• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

AMD64 vs Dual MP's

L

lelliott731

[H]ard DCOTM April 2017
Joined
Mar 15, 2002
Messages
941
Hey guys, I'm working on the RC5-72 effort over at distributed.net and I was wondering which setup would be faster. For the AMD64 system I was thinking a 3400+, a Gigabyte board using the Via chipset, at least 1.5GB of memory. For the MP system I was thinking (2) 2800+ MP's, Tyan's Tiger MPX, and at least 2GB of memory.

One of the problems I'm having is I can't seem to find a RC5-72 keyrate for the AMD Athlon64 3400+, I have found the keyrate for the Dual 2800+ MP's, it is 13,850,114 keys/s. The only entry I see at the speed site, http://www.distributed.net/speed/, for a AMD64 chip is for a 1600+, which I didn't even think they made, and it said the speed was 5,771,251. There was also a Opteron 2200+ that's speed was 8,199,173. I would get a dual Opteron system but they are way to expensive.

So any help would be appreciated, especially if someone has a 3400+ CPU and could benchmark it for me, that'd be even greater. You can get the zip file with the program at http://www1.distributed.net///download/clients.php.
 
Hi lelliott731,
You might be better off asking distributed.net questions in a forum with more distributed.net experience since we almost exclusively talk about medical and science DC projects. I used to do RC5-64 back in the day, but have since moved on to medical research projects so I don't have any idea if my memories apply to the new projects. Have you thought about looking for cures to diseases instead of cracking encryption keys? A lot of us used to do SETI and d.net but found Folding or UD to be a lot more satisfying. If you do decide to join, Folding would love that MP setup you're proposing! :)
 
That is a really good post lelliot731, kudos on lots of info... if I had a 3400+ I'd bench it for you... nobody (that I know of) is running one of those around here yet, but maybe somebody has a 3200+ you could extrapolate from?
Look at the the Medical DC stuff... It sure does some useful stuff.
cheers, and good luck... sharp
 
Fresh from the oven. ;)

A64 3200+
(2000mhz) [Feb 03 20:32:39 UTC] RC5-72: Benchmark for core #4 (DG 3-pipe alt) 0.00:00:16.48 [7,629,598 keys/sec]


A64 3400+
(2200mhz) [Feb 03 20:37:21 UTC] RC5-72: Benchmark for core #4 (DG 3-pipe alt) 0.00:00:16.32 [8,327,184 keys/sec]
 
So the dual MP's whip the AMD64 3400's tail. They pump out 13,850,114 keys/s. Thanks for the info CIWS!
 
Originally posted by lelliott731
So the dual MP's whip the AMD64 3400's tail. They pump out 13,850,114 keys/s. Thanks for the info CIWS!
Click to expand...

Sounds like it, I'd have to run it on my Dual 2600+, but I suspect each of those CPUs does 6-7 mill keys, which combined will still stomp the single CPU setup.
 
Na dude, I ran RC5 and a few other dist.net clients years ago. Everything is now working on medical oriented stuff. Folding,UD,FAD, etc It took 200 thousand+ people almost 5 years to crack -64 and everthing is already at least 128bit encryption. So I'm not too worried about a brute force attack ;)
 
Originally posted by lelliott731
CIWS you want to join my RC5-72 team:)?
Click to expand...

I don't think he does, but how about you join our folding team?

Check out the FAQ at the top of the forum to see what it's about.
 
You must log in or register to reply here.
Back
Top