people really thought that, they just wouldn't use Microsoft products. How much of a threat was Code Red or Nimda infection on a system which wasn't running Microsoft Exchange, Microsoft Internet Information Server or (in the case of Nimda) Microsoft Internet Explorer? Well, _other_ infected systems might load up your network to some extent, but _your_ system certainly wasn't going to get infected! Regards Brian Beesley _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: number of processors participating
On 29 Oct 2001, at 19:30, Henk Stokhorst wrote: [... snip ...] However it has already been implemented in the latest version (v21). That version contains more improvements so I wondered if it wouldn't be a good idea to inform users through the occasional newsletter. Particulary because it gives a 10% improvement for Pentium I, II and III users and it skips P-1 if it has been done. Umm - I haven't noticed any significant improvement in v21 speed on Pentium or Pentium II - the big changes are implementing prefetch, which is only applicable to AMD Athlon family, PIII and faster Celeron processors, and exploiting the SSE2 instruction set on Pentium 4 only. Apart from (sometimes) skipping P-1, the changes between v20 and v21 are pretty well cosmetic if you're using a 486 / Cyrix / AMD K6 / Intel Pentium (Classic or MMX) / Pentium Pro / Pentium II / Celeron 533 MHz CPU. There _are_ some other changes - including a bit of fine tuning of the exponent / FFT run length size breaks - but nothing which really makes an upgrade look inescapable. In fact, these older systems are more likely to have a memory constraint than newer systems with faster processors; due to the inclusion of the Pentium 4 specific SSE2 code, the v21 binary has a significantly bigger memory footprint, so systems which won't benefit from the prefetch code which are feeling memory pressure might be better _not_ upgrading. The speed improvement from v20 to v21 on a PIII or Athlon system should be somewhere close to 25%, rather than 10%. On these systems an upgrade seems highly desirable. If you're still running v20 (or earlier) on a Pentium 4, then quite frankly you really SHOULD upgrade. NOW. The execution speed will approximately treble. As for reduced participation - whilst other reasons certainly do have an effect, I've previously mentioned two other possible reasons: (1) adverse publicity stemming from the prosecution of a sysadmin for running RC5 clients on his systems without the agreement of the management at the college which employed him; (2) steep rises in electricity prices and unreliability of supply in some places e.g. USA West Coast deterring people from running extended jobs. Regards Brian Beesley _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: SV: Mersenne: number of processors participating
Still the only time I've ever seen Prime95/NTPrime slow down a system is when I was doing some Netmeeting video conferences. With it running, the video conference would run DOG slow. Stop the NTPrime service and curiously had to restart the video conference for the effect, but the video would then be running great. That was with, umm.. version 20 I think? I haven't tried again with later versions... wasn't one of the things George did something to do with the priority setting? I've had similar problems with a few other multimedia sorts of junkware. Near as I can tell, some of these things put their video or animation thread at Idle_Priority+1 or something, and it gets eaten alive by Prime95. -jrp _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: SV: Mersenne: number of processors participating
On Mon, 29 Oct 2001 17:05:02 -0800, Aaron Blosser [EMAIL PROTECTED] wrote: Still the only time I've ever seen Prime95/NTPrime slow down a system is when I was doing some Netmeeting video conferences. With it running, the video conference would run DOG slow. Stop the NTPrime service and curiously had to restart the video conference for the effect, but the video would then be running great. That was with, umm.. version 20 I think? I haven't tried again with later versions... wasn't one of the things George did something to do with the priority setting? Aaron Out of curiousity, have you tried tinkering with the thread priorities of the programs in question? I find the utility bvslice (http://www.blueneptune.com/~maznliz/marius/software.shtml) to be quite useful. Nathan _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers