12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879 |
- #include <starpu.h>
- extern struct starpu_opencl_program programs;
- void scal_opencl_func(void *buffers[], void *_args)
- {
- float *factor = _args;
- int id, devid, err;
- cl_kernel kernel;
- cl_command_queue queue;
- cl_event event;
-
- unsigned n = STARPU_VECTOR_GET_NX(buffers[0]);
-
- cl_mem val = (cl_mem)STARPU_VECTOR_GET_DEV_HANDLE(buffers[0]);
- {
- id = starpu_worker_get_id();
- devid = starpu_worker_get_devid(id);
- err = starpu_opencl_load_kernel(&kernel, &queue,
- &programs,
- "vector_mult_opencl",
- devid);
- if (err != CL_SUCCESS) STARPU_OPENCL_REPORT_ERROR(err);
- err = clSetKernelArg(kernel, 0, sizeof(n), &n);
- err |= clSetKernelArg(kernel, 1, sizeof(val), &val);
- err |= clSetKernelArg(kernel, 2, sizeof(*factor), factor);
- if (err) STARPU_OPENCL_REPORT_ERROR(err);
- }
- {
- size_t global=n;
- size_t local;
- size_t s;
- cl_device_id device;
- starpu_opencl_get_device(devid, &device);
- err = clGetKernelWorkGroupInfo (kernel, device, CL_KERNEL_WORK_GROUP_SIZE,
- sizeof(local), &local, &s);
- if (err != CL_SUCCESS) STARPU_OPENCL_REPORT_ERROR(err);
- if (local > global) local=global;
- err = clEnqueueNDRangeKernel(queue, kernel, 1, NULL, &global, &local, 0,
- NULL, &event);
- if (err != CL_SUCCESS) STARPU_OPENCL_REPORT_ERROR(err);
- }
- {
- clFinish(queue);
- starpu_opencl_collect_stats(event);
- clReleaseEvent(event);
- starpu_opencl_release_kernel(kernel);
- }
- }
|