gpuArray of variable size for codegen
3 views (last 30 days)
Show older comments
Arabarra
on 2 Nov 2018
Commented: Benjamin Ballintyn
on 13 Jan 2020
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
0 Comments
Accepted Answer
Joss Knight
on 5 Nov 2018
Support for gpuArray input comes with R2018b. I don't know about the other thing, sorry.
1 Comment
Benjamin Ballintyn
on 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.
More Answers (0)
See Also
Categories
Find more on Kernel Creation from MATLAB Code in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!