Is there any limit in the number of nested IFs we can use in your OpenCL implementation?
I ask this because if I use more than 6 the SKA tool starts to output N/A values plus my kernels start to hang...
Thanks.
from profilec doc.
FCStacks - The number of flow control stack size used by the kernel (only for GPU device). This number may affect the number of wavefronts in-flight. To reduce the stack size, reduce the amount of flow control nesting in the kernel.
bubu,
I donlt think it should return N/a in any case. Can you please provide a test case.