Hey, I've recently started developing program under OpenCL and created Kernel and it's executed corretly, but somehow calculations made by my Intel CPU are faster then same one made by my grafic card NVIDIA GeForce 740. How is it posssible???
Here below is code of my Kernel, if accessing it is also needed I'll attach it later.链接已复制
2 回复数
Any architecture (CPU, GPU or FPGA) has coding style guidelines that impact performance; it is not surprising to get bad performance when these guidelines are not followed.
However, this forum is for Altera's OpenCL compiler; I can help you with optimizing your code for the Altera FPGAs. For GPU optimizations, please refer to NVIDIA's forum.One possible reason I might think of is the kernel launch overhead so you should profile your code and see whether it is the case.
Are you running your code on Windows or Linux? The overhead might be a problem if you have too small(fast) kernels or little data.