![]() The top line should report the device (or devices) available. $ sudo ln -s /usr/lib/libGL.so.1 /usr/lib/libGL.soĤ) Compile the examples in the SDK $ cd ~/NVIDIA_GPU_Computing_SDK/Cĥ) Run the device query project to determine if programs can access the GPU: $ cd ~/NVIDIA_GPU_Computing_SDK/C/bin/linux/release gpucomputingsdk_3.2.16_n Test the InstallationĢ) Before you can compile any of the examples, you need a few libraries: $ sudo apt-get install libglut3-devģ) Create a few links so the code knows where to find the libraries: $ sudo rm /usr/lib/libGL.so If you want to have Ubuntu (or any Linux variant with Bash) call them on startup, use your favorite editor to open ~/.bashrc and add the following lines (I put them at the end): # CUSTOM – Add export path for CUDAĮxport LD_LIBRARY_PATH=/usr/local/cuda/lib:$LD_LIBRARY_PATHĥ) Install the SDK as a regular user (when asked, install to the default directory): $. $ export LD_LIBRARY_PATH=/usr/local/cuda/lib:$LD_LIBRARY_PATHĤ) Optional: You many notice that you have to re-type the export lines every time you restart the computer. cudatoolkit_3.2.16_linux_32_ubuntu10.04.runģ) Define PATH variables to include the new directory (note: change lib to lib64 for 64-bit installations): $ export PATH=/usr/local/cuda/bin:$PATH Install the CUDA Toolkit and SDKġ) If, for some reason, you have used the CUDA SDK previously, remove all the files from /usr/local/cuda and ~/NVIDIA_GPU_Computing_SDK.Ģ) Install the toolkit: $ sudo. Check the “NVIDIA Driver Version” field in “X Server Information.” It should match the file version you just installed (260.19.26 in this case). OR reboot the system: $ sudo shutdown –r nowĩ) Login and make sure that the correct version of the driver was installed: System -> Administration -> NVIDIA X Server Settings. devdriver_3.2_linux_32_260.19.26.runĦ) If you get an error about the script failing, say “OK” to continue anyway.ħ) Say “No” if asked to run the nvidia-xconfig utility.Ĩ) Restart the GUI with: $ sudo /etc/init.d/gdm start run file as superuser (note the version/filename might be different): $ sudo. Install the Driverģ) Kill the X server by issuing: $ sudo /etc/init.d/gdm stopĤ) Assuming you only have the 3 NVIDIA files in your ~/Downloads directory, give them all execution permission: $ cd ~/Downloadsĥ) Execute the driver install. Save them to some directory on your computer. CUDA Toolkit for Ubuntu Linux 10.04 (32-bit).If it is not installed, call the following: $ sudo apt-get install gcc build-essentialĤ) You can check the version of gcc with: $ gcc –versionĥ) For this post, I installed gcc 4.4.3 Downloadįrom the “Downloads” page on NVIDIA’s “GPU Computing” site, navigate to the Linux section and download the following files: Pre-requisitesġ) CUDA-enabled graphics card (I’m using a GTX 470)Ģ) A supported Linux distribution (I’m using Ubuntu 10.04 LTS 32-bit)ģ) GCC installed. I hope it works as a good starting place, though. ![]() Note that in a couple weeks, Ubuntu or CUDA might change, and these steps will no longer apply. I’ve created a step-by-step guide on getting CUDA running in Ubuntu. I recommend going here as a starting place: ![]() For this walkthrough, I will give you a tutorial on how to set up the CUDA SDK on Linux (specifically, Ubuntu). ![]() Downloadsįor those crazy enough to dive into the world of GPGPU, one option is NVIDIA’s CUDA. Obviously some things have changed, but it should at least provide a decent starting place. Please keep in mind that it was written a few years ago with Ubuntu 10.04 and the CUDA toolkit 3.2.16. DISCLAIMER: This is a post from my old blog that I copied here to help out anyone interested in installing CUDA on Ubuntu. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |