Let's buy GIMPS an Opteron!

[Bok]

Originally Posted by Xyzzy

They say Linux is free, if your time is worth nothing...

I spent a whole day tracking down a mysterious bug that was preventing sftp from working... Eventually I found the answer here...

http://lists.suse.com/archive/suse-amd64/2003-Aug/0036.html

I'm only posting this so if I have this problem again I have the solution documented!

Xyzzy,

sorry, I came across this over last weekend as well, should have mentioned it.

Bok

[GP2]

Originally Posted by Bok

Dresdenboy,

I'm not sure what a revision C is?? But it's a brand new 1.8Ghz model.. I'll run mprime on it today, see what it does.

Bok

See earlier in this thread:
http://www.mersenneforum.org/viewtopic.php?p=9922#9922
and the two following messages.

It turns out that our GIMPS Opteron is only revision B, which may or may not be a problem with respect to poor benchmarks, if I'm reading those messages correctly.

[Bok]

ahh,

ok, I'll try and run the same benchmarks when I get back home tomorrow.

Bok :)

[Xyzzy]

Originally Posted by dsouza123

I am just curious, looking at the TLC SETI benchmark page using the link provided, it has one mysterious colum CpF with values ranging from 1.29 to 11.12 .

What is it and how is it calculated ? Is it some sort of efficiency calc ?

http://cox-internet.com/setispy/efficiency.htm

I tested the ecc2-109 client on xyzzy's opteron. The results were as follows:

Official core 855k Iterations per second ~ 610 Iteration per Megahertz
aloha core (a new optimized core) 920k Iterations per second ~ 657 Iterations per Mhz

All of the results from other cpus were obtained with the official core.

Results from AXP 1600+ running at the same frequency range from 752 to 802k Its/sec.

Interrestingly enough the only other cpu which can rival the opteron in Iterations / Mhz is the centrino. A 1400 Centrino was reported to get 853k Its/sec.

P4s do not usually perform as well in ecc2-109 the closest P4 I could find is a 1.6 Ghz P4 and runs around 592k Its/s.
The average for non HT enabled P4 is around 370 Iterations per Mhz and 420 for HT P4s

Cheers,
Marc

[Prime95]

To bok, who may have a revision C Opteron. If it is revision C run p95tst, do Advanced/Time 20000000, and post the strange timer results in results.txt.

To those running timings on the opteron: I've started an mprime running. To pause it for benchmarking purposes, run the program /home/gw/pauser. Within 2 minutes mprime will stop running until you kill pauser. Please remember to kill pauser before you logout.

BTW, credit for this CPU's results will go to TeamOpteron

[GP2]

Originally Posted by Prime95

To bok, who may have a revision C Opteron. If it is revision C run p95tst, do Advanced/Time 20000000, and post the strange timer results in results.txt.

I wonder if there is any other way to tell what revision it is, other than looking at the markings on the CPU, which is impractical after thermal compound and heat sink have been applied. Do the CPUID programs out there handle this yet?

Just curious; I don't have an Opteron myself.

[Xyzzy]

Originally Posted by Prime95

To those running timings on the opteron: I've started an mprime running. To pause it for benchmarking purposes, run the program /home/gw/pauser. Within 2 minutes mprime will stop running until you kill pauser. Please remember to kill pauser before you logout.

Are you running the client via nohup? You might want to so the process isn't killed if (when!) your connection is killed... I have a pretty reliable line but it is far from perfect...

Also, can the pauser program maybe kick back on if say 30 minutes of idle time goes by? I'd hate for someone to forget to kill it... (I check everything every 3-4 hours so I suppose I might catch it eventually!)

I'm curious, how much of an effect does having a program like mprime running at nice 19 have on running timings?

Do you think us having a revision B Opteron will be a problem? I'm half tempted to call AMD and complain, since our primary development focus deals with SSE2... Thoughts?

[Prime95]

Originally Posted by Xyzzy

Are you running the client via nohup? You might want to so the process isn't killed if (when!) your connection is killed... I have a pretty reliable line but it is far from perfect...

Yeah, I've been dropped 4 times today. It seems if I'm idle for a while I get kicked off automatically.

Also, can the pauser program maybe kick back on if say 30 minutes of idle time goes by? I'd hate for someone to forget to kill it

Good idea. I'll make pauser operate for just 1 hour.

I'm curious, how much of an effect does having a program like mprime running at nice 19 have on running timings?

On my Celeron 950 it makes a big difference. Using FreeBSD on my Athlon it makes no difference. I just guessed its a Linux scheduler issue. Haven't tried it on the Opteron yet.

Do you think us having a revision B Opteron will be a problem?

I doubt it. I suspect the changes are very, very minor. As soon as we get access to an Opteron C we will know for sure.

[Prime95]

BTW, would anyone like to volunteer to get some mlucas and glucas timings?

[Xyzzy]

Originally Posted by Prime95

Yeah, I've been dropped 4 times today. It seems if I'm idle for a while I get kicked off automatically.

Putty has a keep alive option...