Hello) I have a simple question. How can I run AMDAPP on NVidia card? Do I need to install any additional framework?
When you look here: http://developer.amd.com/resources/heterogeneous-computing/opencl-zone/getting-started-with-opencl/
and here: http://developer.amd.com/tools/heterogeneous-computing/amd-accelerated-parallel-processing-app-sdk/system-requirements-driver-compatibility/
AMDAPP supports AMD GPUs and x86 CPUs only.
So to use OpenCL on nvidia you may go here: https://developer.nvidia.com/opencl
where the following is stated:
>> OpenCL support is included in the latest NVIDIA GPU drivers, available at www.nvidia.com/drivers
That is all true. However, you have to remember that OpenCL has been designed as a portable framework. In principle you can certainly take a binary compiled against AMD's SDK and run it on NVIDIA's runtime, and many people do so. You need to be careful to not use OpenCL 1.2 API calls in that situation.
To run you do of course need NVIDIA's runtime to be installed, but this may well come with their standard driver installation.
Many APP SDK Samples should run on the NVIDIA GPUs with just NVIDIA driver installed. Even for other samples using OpenCL 1,2 APIs , it should not be very difficult to make them work by using old APIs.
But I care about an error that I still have
Setting of real/effective user Id to 0/0 failed
FATAL: Module fglrx not found.
Error! Fail to load fglrx kernel module! Maybe you can switch to root user to load kernel module directly
what does it mean? examples works, but....
This is a known error and has been lodged with the engineernig team.
Will be fixed in a subsequent release.
Thanks for your patience and Sorry about the hassle.
Retrieving data ...