How to allocate a task to GPU

Hi,
I’ve installed OpennSSL in my system and on my virtual server. Now i’ve to monitor traffic between them and the CPU load. This is the first step that i’ve done. Now i’ve to try to allocate the openssl task to the GPU. can someone help me to write a litlle OpenCL program for this?
Thank you.

I suspect that you misunderstand what OpenCL and GPUs are capable of. Code (such as OpenSSL) written for a CPU cannot just run on a GPU - it has to be rewritten.

Ok, thank you. My target is assign to GPU some threads that kernel usually assign to CPU. I’m talking about jobs that perform mathematical calculations. It’s a work for my Univeristiy thesis. I suppose that i’ve to work with opencl. Can someone help me? is there a tutorial opencl? thank you

ok, I’ll try to post a more precise question: i’ve a computer with a lot of CPU and GPU. My idea is to create a kernel program for each GPU device. I would assign to each kernel program a thread of process for parallel work and then join each single thread for final result. Is it possible?
thank you so much!

Yes.

You’d create a command queue for each GPU and feed it work. You could also use OpenCL to enqueue work for the CPUs.

[QUOTE=Dithermaster;30105]Yes.

You’d create a command queue for each GPU and feed it work. You could also use OpenCL to enqueue work for the CPUs.[/QUOTE]

thank you for your reply. But i think if i would assign to GPU some processes that usually run on CPU i’ve to rewrite the code of the processes. is that right?