How expensive is calling clEnqueueNDRangeKernel?

[santevid]

Question #1

I have a function Run() that calls execution of two kernels:

void Run()

{

//I’am using C++ bindings

queue->enqueueNDRangeKernel(*kernelRow, cl::NullRange, *globalRangeRow, *localRangeRow, NULL, eventRow);

queue->enqueueNDRangeKernel(*kernelColumn, cl::NullRange, *globalRangeCol, *localRangeCol, NULL, eventCol);

queue.finish()

}

// As you see, I’m using events (eventRow, eventCol) because of profiling.

How expensive (time performance) is calling enqueueNDRangeKernel (or clEnqueueNDRangeKernel ).

With Nvidia OpenCL Profiler, I got total time of execution (on GPU) 351 ms, but when I measured time of running of method Run()

I got 622 ms.

Why this difference is so large?

When is data transfered to GPU, on calling clEnqueueNDRangeKernel or when buffer is created (clCreateBuffer)?

I tested on NVIDIA GT240.

I also tested on ATI HD 5670 and difference is much smaller.

[madsen]

Hi!

I measured the overhead in launching my kernel to be 41um here:
[url=“http://forums.nvidia.com/index.php?showtopic=162539”]The Official NVIDIA Forums | NVIDIA

This is of cause just on my machine, but it means that even though my calculations run much faster on the GPU, I can’t benefit since the overhead is killing the execution.

Madsen