clFFT for GPU on i.MX 8M board

[golchin2010p]

Hi,

I would to use clFFT for GPU core of my board (phyBOARD-Polaris i.MX 8M). I have followed the instruction of this link https://github.com/clMathLibraries/clFFT.  For kernel size of 128, it takes more than a second to do the computations. Is there a way to reduce the kernel computation for larger kernel sizes?

I would greatly appreciate your help.

Best regards,

Parian

[CarlosCasillas]

Hi Parian,
As the mentioned board is from Pythec, you should directly contact them for hardware/software questions:

Support | PHYTEC 

In case if requiring a custom software integration, you may consider NXP Professional Services:

NXP Professional Services | NXP 

Hope this will be useful for you.
Best regards!
/Carlos
-------------------------------------------------------------------------------
Note:
- If this post answers your question, please click the "Mark Correct" button. Thank you!

-------------------------------------------------------------------------------