Message boards : Number crunching : 362,000 secs per 1,000,000 turns
Message board moderation

To post messages, you must log in.

AuthorMessage
borandi

Send message
Joined: 9 Nov 05
Posts: 45
Credit: 20,379
RAC: 0
Message 12282 - Posted: 22 Jan 2006, 22:24:46 UTC

http://lhcathome.cern.ch/workunit.php?wuid=973422

Gotta love those P133's taking almost 4 days and 5hrs just to do 1 large WU.

Next time LHC has work it may do one again :D


BOINC@Hull . xfire . mySpace

ID: 12282 · Report as offensive     Reply Quote
Profile The Gas Giant

Send message
Joined: 2 Sep 04
Posts: 309
Credit: 715,258
RAC: 0
Message 12283 - Posted: 23 Jan 2006, 2:31:53 UTC
Last modified: 23 Jan 2006, 2:34:08 UTC

That's pretty funny and it's not even due to the W98 problem that causes the cpu time to increase even when a wu is preempted. It would be better off doing SETI@home and using the optimised SETI application, especially since it gets less granted credit than claimed.

Live long and crunch.

Paul
(S@H1 8888)
BOINC/SAH BETA
ID: 12283 · Report as offensive     Reply Quote
Fivestar Crashtest

Send message
Joined: 27 Sep 04
Posts: 11
Credit: 156,184
RAC: 0
Message 12284 - Posted: 23 Jan 2006, 3:16:23 UTC - in response to Message 12282.  

http://lhcathome.cern.ch/workunit.php?wuid=973422

Gotta love those P133's taking almost 4 days and 5hrs just to do 1 large WU.



Good heavens! You actually have Windows XP on that?! Is it truly installed or part of some kind of cluster?

ID: 12284 · Report as offensive     Reply Quote
River~~

Send message
Joined: 13 Jul 05
Posts: 456
Credit: 75,142
RAC: 0
Message 12293 - Posted: 23 Jan 2006, 8:35:29 UTC - in response to Message 12284.  

http://lhcathome.cern.ch/workunit.php?wuid=973422

Gotta love those P133's taking almost 4 days and 5hrs just to do 1 large WU.



Good heavens! You actually have Windows XP on that?! Is it truly installed or part of some kind of cluster?

you might get better throughput with win98 or 95 - a typical P133 has rather small memory for the huge needs of XP, and a lot of that proc time os almost certainly swapping operating system in and out whenever the app makes a system call

Just a thought...
ID: 12293 · Report as offensive     Reply Quote
borandi

Send message
Joined: 9 Nov 05
Posts: 45
Credit: 20,379
RAC: 0
Message 12320 - Posted: 23 Jan 2006, 18:09:57 UTC - in response to Message 12283.  

That's pretty funny and it's not even due to the W98 problem that causes the cpu time to increase even when a wu is preempted. It would be better off doing SETI@home and using the optimised SETI application, especially since it gets less granted credit than claimed.

Live long and crunch.


Every time it tries a SETI WU, after 50hrs it always seems to have a computational error. ATM its either on LHC or SZTAKI :D

BOINC@Hull . xfire . mySpace

ID: 12320 · Report as offensive     Reply Quote
borandi

Send message
Joined: 9 Nov 05
Posts: 45
Credit: 20,379
RAC: 0
Message 12321 - Posted: 23 Jan 2006, 18:14:22 UTC - in response to Message 12284.  

http://lhcathome.cern.ch/workunit.php?wuid=973422

Gotta love those P133's taking almost 4 days and 5hrs just to do 1 large WU.



Good heavens! You actually have Windows XP on that?! Is it truly installed or part of some kind of cluster?


It is truly installed on a 3.2GB HDD.


you might get better throughput with win98 or 95 - a typical P133 has rather small memory for the huge needs of XP, and a lot of that proc time os almost certainly swapping operating system in and out whenever the app makes a system call


My CPU effieciency on an LHC WU of 95.15% begs to differ =D I think in that machine there is 96MB RAM, and it runs fine as long as I only access it through boincView. Note, XP only requires 64MB.
BOINC@Hull . xfire . mySpace

ID: 12321 · Report as offensive     Reply Quote
m.mitch

Send message
Joined: 4 Sep 05
Posts: 112
Credit: 2,059,098
RAC: 874
Message 12355 - Posted: 24 Jan 2006, 11:22:35 UTC - in response to Message 12283.  
Last modified: 24 Jan 2006, 11:23:17 UTC

That's pretty funny and it's not even due to the W98 problem that causes the cpu time to increase even when a wu is preempted. It would be better off doing SETI@home and using the optimised SETI application, especially since it gets less granted credit than claimed.

Live long and crunch.


I had a simmilar problem. I thought it was LHC on WinXPSP2 but it was only occuring on one of my XP boxes. So I left it alone.


Click here to join the #1 Aussie Alliance on LHC.
ID: 12355 · Report as offensive     Reply Quote
[B@H] Ray

Send message
Joined: 13 Jul 05
Posts: 82
Credit: 6,336
RAC: 0
Message 12370 - Posted: 24 Jan 2006, 17:39:17 UTC - in response to Message 12282.  
Last modified: 24 Jan 2006, 17:40:04 UTC

http://lhcathome.cern.ch/workunit.php?wuid=973422

Gotta love those P133's taking almost 4 days and 5hrs just to do 1 large WU.

Next time LHC has work it may do one again :D



If I had enoughf memory in my P133 I would run it, but only 16 megs. The cost of additional memory would be better spent on a faster CPU for one of the other systems.

Got a free IBM Aptiva with an AMD K6 cpu, seems to run good. Have more PC100 memory for that, will have to put it in and try BOINC on it. Don't know the speed of that K6, will have to run CPUz on it to find out. If nothing else I can get a cheap board and a celeron cpu for a 3rd cruncher, no would be better off getting a HT CPU for this one. Anyone have an used early P4 HT, 2.4 or 2.6 gig (socket 478) to sell cheap? But then this board is probably to early to support HT.

Ray

Pizza@Home - Rays Place - Rays place Forums
ID: 12370 · Report as offensive     Reply Quote
[B@H] Ray

Send message
Joined: 13 Jul 05
Posts: 82
Credit: 6,336
RAC: 0
Message 12459 - Posted: 26 Jan 2006, 15:12:48 UTC

My wife had a 486SX25 notebook, have not run BOINC on that eather as it only has 4 megs of memory. But from the speed of that you can figure that it would take at least 5 times longer than a P133. Than you figure in that the 486SX processors had no floteing point unit and for this dubble the time.

Pizza@Home - Rays Place - Rays place Forums
ID: 12459 · Report as offensive     Reply Quote
m.mitch

Send message
Joined: 4 Sep 05
Posts: 112
Credit: 2,059,098
RAC: 874
Message 12551 - Posted: 28 Jan 2006, 15:31:16 UTC - in response to Message 12355.  

I had a simmilar problem. I thought it was LHC on WinXPSP2 but it was only occuring on one of my XP boxes. So I left it alone.


No, I was wrong. It is LHC and it's happening on my only Win98SE box


Click here to join the #1 Aussie Alliance on LHC.
ID: 12551 · Report as offensive     Reply Quote
Henry Nebrensky

Send message
Joined: 13 Jul 05
Posts: 169
Credit: 15,000,737
RAC: 21
Message 12683 - Posted: 9 Feb 2006, 1:00:45 UTC - in response to Message 12282.  
Last modified: 9 Feb 2006, 1:03:21 UTC

http://lhcathome.cern.ch/workunit.php?wuid=973422

Gotta love those P133's taking almost 4 days and 5hrs just to do 1 large WU.

Next time LHC has work it may do one again :D



It could be 40% worse -
http://lhcathome.cern.ch/show_host_detail.php?hostid=43358
took ~509 000 s for one of the last lot - which turned out to be 6 days, 23 and a bit hours. Still met the seven-day deadline though!

Is the P133 really a straight Pentium (i586) chip? BOINC claimed LHC had no clients for the i586-pc-linux-gnu platform, but that may be a Windows vs Linux thing. I ask as I've got a spare P233 chip (neener-neener-neener! :) ) but I'm not sure I can be bothered to upgrade the thing as I can't decide whether the abysmal performance is down to a cheap Cyrix FPU or the memory banned-width of the 72-pin SIMMs...
And I think I'm getting rid of it soon - but then I said that a couple of years ago too!

Thanks

Henry
ID: 12683 · Report as offensive     Reply Quote
borandi

Send message
Joined: 9 Nov 05
Posts: 45
Credit: 20,379
RAC: 0
Message 12687 - Posted: 9 Feb 2006, 7:13:29 UTC - in response to Message 12683.  

Is the P133 really a straight Pentium (i586) chip?


http://www.boincathull.co.uk/p133.png

Does that answer your question? :p

borandi

BOINC@Hull . xfire . mySpace

ID: 12687 · Report as offensive     Reply Quote
[B@H] Ray

Send message
Joined: 13 Jul 05
Posts: 82
Credit: 6,336
RAC: 0
Message 12694 - Posted: 9 Feb 2006, 19:33:19 UTC - in response to Message 12687.  

Is the P133 really a straight Pentium (i586) chip?


That is it, one of the early Pentium chips. Only diferance between that and the earlier P60 & P90 chips is the speed.

But when they came out they were really considered fast, the fastest 486 (486DX4 100) was slow compaired the the Pentiums.

I can remember that the first Pentium chips were really expensive for the first couple of Mounths, and most people thought that only larger companies that needed a lot of computing power would evev use the pentium chip. But as you can see years later they were wrong.

I have never seen a 286, 386 or 486 chip crunching except for one 486 working on SETI but it is taking close to a week per WU there. Definately not good for projects with shorter deadlines.

Ray

Pizza@Home - Rays Place - Rays place Forums
ID: 12694 · Report as offensive     Reply Quote
River~~

Send message
Joined: 13 Jul 05
Posts: 456
Credit: 75,142
RAC: 0
Message 12695 - Posted: 9 Feb 2006, 21:33:15 UTC - in response to Message 12694.  


I can remember that the first Pentium chips were really expensive for the first couple of Mounths, and most people thought that only larger companies that needed a lot of computing power would evev use the pentium chip. But as you can see years later they were wrong.


That is not quite as bad as IBM's howler, determining that there would only ever be a market for about sis computers, at a time when English Electric had already got orders for that number in the UK alone... the very first being sold to a tea company

Sometimes we all can be a bit slow when it comes to seeing what use will be made of new crunch power.

Or the power of the marketing department...

R~~
ID: 12695 · Report as offensive     Reply Quote
Profile Purple Rabbit

Send message
Joined: 22 Oct 04
Posts: 8
Credit: 3,630,326
RAC: 632
Message 12727 - Posted: 13 Feb 2006, 15:02:01 UTC - in response to Message 12694.  

I have never seen a 286, 386 or 486 chip crunching except for one 486 working on SETI but it is taking close to a week per WU there. Definately not good for projects with shorter deadlines.

My 486 (AMD 586-133) does SETI in 12.5 days. It's not really worth it. SIMAP seems to be a good choice for slower computers. The 486 does it in 22 hours and I'm almost always first to return a result.
ID: 12727 · Report as offensive     Reply Quote
borandi

Send message
Joined: 9 Nov 05
Posts: 45
Credit: 20,379
RAC: 0
Message 12729 - Posted: 13 Feb 2006, 17:28:51 UTC - in response to Message 12727.  


My 486 (AMD 586-133) does SETI in 12.5 days. It's not really worth it. SIMAP seems to be a good choice for slower computers. The 486 does it in 22 hours and I'm almost always first to return a result.


SZTAKI is also a good one for slower computers. I put it on all my 400Mhz and below.

BOINC@Hull . xfire . mySpace

ID: 12729 · Report as offensive     Reply Quote

Message boards : Number crunching : 362,000 secs per 1,000,000 turns


©2024 CERN