Check out my first novel, midnight's simulacra!
CUDA: Difference between revisions
| Line 35: | Line 35: | ||
* Add the library path to LD_LIBRARY_PATH, assuming CUDA's been installed to a non-standard directory. | * Add the library path to LD_LIBRARY_PATH, assuming CUDA's been installed to a non-standard directory. | ||
* Set the <tt>CUDA_INSTALL_PATH</tt> and <tt>ROOTDIR</tt> (yeargh!) if outside the SDK. | * Set the <tt>CUDA_INSTALL_PATH</tt> and <tt>ROOTDIR</tt> (yeargh!) if outside the SDK. | ||
* I keep the following in <tt>bin/cudasetup</tt> of my home directory. Source its output, ala <tt>eval `cudasetup`</tt>: | * I keep the following in <tt>bin/cudasetup</tt> of my home directory. Source its output, ala <tt>eval `cudasetup`</tt>:<pre>#!/bin/sh | ||
< | |||
CUDA=$HOME/local/cuda | CUDA=$HOME/local/cuda | ||
| Line 50: | Line 49: | ||
else | else | ||
echo "export LD_LIBRARY_PATH=$CUDA/lib64" | echo "export LD_LIBRARY_PATH=$CUDA/lib64" | ||
fi</ | fi</pre> | ||
===Handrolled builds=== | ===Handrolled builds=== | ||
Revision as of 04:10, 26 January 2010
Installation on Debian
There exist libcuda-dev packages in the non-free archive area, but they seem incomplete or obsolete (or both). I instead used the NVIDIA upstream files, installing CUDA onto a 64-bit Debian Unstable system 2010-01-25 (hand-rolled 2.6.32.6 kernel, built with gcc-4.4). This machine did not have CUDA-compatible hardware (it uses Intel 965).
- Download the Ubuntu 9.04 files from NVIDIA's "CUDA Zone".
- Run the toolkit installer (sh cudatoolkit_2.3_linux_64_ubuntu9.04.run)
- For a user-mode install, supply $HOME/local or somesuch
* Please make sure your PATH includes /home/dank/local/cuda/bin * Please make sure your LD_LIBRARY_PATH * for 32-bit Linux distributions includes /home/dank/local/cuda/lib * for 64-bit Linux distributions includes /home/dank/local/cuda/lib64 * OR * for 32-bit Linux distributions add /home/dank/local/cuda/lib * for 64-bit Linux distributions add /home/dank/local/cuda/lib64 * to /etc/ld.so.conf and run ldconfig as root * Please read the release notes in /home/dank/local/cuda/doc/ * To uninstall CUDA, delete /home/dank/local/cuda * Installation Complete
- Run the SDK installer (sh cudasdk_2.3_linux.run)
- I just installed it to the same directory as the toolkit, which seems to work fine.
======================================== Configuring SDK Makefile (/home/dank/local/cuda/shared/common.mk)... ======================================== * Please make sure your PATH includes /home/dank/local/cuda/bin * Please make sure your LD_LIBRARY_PATH includes /home/dank/local/cuda/lib * To uninstall the NVIDIA GPU Computing SDK, please delete /home/dank/local/cuda * Installation Complete
Building
SDK's common.mk
This assumes use of the SDK's common.mk, as recommended by the documentation.
- Add the library path to LD_LIBRARY_PATH, assuming CUDA's been installed to a non-standard directory.
- Set the CUDA_INSTALL_PATH and ROOTDIR (yeargh!) if outside the SDK.
- I keep the following in bin/cudasetup of my home directory. Source its output, ala eval `cudasetup`:
#!/bin/sh
CUDA=$HOME/local/cuda [ -d "$CUDA" ] || { echo "$CUDA is not a directory, exiting" >&2 ; exit 1 ; } echo "# run \"eval \`$0\`\" to source these exports" echo "export CUDA_INSTALL_PATH=$CUDA" echo "export ROOTDIR=$CUDA/C/common/" # check for its current presence? FIXME if [ -n "$LD_LIBRARY_PATH" ] ; then echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CUDA/lib64" else echo "export LD_LIBRARY_PATH=$CUDA/lib64" fi
