Hello,
I've been using a Tesla GPU card with 6GB RAM with R2012a for a number of years and it has worked well. But now I need to work on larger matrix sizes (e.g., 8192x8192 fft2) the good old Tesla card can't handle anymore. So recently we bought a new Quadro RTX 5000 with 16GB RAM. The 10.1 NVidia driver installed successfully:
Then I ran the following test code (gputest.m):
M = 4095;
a = rand(M);
b = gpuArray(a);
c = 2*b;
It runs sucessfully. But when I change M to 4096:
M = 4096;
a = rand(M);
b = gpuArray(a);
c = 2*b;
>> gputest
Error using parallel.gpu.GPUArray/mtimes
An unexpected error occurred trying to launch a kernel. The CUDA error
was: CUDA_ERROR_INVALID_VALUE.
Error in gputest (line 8)
c = 2*b;
It seems the maximum matrix size the new Quadro RTX 5000 card can handle is 4095x4095. I can transfer larger matrices to GPU (b = gpuArray(a) with M > 4095 doesn't give errors), just can't perform any operations on them. Any ideas? Are there some settings for the GPU driver I need to change?
Thank you.
4 Comments
Matt J (view profile)
Direct link to this comment
https://de.mathworks.com/matlabcentral/answers/453550-gpu-parallel-computing-error-with-quadro-rtx-5000#comment_688535
Xinbing Liu (view profile)
Direct link to this comment
https://de.mathworks.com/matlabcentral/answers/453550-gpu-parallel-computing-error-with-quadro-rtx-5000#comment_688561
Matt J (view profile)
Direct link to this comment
https://de.mathworks.com/matlabcentral/answers/453550-gpu-parallel-computing-error-with-quadro-rtx-5000#comment_688591
Xinbing Liu (view profile)
Direct link to this comment
https://de.mathworks.com/matlabcentral/answers/453550-gpu-parallel-computing-error-with-quadro-rtx-5000#comment_688598
Sign in to comment.