Better performace: GPU + Workers
7 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Nycholas Maia
le 5 Mai 2017
Commenté : Joss Knight
le 15 Mai 2017
How can I know what is the best optimization method for me?
- Run the code only inside the GPU? Or run only inside the multiple workers/cores?
- Is possible to join/mix theses two methods to get a even better performance?
0 commentaires
Réponse acceptée
Joss Knight
le 13 Mai 2017
It depends what you're optimizing. Use of the GPU only really make sense if the objective function is a large enough operation to fully utilize the GPU (e.g. it is multiplying a very large matrix by a vector, such as in iterative solvers). Use of a parallel pool with GPU computation only gains you anything if you have multiple GPUs, but is perfectly possible if you are implementing your own objective function.
Alternatively, if you are on linux, you can try using MPS to allow overlapping use of the same GPU on multiple workers. This can potentially make it viable to use the GPU with smaller operations.
3 commentaires
Walter Roberson
le 14 Mai 2017
"Is not good always use GPU in small or medium operations too?"
Not always. There is communications overhead with the GPU.
Joss Knight
le 15 Mai 2017
Well, my answer to that would be no, the GPU SMs are a lot slower than a CPU core, so you need a lot of parallelism to make it worthwhile.
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur GPU Computing dans Help Center et File Exchange
Produits
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!