gpuDevice command very slow
1 visualizzazione (ultimi 30 giorni)
Mostra commenti meno recenti
Anthony
il 17 Giu 2013
Modificato: Andrei Pokrovsky
il 15 Set 2016
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
0 Commenti
Risposta accettata
James Lebak
il 17 Giu 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.
0 Commenti
Più risposte (2)
Andrei Pokrovsky
il 15 Set 2016
Modificato: Andrei Pokrovsky
il 15 Set 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/
0 Commenti
Anthony
il 17 Giu 2013
2 Commenti
Edric Ellis
il 18 Giu 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
Vedere anche
Categorie
Scopri di più su GPU Computing in Help Center e File Exchange
Prodotti
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!