Install the CUDA Development Environment on Ubuntu11.10

Source: Internet
Author: User
Tags cuda toolkit nvcc
All the content in this article is tested on my ThinkPadW520Ubuntu11.10x64 bit, but it does not mean that this article is suitable for you. Cheungmine, author of this article, is not responsible for any consequences arising from the operations in this article. English Reference documents: Workshop

All the content in this article is tested on my ThinkPad W520 Ubuntu 11.10 x64 bit, but it does not mean that this article is suitable for you. Cheungmine, author of this article, is not responsible for any consequences arising from the operations in this article.

Http://developer.nvidia.com/nvidia-gpu-computing-documentation

Step 2: Make sure your machine supports CUDA

The following machines support CUDA

NVIDIA GeForce 8, 9,200,400, and 500 series GPUs

NVIDIA TeslaTM computing solutions

Category of the NVIDIA Quadro products

Run the command to bring up the dialog box:

$ Nvidia-settings

NOTE: If your machine does not display a dialog box similar to the preceding one after running the nvidia-settings command, it means that you have not correctly installed the nvidia driver. See my article Ubuntu 11.10 ultimate solution for nvidia graphics Driver Installation: http://www.linuxidc.com/Linux/2012-04/58914.htm

Step 2: Install CUDA Toolkit

Download to the address below: http://developer.nvidia.com/cuda-toolkit

1) cudatoolkit_4.1.28_linux_64_ubuntu11.04.run

And

2) gpucomputingsdk_4.1.28_linux.run

Go to the directory of cudatoolkit_4.1.28_linux_64_ubuntu11.04.run and run the following command to install Toolkit:

$ Sudo sh./cudatoolkit_4.1.28_linux_64_ubuntu11.04.run

By default. Prompt that the installation is complete, set the environment variables, and execute the following two commands:

$ Export PATH =/usr/local/cuda/bin: $ PATH

$ ExportLD_LIBRARY_PATH =/usr/local/cuda/lib: $ LD_LIBRARY_PATH

In particular, if it is a 64-bit system, you need to add one more sentence:

$ ExportLD_LIBRARY_PATH =/usr/local/cuda/lib64: $ LD_LIBRARY_PATH

Of course, we can write the above command ~ /. In bashrc, environment variables are automatically added when the system starts.

$ Gedit ~ /. Bashrc

Add the following three sentences ~ /. Save the last part of bashrc and log out again.

Export PATH =/usr/local/cuda/bin: $ PATH

Export LD_LIBRARY_PATH =/usr/local/cuda/lib: $ LD_LIBRARY_PATH

ExportLD_LIBRARY_PATH =/usr/local/cuda/lib64: $ LD_LIBRARY_PATH

Verify installation:

Run $ nvcc-V to obtain the CUDAToolkit version to verify whether the installation is successful.

Nvcc: NVIDIA (R) Cudacompiler driver

Copyright (c) 2005-2011 NVIDIA Corporation

Built on Thu_Jan_12_14: 41: 45_PST_2012

Cuda compilation tools, release 4.1, V0.2.1221

Step 2: Install the GPU Computing SDK

For future development convenience, the SDK should not be installed as a root user. Run

$ Sh./cuda_installation/gpucomputingsdk_4.0.17_linux.run

Follow the prompts to complete the installation. Installed in the current user's Home by default.

Related Article

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.