Message boards :
Number crunching :
Is nVidia TESLA good for Seti?
Message board moderation
Author | Message |
---|---|
Igor_b Send message Joined: 25 Jun 00 Posts: 4 Credit: 940,538,303 RAC: 24 |
Hello, Currently, for Seti@Home, we are mainly using nVidia GeForce and some AMD Radeon GPU's. We'd like to increase our crunching performance by applying nVidia TESTLA GPU's, we never used it before. I've already tried to find information about it, but didn't found anything. So, will TESLA GPU have really magnificent performance when running Seti? On nVidia GeForce 1080 we get about 40 000 in computer statistics. Any information will be appreciated. Best regards. |
rob smith Send message Joined: 7 Mar 03 Posts: 22189 Credit: 416,307,556 RAC: 380 |
Unless one goes a long way up the Tesla tree it is unlikely that one would see a significant gain in performance over a GTX1080 or GTX1080ti running the "special application" under Linux, but by then the price is so high as to make it "not economic" (GTX1080 = ~£520, Tesla 16GB NVIDIA Tesla P100 = ~£6400) Bob Smith Member of Seti PIPPS (Pluto is a Planet Protest Society) Somewhere in the (un)known Universe? |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
Hello, Tesla and GeForce GPUs use the same silicone. In most configurations the Tesla GPUs have lower clock rates. DP performance of GeForce GPUs is limited to 1/32 of SP and some Tesla GPUs are 1/2 of SP. However SETI@home applications use SP and not DP. So Tesla performance compared the GeForce counterpart would be the same or less. Some users here have setup hosts in cloud computing environments that offer Tesla GPUs. Which may be a lower cost alternative versus purchasing hardware. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
©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.