Difference between revisions of "Jetson/Installing CUDA"

From eLinux.org
Jump to: navigation, search
(Created the CUDA native installation instructions. (Needs formatting))
 
(Added an intro)
Line 1: Line 1:
== Installing the CUDA Toolkit onto your device for native on-board CUDA development ==
+
You have two options for developing CUDA applications for Jetson TK1:
 +
# native compilation (compiling code onboard the Jetson TK1)
 +
# cross-compilation (compiling code on an x86 desktop in a special way so it can execute on the Jetson TK1 target device).
 +
 
 +
Native compilation is generally the easiest option, but takes longer to compile, whereas cross-compilation is typically more complex to configure and debug, but for large projects it will be noticeably faster at compiling. The CUDA Toolkit currently only supports cross-compilation from an Ubuntu 12.04 Linux desktop. Whereas native compilation happens onboard the Jetson device and thus it doesn't matter which OS or desktop you use for native compilation.
 +
 
 +
== Installing the CUDA Toolkit onto your device for native CUDA development ==
 
Download the CUDA Toolkit for L4T by going to "https://developer.nvidia.com/jetson-tk1-support" and downloading the .deb file. (Make sure you use the "Toolkit for L4T" and not the "Toolkit for Ubuntu" since that is for cross-compilation instead of native compilation). You will need to register & log in first before downloading, so the easiest way is perhaps to download the file on your PC. Then if you want to copy the file to your device through your network you can do something like this:
 
Download the CUDA Toolkit for L4T by going to "https://developer.nvidia.com/jetson-tk1-support" and downloading the .deb file. (Make sure you use the "Toolkit for L4T" and not the "Toolkit for Ubuntu" since that is for cross-compilation instead of native compilation). You will need to register & log in first before downloading, so the easiest way is perhaps to download the file on your PC. Then if you want to copy the file to your device through your network you can do something like this:
 
scp ~/Downloads/cuda-repo-l4t-wr19.2_6.0-42_armhf.deb ubuntu@tegra-ubuntu:Downloads/.
 
scp ~/Downloads/cuda-repo-l4t-wr19.2_6.0-42_armhf.deb ubuntu@tegra-ubuntu:Downloads/.

Revision as of 06:34, 5 June 2014

You have two options for developing CUDA applications for Jetson TK1:

  1. native compilation (compiling code onboard the Jetson TK1)
  2. cross-compilation (compiling code on an x86 desktop in a special way so it can execute on the Jetson TK1 target device).

Native compilation is generally the easiest option, but takes longer to compile, whereas cross-compilation is typically more complex to configure and debug, but for large projects it will be noticeably faster at compiling. The CUDA Toolkit currently only supports cross-compilation from an Ubuntu 12.04 Linux desktop. Whereas native compilation happens onboard the Jetson device and thus it doesn't matter which OS or desktop you use for native compilation.

Installing the CUDA Toolkit onto your device for native CUDA development

Download the CUDA Toolkit for L4T by going to "https://developer.nvidia.com/jetson-tk1-support" and downloading the .deb file. (Make sure you use the "Toolkit for L4T" and not the "Toolkit for Ubuntu" since that is for cross-compilation instead of native compilation). You will need to register & log in first before downloading, so the easiest way is perhaps to download the file on your PC. Then if you want to copy the file to your device through your network you can do something like this: scp ~/Downloads/cuda-repo-l4t-wr19.2_6.0-42_armhf.deb ubuntu@tegra-ubuntu:Downloads/. On the device, install the .deb file and the CUDA Toolkit. eg: cd ~/Downloads

  1. Install the CUDA repo metadata that you downloaded manually for L4T

sudo dpkg -i cuda-repo-l4t-r19.2_6.0-42_armhf.deb

  1. Download & install the actual CUDA Toolkit including the OpenGL toolkit from NVIDIA. (It only downloads around 15MB)

sudo apt-get update sudo apt-get install cuda-toolkit-6-0

  1. Add yourself to the "video" group to allow access to the GPU

sudo usermod -a -G video $USER

Add the 32-bit CUDA paths to your .bashrc and start using it in your current shell console: echo "# Add CUDA bin & library paths:" >> ~/.bashrc echo "export PATH=/usr/local/cuda-6.0/bin:$PATH" >> ~/.bashrc echo "export LD_LIBRARY_PATH=/usr/local/cuda-6.0/lib:$LD_LIBRARY_PATH" >> ~/.bashrc source ~/.bashrc Verify that the CUDA Toolkit is installed: nvcc -V

If you think you will write your own CUDA code or you want to see what CUDA can do, then build & run some of the CUDA samples: Install writeable copies of the CUDA samples to your home directory (it will create a "NVIDIA_CUDA-6.0_Samples" folder):

   cuda-install-samples-6.0.sh /home/ubuntu

Build the CUDA samples (takes around 15 minutes):

   cd ~/NVIDIA_CUDA-6.0_Samples
   make

Run some CUDA samples:

   1_Utilities/deviceQuery/deviceQuery
   1_Utilities/bandwidthTest/bandwidthTest
   cd 0_Simple/matrixMul
   ./matrixMulCUBLAS
   cd ../..
   cd 0_Simple/simpleTexture
   ./simpleTexture
   cd ../..
   cd 3_Imaging/convolutionSeparable
   ./convolutionSeparable
   cd ../..
   cd 3_Imaging/convolutionTexture
   ./convolutionTexture
   cd ../..
   Note: Many of the CUDA samples use OpenGL GLX and open graphical windows. If you are running these programs through an SSH remote terminal, you can remotely display the windows on your desktop by typing "export DISPLAY=:0" and then executing the program. (This will only work if you are using a Linux/Unix machine or you run an X server such as the free "Xming" for Windows). eg:
       export DISPLAY=:0
       cd ~/NVIDIA_CUDA-6.0_Samples/2_Graphics/simpleGL
       ./simpleGL
       cd ~/NVIDIA_CUDA-6.0_Samples/3_Imaging/bicubicTexture
       ./bicubicTexture
       cd ~/NVIDIA_CUDA-6.0_Samples/3_Imaging/bilateralFilter
       ./bilateralFilter
   Note: the Optical Flow sample (HSOpticalFlow) and 3D stereo sample (stereoDisparity) take rougly 1 minute each to execute since they compare results with CPU code.