Crunch Time S5 Workunits

MarkF
MarkF
Joined: 12 Apr 05
Posts: 393
Credit: 1516715
RAC: 0

nevermorestr: good point! It

nevermorestr:
good point!
It seems to me though that too many are saying that the SR5 app is nearly as thoroughly optimized as the SR4 Akos variants. As David has pointed out the overall system of various projects may not be prepared for such improvements. Yet as a volunteer for this project I feel I am justified in expecting that the devs make the best use of my contribution.

[B@H] Ray
[B@H] Ray
Joined: 4 Jun 05
Posts: 621
Credit: 49583
RAC: 0

RE: Average crunch time for

Message 38186 in response to message 38183

Quote:

Average crunch time for S5's (the first 5 validated) was 15:01:25 (standard)
Average credit for above was 154.48 claimed/granted.
Average credit per hour was 10.28 claimed/granted.

Hope it helps anyone studying such things - if it matters, these are from P4 (Northwoods) with CPU speeds from 2.4 to 3.4 GHz, with HT enabled on all but the 2.4 (not HT capable).


Dark Star
Just started my first lonh S5, 2 hours into it with a P4 Northwood 2.4, looks like it will be about 15 hours, same as yours.

Completed 19 of the short ones on the Northwood, 1:40 to 1:45 each, 11.42 credits per hr. Granted.

Will still have to see how it does on the Prescott at 2.93 Gig. That one is still loaded with the S5 uuits.

When Rosetta had fixed linght units the Prescott did them faster and did the S4 faster but the Northwood is faster at SETI and CPDN. If you are running more than one project you may want to check and see whare each system dues the bast. I am down to just CPDN, Rosetta and E@H, will be finishing up CPDN in a while.


Try the Pizza@Home project, good crunching.

Digger
Digger
Joined: 24 Mar 05
Posts: 84
Credit: 27421
RAC: 0

RE: Will still have to see

Message 38187 in response to message 38186


Quote:
Will still have to see how it does on the Prescott at 2.93 Gig. That one is still loaded with the S5 uuits.


Hi Ray,

My Celeron D crunches a short S5 unit in about 1:30 for 20.03 granted credit. Works out to 13.35/hour. Will be interesting to compare notes when you get some, as I think my machine could be doing a lot better than it is.

Dig

[B@H] Ray
[B@H] Ray
Joined: 4 Jun 05
Posts: 621
Credit: 49583
RAC: 0

RE: RE: Will still have

Message 38188 in response to message 38187

Quote:

Quote:
Will still have to see how it does on the Prescott at 2.93 Gig. That one is still loaded with the S5 uuits.

Hi Ray,

My Celeron D crunches a short S5 unit in about 1:30 for 20.03 granted credit. Works out to 13.35/hour. Will be interesting to compare notes when you get some, as I think my machine could be doing a lot better than it is.

Dig


Here is a link to my Celeron D 2.93, but all S4 at this time. That has been averageing 55 min for the S4 comaired to 65 to 68 for the P4. The P4 2.4 (with S5) is at This link

Maby in a few days there will be some S5 units there for the Celeron. For Rosetta before I had only one unit in the que at one time so I zipped BOINC before running it, than ran it on both systems, the Celeron was about 15% faster. But for CPDN & SETI which needs a larger L2 Cacsh the P4 is faster.

Ray


Try the Pizza@Home project, good crunching.

[B@H] Ray
[B@H] Ray
Joined: 4 Jun 05
Posts: 621
Credit: 49583
RAC: 0

RE: RE: RE: Will still

Message 38189 in response to message 38188

Quote:
Quote:

Quote:
Will still have to see how it does on the Prescott at 2.93 Gig. That one is still loaded with the S5 uuits.

Hi Ray,

My Celeron D crunches a short S5 unit in about 1:30 for 20.03 granted credit. Works out to 13.35/hour. Will be interesting to compare notes when you get some, as I think my machine could be doing a lot better than it is.

Dig


Here is a link to my Celeron D 2.93, but all S4 at this time. That has been averageing 55 min for the S4 comaired to 65 to 68 for the P4. The P4 2.4 (with S5) is at This link

Maby in a few days there will be some S5 units there for the Celeron. For Rosetta before I had only one unit in the que at one time so I zipped BOINC before running it, than ran it on both systems, the Celeron was about 15% faster. But for CPDN & SETI which needs a larger L2 Cache the P4 is faster.

Ray



Try the Pizza@Home project, good crunching.

Digger
Digger
Joined: 24 Mar 05
Posts: 84
Credit: 27421
RAC: 0

RE: Here is a link to my

Message 38190 in response to message 38188


Quote:
Here is a link to my Celeron D 2.93, but all S4 at this time. That has been averageing 55 min for the S4...


Thanks Ray,

For comparison I checked some of my old logs for the Celeron D. It crunched an S4 unit with the Akos optimized app in an average of 3300 seconds or 55 minutes, so we are right on the money. You should expect to do an S5 shortie in 1:30 or so.

Dig

Akos Fekete
Akos Fekete
Joined: 13 Nov 05
Posts: 561
Credit: 4527270
RAC: 0

I found a good

I found a good debugger...
Times will cut down...

Quote from Mahbubur

Quote:
So im getting a 23.9% improvemnt in crunch times using HT.

This tell me a lot.

Beach Bum
Beach Bum
Joined: 12 Dec 05
Posts: 68
Credit: 215346
RAC: 0

RE: I have noticed no

Quote:

I have noticed no change in my RAC. In another project when things were changed, you noticed a large change in RAC, quickly. Since this one has been running for several days, and now most of my machines are on S5, I am still getting the same RAC.

I believe that they have the numbers running well. No one else is complaining of loss of RAC, that I have seen, either.

Actaully Pooh Bear I have seen a drop in my per hour credit return. But expected this as the WU's are longer, and the S-5 App is still in its first rollouts. It will get better and the return will go back up. Most of my Machines on S-4 Akos were returning around 20 credits per hour. Now they are returning around 8 credits per hour. Time and further optimizations by the Devolpment team will pull that back up for all of us. At least here there is a staff that talks to you. Trys to explain what is going on. And is open to suggestions. Unlike another project a lot of us know.

Come Join us at Hawaiian Beach Bums

somebodley
somebodley
Joined: 3 Mar 06
Posts: 119
Credit: 180339
RAC: 0

RE: RE: Here is a link to

Message 38193 in response to message 38190

Quote:

Quote:
Here is a link to my Celeron D 2.93, but all S4 at this time. That has been averageing 55 min for the S4...

Thanks Ray,
For comparison I checked some of my old logs for the Celeron D. It crunched an S4 unit with the Akos optimized app in an average of 3300 seconds or 55 minutes, so we are right on the money. You should expect to do an S5 shortie in 1:30 or so.
Dig


My Mac Powerbook 1Gig does a short (h1_0356.5_S5R1_32650_S5R1a) in 8,447.31 CPU secs for credit of 19.36.
The other chap (using Linux 2.6.16.1 and an Athlon XP 1700+) recorded 4,121.52 for exactly the same credit.
Will increasing my Memory (at present only 512MB) give me more oomph?

[edit] ... what relevance is Floating Point Speed and Measured Integer Speed and what relevance do they have to this work?

Mahbubur
Mahbubur
Joined: 31 Mar 06
Posts: 46
Credit: 258468
RAC: 0

RE: Ive done 19 short work

Message 38194 in response to message 38171

Quote:

Ive done 19 short work units with a pentium 4 3.0ghz system with ht off.

Averaging at 4860 seconds claiming and recieving 19.5 credits each time.

Ive swithced to HT on and now average 7400 seconds based on a sample of 4 claiming 19.5 credits each time.

4860*2 = 9720 while with HT 7400.

(9720-7400)/9720= 0.239

So im getting a 23.9% improvemnt in crunch times using HT.

Over a greater sample times are 7520 with HT, showing a 22.6% improvement.

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.