gpuArray of variable size for codegen

3 vues (au cours des 30 derniers jours)
Arabarra
Arabarra le 2 Nov 2018
Hi,
I'm trying to figure out the actual potential of the codegen capabilities on the GPU. In particular there are two points that I are not addressed explicitly in the online documentation (or I couldn't find the info).
*) First, it seems that the gpuArray type cannot be used as input. This is surprising, as it reduces drastically the applicability of mex functions generated with codegen... Is there a way to create mex files that accept gpuArray vectors as rhs?
*) Second, codegen throws a warning when input arguments of matrices that will be sent to the GPU (by a coder.gpu.kernelfun pragma inside the .m file) are declared to be of variable size using coder.typeof(). Again, a significant restriction on the usability of codegen.... Am I missing something here? Is there a way to trick codegen into accepting dynamically sized arrays as input for GPU processing?
thanks! Daniel

Réponse acceptée

Joss Knight
Joss Knight le 5 Nov 2018
Support for gpuArray input comes with R2018b. I don't know about the other thing, sorry.
  1 commentaire
Benjamin Ballintyn
Benjamin Ballintyn le 13 Jan 2020
I am running 2018b and when trying to use coder.typeof to specify a variable sized gpuArray input I get the following error:
"Variable-size dimension inputs are not supported when using CODER.TYPEOF to represent gpuArray inputs."
So it seems gpuArrays can be inputs to codegen functions but they cannot be specified as variable size. This is definitely a significant drawback since you would need to recompile the desired function(s) every time you want to change the input size.

Connectez-vous pour commenter.

Plus de réponses (0)

Catégories

En savoir plus sur Kernel Creation from MATLAB Code dans Help Center et File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by