View Single Post
Old 2019-06-11, 22:05   #8
kriesel
 
kriesel's Avatar
 
"TF79LL86GIMPS96gpu17"
Mar 2017
US midwest

11100110001102 Posts
Default What's the best CUDA level to run CUDALucas with my GPU?

Update:
Please run Gpuowl instead if at all possible. Faster, more reliable, better error detection/correction, PRP with GEC and proof almost eliminating verification effort (~99.5%!).
Original post follows. Some old NVIDIA GPUs can't run Gpuowl.


It depends. What does best mean? What does your GPU require? What's the lowest CUDA level usable with your GPU? What's the highest CUDA level that still supports your GPU? What other GPUs do you have in the same system, that may constrain your choice of driver version or CUDA level? What driver versions and CUDA level support are available for the OS you are using? Which fft lengths will you run the most? Which releases have unacceptable reliability or bugs? Which is fastest on your hardware, and most-used fft lengths, providing the other considerations are acceptable?
In general, unless your GPU is so new that it requires the latest release, it's likely some other CUDA version could perform better. And it can vary depending on the program inputs.

I tested years ago for a performance dependence on NVIDIA driver version (~v260-v378), and did not see any statistically significant difference for driver version, on a GTX480 and Windows 7, CUDA versions 4.2-8.0. (However, on AMD, I have seen reductions of performance with driver version updates, including a drop of over 5%.) On NVIDIA, CUDA version does affect speed.

Test results ranging from CUDA5 to CUDA8 provided by ATH for his Titan black GPU are shown in the attachment. CUDA8 is rarely the fastest.


Top of reference tree: https://www.mersenneforum.org/showpo...22&postcount=1
Attached Files
File Type: pdf titan black cuda timings.pdf (18.7 KB, 358 views)

Last fiddled with by kriesel on 2022-04-20 at 14:31 Reason: minor edit
kriesel is offline