Hüseyin Tuğrul BÜYÜKIŞIK

Note: the test system is a low-end one with these components: - fx8150 at 2.1 GHz + 4GB RAM (single channel 1333 MHz DDR3) - GT1030 2GB VRAM (pcie v2.0...

By exchanging m_pBuff(experimenting on the host_mem setting) with my virtual array and setting 3MB caching per GPU, this happened:  This is with 4MB caching and a different page-size: ...

Now I only need to somehow tell windows to use this drive (can I use all 3 cards somehow for 3 drives or 1 drive?) for swap file. 1 RAM...

Constant with __ prefix type arrays can have a maximum of 64k elements and they are not shared between different kernels anyway ``` __constant char arr[max 64k]={0}; __kernel void hello(__global...

Using readonly flag makes an optimization for cases like: - on every iteration, cpu writes data, gpu reads - always goes through pci-e but more optimized path than normal array...

No, there is no equivalent of setting constant arrays from CPU command(like cudaMemcpyToSymbol), I'm sorry.

If there is "initialize once, use always" scenario, then I'd do this: - set read flag to true (default), write flag to false - initialize its data - run your...

Lastly, only OpenCL 2.0 supports static variables on global scope and it was not tested. I guess it works but only for same kernel (a kernel2 would still see another...

Hi, can you write here the code you are tring to run? Seems like a usage error? Or my documentation error?

Are you using threading binaries maybe that .net version only uses own threading dlls?