If this gives an error, and if so, then how to check it? (Opencl)

Question

I learned how to create reliable code in OpenCL and look at the following kernel code:

string kernel_code =
" void kernel simple_add(global const int *A,    "
"                        global const int *B,    "
"                        global int *C, int n) { "
"                                                "
"   int index = get_global_id(0);                "
"   C[index]=A[index]+B[index];                  "
" }                                              ";

And using a special code to send it to the GPU:

Kernel ker(program, "simple_add");
ker.setArg(0, buffer_A);
ker.setArg(1, buffer_B);
ker.setArg(2, buffer_C);
ker.setArg(3, N);
q.enqueueNDRangeKernel(ker,NullRange,NDRange(32),NDRange(32));
q.finish();

The fact is that I use more work items than necessary, so I think I should check to see if the index is indexed by kernel code. But I do not use it and do not check the errors returned by enqueueNDRangeKernel, or upon completion it gives me CL_SUCCESS .. Somehow this should not give me errors for any reason or I don’t know how to get them .. What is the answer?

Answer 1

C ++, - undefined OpenCL, , . , ​​ . , ( IOMMU) , .

, , , GPU 4096 - . , - 4096- , .