Forum > GPU crunching
GTX 460 superclocked
Ghost0210:
Could be wrong on the memory usage :P
But thats what I've found on this card 1 shorty ~3min 20, 2 @ a time ~5min 50, 3 at a time just over 7 minutes 30, this is about a 20% increase over the stock fermi app
Jason G:
I find 2 at a time to be best on my 480, stock is better with 3 at a time because it uses less cores. Probably as things progress I'll get a single task to use the whole cards, so back to 1-2 tasks will become optimal.
The 460 is a bit unknown at this point, because there is a big question mark on how to use 48 cores per multiprocessor effectively, given that it is 3 half warps. We probably won't know much more about how to handle that the best until further documentation becomes available, but to my mind may require some significant adaptation of kernel geometries to get the most from. All indications are that these are going to be extremely popular cards, so it will be done eventually, whatever changes (if any) are needed.
Jason
Frizz:
--- Quote from: Ghost ---But thats what I've found on this card 1 shorty ~3min 20, 2 @ a time ~5min 50, 3 at a time just over 7 minutes 30, ...
--- End quote ---
and:
--- Quote from: Ghost ---On my 465 I get the best through put with two tasks running at a time
--- End quote ---
OK ... when I do the math 3 WUs at a time is the optimum, no?
Completion time for 3 WUs:
1 at a time: 3 x 3:20 -> 10:00
2 at a time: 1.5 x 5:50 -> 8:45
3 at a time: 1 x 7:30 -> 7:30
Jason G:
--- Quote from: Frizz23 on 10 Aug 2010, 03:34:49 pm ---OK ... when I do the math 3 WUs at a time is the optimum, no?
Completion time for 3 WUs:
1 at a time: 3 x 3:20 -> 10:00
2 at a time: 1.5 x 5:50 -> 8:45
3 at a time: 1 x 7:30 -> 7:30
--- End quote ---
If the tasks used for measurement were all the same angle range yes, that's fine. Quite possibly the best 'for now', because of those big question marks over using the 460 architecture effectively.
Don't forget about cpu overhead & Bus contention though ... so always best to measure. Things don't 'always' scale nicely when you try cram in more work than the hardware can handle.
Frizz:
Would you say its OK if I go for the 768MB version?
Navigation
[0] Message Index
[#] Next page
[*] Previous page
Go to full version