My program is launching a CL_OUT_OF_RESOURCES after enqueue a kernel. I’m pretty sure that is not a memory or registers issue. Basically because I tried with a very simple kernel with very few registers and I get the same error. In addition the memory arrays I am allocating in GPU are small (up to 200 cl_float2).

Is there some way to query which is exactly the reason why I get out of resources?

Did you pass a callback function when you called clCreateContext(). The callback may provide additional information about the error.

No, I didn’t. I’ll try it. Thank you.

I created the context with a call back function. It seems that the call back function does not handle the error lauched by the kernel. I read the following in the OpenCL especification:

NOTE: There are a number of cases where error notifications need to be delivered due to an error that occurs outside a context. Such notifications may not be delivered through the pfn_notify callback. Where these notifications go is implementation-defined.

May be my error occurs outside the context? If it is, is there some way to get more information about the error?