Effacer les filtres
Effacer les filtres

gpuDevice command very slow

4 vues (au cours des 30 derniers jours)
Anthony
Anthony le 17 Juin 2013
I am running CUDA kernels using the parallel computing toolbox and r2012a. Recently upgraded to a 600 series (Kepler) gpu. To setup the CUDA kernel we extract the maximum threads per block using: gpu_han=gpuDevice(1); k = parallel.gpu.CUDAKernel('gpu_tfm_linear_arb.ptx', gpu_tfm_linear_arb.cu'); k.ThreadBlockSize = gpu_han.MaxThreadsPerBlock;
This is now executing very slowly (order 2mins). If I specify the threadblocksize manually to the max of the card (1024 in this case), it executes in 0.1 s.
This used to run quickly with a 400 series card. Any help gratefully received

Réponse acceptée

James Lebak
James Lebak le 17 Juin 2013
MATLAB R2012a doesn't include code for the Kepler series GPUs. This means that the very first time you call any GPU command after upgrading to a Kepler card, be it gpuDevice or something else, MATLAB will wait for the CUDA driver to just-in-time compile all the PTX code that ships with MATLAB for the Kepler device. This behavior allows MATLAB to work with cards that weren't available when that version of MATLAB was released.
The good news is that this should be a one-time hit. The next time you start MATLAB the JIT'd code should be cached and you should not get the performance hit.
The other thing to point out is that you should consider recompiling your CUDA kernel and producing PTX for the new card, if you haven't already done so, or you may see a similar one-time hit the first time you launch your own kernel for the same reason.

Plus de réponses (2)

Andrei Pokrovsky
Andrei Pokrovsky le 15 Sep 2016
Modifié(e) : Andrei Pokrovsky le 15 Sep 2016
Try setting these env vars:
export CUDA_CACHE_MAXSIZE=2147483647
export CUDA_CACHE_DISABLE=0
This cured the problem on my GTX1080.
https://devblogs.nvidia.com/parallelforall/cuda-pro-tip-understand-fat-binaries-jit-caching/

Anthony
Anthony le 17 Juin 2013
Thanks that is helpful. I don't have write access to the program data directory, is there a way to alter where the cache of this data is stored?
  2 commentaires
Edric Ellis
Edric Ellis le 18 Juin 2013
The cache is not stored where the program lives, this page from NVIDIA has all the gory details, including this:
  • on Windows, %APPDATA%\NVIDIA\ComputeCache,
  • on MacOS, $HOME/Library/Application\ Support/NVIDIA/ComputeCache,
  • on Linux, ~/.nv/ComputeCache
Anthony
Anthony le 12 Juil 2013
Thanks a lot, don't know how I missed that. Problem fixed.

Connectez-vous pour commenter.

Catégories

En savoir plus sur GPU Computing dans Help Center et File Exchange

Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by