2
$\begingroup$

Before there was CUDA or OpenCL people were using GPUs for computation. I am trying to find out how they did that -- because I want to press my Rasberry Pi's GPU for computing and it does not seem to have OpenCL support.

I am looking for notes on how they did this.

I've done cursory Googling but have come up empty handed -- primarily because I think the search indexes and full of CUDA and OpenCL related material.

Would appreciate any pointers on how to use GPUs for computation in the absence of CUDA and OpenCL.

$\endgroup$
3
$\begingroup$

I don't know a definitive source, but have a look at "GPU Gems 2", which is a book published by NVIDIA about ten years ago and available online. While much of it is about computer graphics, it has a number of sections devoted to general purpose computing on GPUs from the time before CUDA and OpenCL.

I am not familiar enough with Raspberry Pi to tell if this book will actually help you very much.

$\endgroup$
3
$\begingroup$

Since your question seems to be specifically about the Raspberry Pi, I would suggest searching for "Raspberry Pi GPGPU" in addition to the book suggested by @Kirill. GPGPU refers to general purpose computing on graphics processing units and should get you results specific to using the RPi's GPU for non-graphics tasks.

You should also have a look at the answers to this question on RaspberryPi.Stackexchange which is basically a duplicate of yours. The conclusion seems to be that OpenCL is not likely to be implemented on the RPi so your best bet is to use OpenGL capabilities to perform your computations via shaders. This is more limited than truly general purpose techniques such as OpenCL, but appears to be the best you can do. That question is a couple years old so you might want to ask over there about any updates since then.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.