Welcome to MilkyWay@home

particle swarm searches -- ps_X

Message boards : Number crunching : particle swarm searches -- ps_X
Message board moderation

To post messages, you must log in.

Previous · 1 · 2

AuthorMessage
msattler

Send message
Joined: 15 Jul 08
Posts: 288
Credit: 5,474,012
RAC: 0
Message 10798 - Posted: 15 Feb 2009, 7:52:32 UTC - in response to Message 10793.  
Last modified: 15 Feb 2009, 7:53:25 UTC

I said transfer, not delete..........


I have better things to do with my time than spend 20 minutes moving posts from one thread to another. Try and keep it in the cafe please.

Whenever I get upset on the interwebs, I try and remember:



It always makes me feel better.


Oh, babysitting is not your thing, eh?

I am cool wlth that.........just let some others know that I don't put up with shit............

I will try to calm down now.......thanks for reminding me that you have better things to do........I am sure that is fact, not BS.


BTW, I can identify with that cartoon........
I don't know how many times I have heard the GF say........
"You were up until HOW long last night?!?!?! Doing WHAT????"
I am the Kittyman.

Please visit and give a Click for Seti City.




ID: 10798 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Seejay
Avatar

Send message
Joined: 22 Dec 07
Posts: 51
Credit: 2,405,016
RAC: 0
Message 10843 - Posted: 15 Feb 2009, 11:16:15 UTC

ps WUs going through the same as nm WUs. No problems visible, but it's difficult to catch them, seeing as the DB is purged almost instantaneously. How are they looking serverside, Travis? ;^).
ID: 10843 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
John Clark

Send message
Joined: 4 Oct 08
Posts: 1734
Credit: 64,228,409
RAC: 0
Message 10844 - Posted: 15 Feb 2009, 11:53:07 UTC

I would echo Seejay's comments, and both type of WUs (nm_ and ps_) are crunched in a similar time.

From my observation, limited due to the insta-purge, the blocks of errors reported earlier seem to have stopped.

Is that your view Travis?
ID: 10844 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Travis
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 30 Aug 07
Posts: 2046
Credit: 26,480
RAC: 0
Message 10964 - Posted: 16 Feb 2009, 1:22:38 UTC - in response to Message 10844.  

I would echo Seejay's comments, and both type of WUs (nm_ and ps_) are crunched in a similar time.

From my observation, limited due to the insta-purge, the blocks of errors reported earlier seem to have stopped.

Is that your view Travis?


It doesn't look like things are erroring out very much at all anymore, at least from what I can see in the database. I think I'll be increasing the purge time tomorrow.
ID: 10964 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile banditwolf
Avatar

Send message
Joined: 12 Nov 07
Posts: 2425
Credit: 524,164
RAC: 0
Message 11048 - Posted: 16 Feb 2009, 21:25:17 UTC

Finally got ps searches they run a tad longer ~ 10% for me. They do have a slightly larger varience on runtime.
Doesn't expecting the unexpected make the unexpected the expected?
If it makes sense, DON'T do it.
ID: 11048 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Misfit
Avatar

Send message
Joined: 27 Aug 07
Posts: 915
Credit: 1,503,319
RAC: 0
Message 11051 - Posted: 16 Feb 2009, 21:55:46 UTC - in response to Message 11048.  

Finally got ps searches they run a tad longer ~ 10% for me. They do have a slightly larger varience on runtime.

So far the timings are the same for me.
me@rescam.org
ID: 11051 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile banditwolf
Avatar

Send message
Joined: 12 Nov 07
Posts: 2425
Credit: 524,164
RAC: 0
Message 11053 - Posted: 16 Feb 2009, 22:03:40 UTC - in response to Message 11051.  

Finally got ps searches they run a tad longer ~ 10% for me. They do have a slightly larger varience on runtime.

So far the timings are the same for me.


More have ran now. About half run the same time, the others vary up to 10% longer for some reason.
Doesn't expecting the unexpected make the unexpected the expected?
If it makes sense, DON'T do it.
ID: 11053 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Travis
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 30 Aug 07
Posts: 2046
Credit: 26,480
RAC: 0
Message 11084 - Posted: 17 Feb 2009, 0:45:24 UTC - in response to Message 11053.  

Finally got ps searches they run a tad longer ~ 10% for me. They do have a slightly larger varience on runtime.

So far the timings are the same for me.


More have ran now. About half run the same time, the others vary up to 10% longer for some reason.


stripe 86 takes longer to compute than stripes 79 and 82, that's probably why.
ID: 11084 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Misfit
Avatar

Send message
Joined: 27 Aug 07
Posts: 915
Credit: 1,503,319
RAC: 0
Message 11086 - Posted: 17 Feb 2009, 0:51:33 UTC - in response to Message 11084.  

Finally got ps searches they run a tad longer ~ 10% for me. They do have a slightly larger varience on runtime.

So far the timings are the same for me.

More have ran now. About half run the same time, the others vary up to 10% longer for some reason.

stripe 86 takes longer to compute than stripes 79 and 82, that's probably why.

Currently my estimated times (SSSE3 optimized) are...
79 - 6:45
82 - 6:45
86 - 6:58
me@rescam.org
ID: 11086 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Previous · 1 · 2

Message boards : Number crunching : particle swarm searches -- ps_X

©2024 Astroinformatics Group