is there a possibility to use self-defined C++ - classes in an OpenCL kernel? It should work like this:
I apologize in advance for the vagueness of this question. Background: I am attempting to write a morphological image processing functio开发者_运维知识库n in OpenCL.I have a __local buffer which I u
I know the following 开发者_运维知识库formula can be used to convert RGB images to YUV images. In the following formula, R, G, B, Y, U, V are all 8-bit unsigned integers, and intermediate values are 1
I have a NVida graphic card and I would like to use it for serious computations. I downloaded a driver from NVida webside and installed JOCL bindings. I downloaded one of the demo programs and compile
i have a problem to which i want a solution and fast....any help is appreciated. I have a laptop with ubuntu10.04 and Nvidia 8400M GS graphics card. I recently started some work on OpenCL and wanted
i have lines of 3 hashes (ie md5, 128bit). actually plenty of them. think billions, thus they wont fit in main memory.
I want to v开发者_运维百科iew the reference counters for these things so I can be sure that they were deleted. Is it possible?
I guess the simple way is to restart the program, but is there a w开发者_JAVA百科ay to get the same effect without closing the program? I call the proper release statements for my allocated memory, my
Quick note: I am using JOCL and Java for my openCL development. I think the calls to openCL that I need will be the same as if I was just using C or C++.
I am using the following parameters for my simulation on Geforce GT 220 card - number of compute units = 6
加载中,请稍侯......