Two possible reasons:

• Your OpenCL kernel actually runs on the CPU (you didn't tell what implementation you use)
• Your OpenCL kernel runs on a GPU, but the runtime is absolutely dominated by PCIe transfer latency, not execution speed.

Note that adding together two values on a GPU is a ridiculously small amount of work compared to PCIe bandwidth (or even GPU memory bandwidth). It is therefore not surprising that any measurements you make turn out "kind of strange".

Also, launching a kernel and synchronizing for the result isn't completely "free" either.

Try again with a much more complicated kernel, and you'll likely see a much bigger (50-100 times) difference.

Two possible reasons:

• Your OpenCL kernel actually runs on the CPU (you didn't tell what implementation you use)
• Your OpenCL kernel runs on a GPU, but the runtime is absolutely dominated by PCIe transfer latency, not execution speed.

Note that adding together two values on a GPU is a ridiculously small amount of work compared to PCIe bandwidth (or even GPU memory bandwidth). It is therefore not surprising that any measurements you make turn out "kind of strange".

Try again with a much more complicated kernel, and you'll likely see a much bigger (50-100 times) difference.

Two possible reasons:

 

1. Your OpenCL kernel actually runs on the CPU (you didn't tell what implementation you use)
2. Your OpenCL kernel runs on a GPU, but the runtime is absolutely dominated by PCIe transfer latency, not execution speed.

Note that adding together two values on a GPU is a ridiculous amount of work compared to PCIe bandwidth (or even GPU memory bandwidth). It is therefore not surprising that any measurements you make are kind of "strange".

 

Try again with a much more complicated kernel, and you'll likely see a much bigger (50-100 times) difference.