Cuda Installation and Verification on Fedora 13

Accelerated Computing CUDA CUDA Programming and Performance
1

Hello,

I am trying to install CUDA on a machine running Fedora 13. The machine currently has 4 individual Nvidia Tesla C1060 cards installed.

I have followed the steps from this website http://www.r-tutor.com/gpu-computing/cuda-installation/cuda3.2-fc13 (except I installed the updated 4.0 versions).

I used these files:

gpucomputingsdk_4.0.17_linux.run
devdriver_4.0_linux_64_270.41.19.run
cudatoolkit_4.0.17_linux_64_fedora13.run

To my knowledge I followed the guide correctly, however at the end when I run deviceQuery I get…

CUDA Device Query (Runtime API) version (CUDART static linking)

cudaGetDeviceCount returned 38
→ no CUDA-capable device is detected
[deviceQuery] test results…
FAILED

Press ENTER to exit…

I am not sure what I did wrong. I installed the devdriver as root user and turned off the x server (also I installed Fedora 13 with basic graphics). I then installed the cuda toolkit and sdk with no problems.

I have did some reading and noticed many people suggesting running nvidia-xconfig. However, when I do that I do not get a display.

Any tips will be appreciated. It is to be said that I am new to linux.

Thanks,

Truxal

Also, is Fedora 13 the best choice for CUDA?

More info:

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2011 NVIDIA Corporation
Built on Thu_May_12_11:09:45_PDT_2011
Cuda compilation tools, release 4.0, V0.2.1221

NVRM version: NVIDIA UNIX x86_64 Kernel Module 275.09.07 Wed Jun 8 14:16:46 PDT 2011
GCC version: gcc version 4.4.5 20101112 (Red Hat 4.4.5-2) (GCC)

2

Hello,

I am trying to install CUDA on a machine running Fedora 13. The machine currently has 4 individual Nvidia Tesla C1060 cards installed.

I have followed the steps from this website http://www.r-tutor.com/gpu-computing/cuda-installation/cuda3.2-fc13 (except I installed the updated 4.0 versions).

I used these files:

gpucomputingsdk_4.0.17_linux.run
devdriver_4.0_linux_64_270.41.19.run
cudatoolkit_4.0.17_linux_64_fedora13.run

To my knowledge I followed the guide correctly, however at the end when I run deviceQuery I get…

CUDA Device Query (Runtime API) version (CUDART static linking)

cudaGetDeviceCount returned 38
→ no CUDA-capable device is detected
[deviceQuery] test results…
FAILED

Press ENTER to exit…

I am not sure what I did wrong. I installed the devdriver as root user and turned off the x server (also I installed Fedora 13 with basic graphics). I then installed the cuda toolkit and sdk with no problems.

I have did some reading and noticed many people suggesting running nvidia-xconfig. However, when I do that I do not get a display.

Any tips will be appreciated. It is to be said that I am new to linux.

Thanks,

Truxal

Also, is Fedora 13 the best choice for CUDA?

More info:

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2011 NVIDIA Corporation
Built on Thu_May_12_11:09:45_PDT_2011
Cuda compilation tools, release 4.0, V0.2.1221

NVRM version: NVIDIA UNIX x86_64 Kernel Module 275.09.07 Wed Jun 8 14:16:46 PDT 2011
GCC version: gcc version 4.4.5 20101112 (Red Hat 4.4.5-2) (GCC)

3

Hello,

I have exactly the same problem. Im installing fedora 13 on a sistem with 3 tesla C1060. Furthermore, after update to fedora 13, I can´t configurate succesfully the xorg.conf file on /etc/X11, so the gnome is not working. Have u fix the problem?

Thanks

Regards

Gonzalo