Advanced search

Message boards : Number crunching : Average Run Time

Author Message
Operator
Send message
Joined: 15 May 11
Posts: 108
Credit: 297,176,099
RAC: 0
Level
Asn
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 28220 - Posted: 26 Jan 2013 | 18:33:10 UTC

Was checking the server status page this morning because I was getting a "no work available" message in the log and came across the Average Run Time in the lower right corner of the page.

Basically, it said that on long runs (8-12 hours on fastest cards) the current average (in hours) was 4.37 with a minimum of 0.45 and a maximum of 29.09 hrs.

There are hosts that can complete a long run WU in less than half an hour?

I'm feeling more than a little inadequate at the moment! I'm running two GTX 590's and thought I was crunching at a reasonable rate. But less than half an hour? Has Nvidia released a GTX 990 Ti SSC that uses dual quantum processors or something? Or am I misinterpreting what that chart says?

Operator

____________

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 7,520
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 28227 - Posted: 26 Jan 2013 | 23:23:09 UTC - in response to Message 28220.

Was checking the server status page this morning because I was getting a "no work available" message in the log and came across the Average Run Time in the lower right corner of the page.

Basically, it said that on long runs (8-12 hours on fastest cards) the current average (in hours) was 4.37 with a minimum of 0.45 and a maximum of 29.09 hrs.

There are hosts that can complete a long run WU in less than half an hour?

There are no such hosts. These short runtimes are those of failing workunits.

I'm feeling more than a little inadequate at the moment! I'm running two GTX 590's and thought I was crunching at a reasonable rate. But less than half an hour? Has Nvidia released a GTX 990 Ti SSC that uses dual quantum processors or something? Or am I misinterpreting what that chart says?

Don't blame yourself, the chart is inadequate here.
It's meaningless to include the failing workunits into this statistics, the result is quite misleading.
I've noticed this, and posted about it nearly a year ago, but it's still there.

Post to thread

Message boards : Number crunching : Average Run Time

//