Message boards :
Graphics cards (GPUs) :
Any benefit from CUDA 4.1 drivers?
Message board moderation
| Author | Message |
|---|---|
|
Send message Joined: 31 Jul 10 Posts: 7 Credit: 449,728,430 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
Saw this today: http://www.techpowerup.com/159439/NVIDIA-Releases-CUDA-Toolkit-4.1.html So CUDA 4.1 is now a GA release I guess. Is there any advantage or improvement in using this version's dev driver versus the older CUDA 4.0 dev driver? (4.1 = 285.05.32 vs. 4.0 = 270.41.19, for Linux anyways) I've had good success running the CUDA 4.0 dev driver in the past and am leery of trying an upgrade to any newer ones on Linux. Just want to see if there would be any tangible gains from using the newer one. Thanks. |
|
Send message Joined: 24 Dec 08 Posts: 738 Credit: 200,909,904 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Saw this today: I asked the same thing of the Seti optimizers. Their answer was that the new stuff was a bit faster on newer (Fermi based) cards but a bit slower on the older cards (GTX295 etc). I am not sure it that was the new optimizing compiler or the (currently beta) driver. We assume the drivers are waiting on the GTX6xx cards being released some time this quarter. Generally I wait for a driver to become WHQL certified before updating. BOINC blog |
|
Send message Joined: 24 Dec 08 Posts: 738 Credit: 200,909,904 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
I asked the same thing of the Seti optimizers. Their answer was that the new stuff was a bit faster on newer (Fermi based) cards but a bit slower on the older cards (GTX295 etc). I am not sure it that was the new optimizing compiler or the (currently beta) driver. It seems the speed up came from compiling with the cuda41rc2 and cuda41 compilers and only on Fermi-based cards. BOINC blog |
oldDirtySend message Joined: 17 Jan 09 Posts: 22 Credit: 3,805,080 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
So what you waiting for, hurry hurry.. ^^ |
GDFSend message Joined: 14 Mar 07 Posts: 1958 Credit: 629,356 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() |
Not for us, the code was already well optimized. gdf |
©2025 Universitat Pompeu Fabra