在NVIDIA硬件上运行OpenCL程序 [英] Run OpenCL program on NVIDIA hardware

问题描述

我已经构建了一个简单的基于OpenCL的程序(使用C ++)，并在Windows 8系统上使用AMD FirePro V4900卡进行了测试.我正在使用AMD APP SDK.

I've build a simple OpenCL based program (in C++) and tested in on Windows 8 system with AMD FirePro V4900 card. I was using AMD APP SDK.

当我将二进制文件复制到另一台计算机(带有NVIDIA Quadro 4000卡的Windows 8)时， 过程入口点clReleaseDevice不能位于动态链接库(我的程序的exe)中".第二台计算机已安装了最新的NVIDIA驱动程序和CUDA 5.

When I copy my binaries to the other machine (Windows 8 with NVIDIA Quadro 4000 card) I get "The procedure entry point clReleaseDevice couldn't be located in the dynamic linked library (exe of my program)". This second machine has the latest NVIDIA drivers and CUDA 5 installed.

要使它与NVIDIA硬件配合使用，我有什么想法?

Any ideas on what to I need to make it work with NVIDIA hardware?

推荐答案

这是OpenCL 1.1与1.2版本的问题. Nvidia仍在OpenCL 1.1版上.您已经使用了AMD的OpenCL 1.2.为了使OpenCL应用程序在两个系统上都可以运行，需要删除clReleaseDevice API调用和其他1.2调用，并使用带有1.1版本选项的AMD SDK重新编译.

Its an OpenCL 1.1 vs 1.2 version issue. Nvidia are STILL on OpenCL version 1.1. You have used AMD's OpenCL 1.2. To get and OpenCL app that works on both systems need to remove your clReleaseDevice API call and other 1.2 calls and recompile using the AMD SDK with the 1.1 version option.

这篇关于在NVIDIA硬件上运行OpenCL程序的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！