Message boards :
Number crunching :
nvidia 930m
Message board moderation
Author | Message |
---|---|
James Nelson Send message Joined: 23 Mar 02 Posts: 381 Credit: 4,806,382 RAC: 0 |
new laptop with nvidia 930m graphics with 2048 m dedicated ram have 2 threads running now but I'm wondering if 3 or 4 would be better. any thoughts ? |
rob smith Send message Joined: 7 Mar 03 Posts: 22228 Credit: 416,307,556 RAC: 380 |
A gtx930 is a low-end card, running two tasks at a time on it will be close to the limit, three at a time will probably be over the limit, and four will most certainly be counter productive. (BTW: SETI on a GPU is not limited by the amount of RAM, but by the number of GPU cores and the speed at which they can task swap - each GPU core is doing a very small bit of the overall task, and thus it swaps tasks very frequently) Bob Smith Member of Seti PIPPS (Pluto is a Planet Protest Society) Somewhere in the (un)known Universe? |
James Nelson Send message Joined: 23 Mar 02 Posts: 381 Credit: 4,806,382 RAC: 0 |
reportes as a geforce 930 not gtx not sure if that matters |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13751 Credit: 208,696,464 RAC: 304 |
new laptop with nvidia 930m graphics with 2048 m dedicated ram have 2 threads running now but I'm wondering if 3 or 4 would be better. any thoughts ? Given the specifications of the unit (limited number of CUDA cores & DDR3 memory, and much lower memory clock speed), 1 WU may be better than 2. Only way to be sure is to check the run times (for similar WUs) while running 2 at a time, then do the same when running 1 at a time & see which goes through the most WUs per hour. Grant Darwin NT |
James Nelson Send message Joined: 23 Mar 02 Posts: 381 Credit: 4,806,382 RAC: 0 |
ok trial and error method |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.