Home PC Games Linux Windows Database Network Programming Server Mobile  
           
  Home \ Linux \ Installation configuration CUDA under Ubuntu 14.04     - Redis-2.8.17 installation and configuration process some errors (Linux)

- Configuring a Linux operating system security management services Explain (Linux)

- 10 tips daily Docker (Server)

- Debian 8.1 (amd64) deployed Memcached (Server)

- A command to install Sublime Text 3 on Manjaro / Archlinux (Linux)

- OpenGL Superb Learning Notes - Depth Texture and Shadows (Programming)

- Mounting Windows shared directory system under the Linux (Linux)

- Multi-core CPU, multi-threading and parallel computation (Linux)

- Linux (Ubuntu) How iptables port mapping (Server)

- 20+ Best Practices article MySQL Performance Optimization (Database)

- To use Linux to create a secure managed gateway (Linux)

- Valgrind * not * leak check tool (Linux)

- The Java Properties class action (Programming)

- Use ARChon runtime environment to run Android apps on Ubuntu (Linux)

- Ubuntu install video conversion tool Selene (Linux)

- count (*) function in MySQL optimization of InnoDB storage engine (Database)

- Linux System Getting Started Learning: The Linux command line burn ISO or NRG image to DVD (Linux)

- Kafka + Log4j log implement centralized management (Server)

- JBPM6 Tutorial - Fast Fun JBPM table (Linux)

- Usage sed some of the parameters (Linux)

 
         
  Installation configuration CUDA under Ubuntu 14.04
     
  Add Date : 2017-08-31      
         
         
         
  First, I installed the system is Ubuntu 14.04.1.

1. Pre-inspection

Shown in the inspection system 1 according to the reference link.

Excuting an order:

: ~ $ Lspci | grep -i nvidia
03: 00.0 3D controller: NVIDIA Corporation GK110GL [Tesla K20c] (rev a1)
04: 00.0 VGA compatible controller: NVIDIA Corporation GK106GL [Quadro K4000] (rev a1)
04: 00.1 Audio device: NVIDIA Corporation GK106 HDMI Audio Controller (rev a1)

Found two K20 and K4000 GPU, there should be an Audio sound card.

Then, run the system version check:

~ $ Uname -m && cat / etc / * release
x86_64
DISTRIB_ID = Ubuntu
DISTRIB_RELEASE = 14.04
DISTRIB_CODENAME = trusty
DISTRIB_DESCRIPTION = "Ubuntu 14.04.1 LTS"
NAME = "Ubuntu"
VERSION = "14.04.1 LTS, Trusty Tahr"
ID = ubuntu
ID_LIKE = debian
PRETTY_NAME = "Ubuntu 14.04.1 LTS"
VERSION_ID = "14.04"
HOME_URL = "http://www.ubuntu.com/"
SUPPORT_URL = "http://help.ubuntu.com/"
BUG_REPORT_URL = "http://bugs.launchpad.net/ubuntu/"

Can be seen, the machine is ubuntu14.04 version.

Then, using a version of gcc gcc --version to check compliance with the requirements of the link 1:

~ $ Gcc --version
gcc (Ubuntu 4.8.2-19ubuntu1) 4.8.2
Copyright (C) 2013 Free Software Foundation, Inc.
This is free software;. See the source for copying conditions There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

Checked, go to nvidia's official website to download drivers for the download is ubuntu14.04 deb package.

2. Install
Deb package installation is relatively simple, but the installation process prompts instability, but also nothing wrong with the place.

First install the necessary libraries in reference links 2.

sudo apt-get install freeglut3-dev build-essential libx11-dev libxmu-dev libxi-dev libgl1-mesa-glx libglu1-mesa libglu1-mesa-dev

Or according to the official website of processes.

$ Sudo dpkg -i cuda-repo- < distro> _ < version> _ < architecture> .deb
$ Sudo apt-get update
$ Sudo apt-get install cuda


It may take a long time to download, but it does not matter, is waiting on that.


Lacks the problem even installed.


Installation tips:

*** Please reboot your computer and verify that the nvidia graphics driver is loaded. ***
*** If the driver fails to load, please use the NVIDIA graphics driver .run installer ***
*** To get into a stable state.

But I did not, suggesting that the use of .run installation is relatively stable, but now I use the no problem.

3. Configuration Environment

My system is 64-bit, so that when added to the configuration environment in .bashrc

$ Export PATH = / usr / local / cuda-6.5 / bin: $ PATH
$ Export LD_LIBRARY_PATH = / usr / local / cuda-6.5 / lib64: $ LD_LIBRARY_PATH

After configuring the environment, execute the command

~ $ Source .bashrc

To take effect immediately.

4. Install sample

After you configure the environment, you can execute the following command:

$ Cuda-install-samples-6.5.sh < dir>

Thus, it will be cuda of sample copy to the dir folder. This command is a copy operation.

Then enter the folder, execute make command to compile, compile a long time to wait.

5. Verify that the installation was successful

5.1. Driver Verifier

First, verify nvidia driver is installed successfully.

~ $ Cat / proc / driver / nvidia / version
NVRM version: NVIDIA UNIX x86_64 Kernel Module 340.29 Thu Jul 31 20:23:19 PDT 2014
GCC version: gcc version 4.8.2 (Ubuntu 4.8.2-19ubuntu1)


5.2. Toolkit verification

Verify cuda toolkit successful.

~ $ Nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2014 NVIDIA Corporation
Built on Thu_Jul_17_21: 41: 27_CDT_2014
Cuda compilation tools, release 6.5, V6.5.12


5.3. Equipment Identity

Use cuda sample has been compiled deviceQuery to verify. deviceQuery at < cuda_sample_install_path> / bin / x_86_64 / linux / release directory. My results were as follows, to detect the two GPU.

~ / Install / NVIDIA_CUDA-6.5_Samples / bin / x86_64 / linux / release $ ./deviceQuery
./deviceQuery Starting ...
 CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 2 CUDA Capable device (s)
 
Device 0: "Tesla K20c"
  CUDA Driver Version / Runtime Version 6.5 / 6.5
  CUDA Capability Major / Minor version number: 3.5
  Total amount of global memory: 4800 MBytes (5032706048 bytes)
  (13) Multiprocessors, (192) CUDA Cores / MP: 2496 CUDA Cores
  GPU Clock rate: 706 MHz (0.71 GHz)
  Memory Clock rate: 2600 Mhz
  Memory Bus Width: 320-bit
  L2 Cache Size: 1310720 bytes
  Maximum Texture Dimension Size (x, y, z) 1D = (65536), 2D = (65536, 65536), 3D = (4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers 1D = (16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers 2D = (16384, 16384), 2048 layers
  Total amount of constant memory: 65536 bytes
  Total amount of shared memory per block: 49152 bytes
  Total number of registers available per block: 65536
  Warp size: 32
  Maximum number of threads per multiprocessor: 2048
  Maximum number of threads per block: 1024
  Max dimension size of a thread block (x, y, z): (1024, 1024, 64)
  Max dimension size of a grid size (x, y, z): (2147483647, 65535, 65535)
  Maximum memory pitch: 2147483647 bytes
  Texture alignment: 512 bytes
  Concurrent copy and kernel execution: Yes with 2 copy engine (s)
  Run time limit on kernels: No
  Integrated GPU sharing Host Memory: No
  Support host page-locked memory mapping: Yes
  Alignment requirement for Surfaces: Yes
  Device has ECC support: Enabled
  Device supports Unified Addressing (UVA): Yes
  Device PCI Bus ID / PCI location ID: 3/0
  Compute Mode:
    < Default (multiple host threads can use :: cudaSetDevice () with device simultaneously)>
 
Device 1: "Quadro K4000"
  CUDA Driver Version / Runtime Version 6.5 / 6.5
  CUDA Capability Major / Minor version number: 3.0
  Total amount of global memory: 3071 MBytes (3220504576 bytes)
  (4) Multiprocessors, (192) CUDA Cores / MP: 768 CUDA Cores
  GPU Clock rate: 811 MHz (0.81 GHz)
  Memory Clock rate: 2808 Mhz
  Memory Bus Width: 192-bit
  L2 Cache Size: 393216 bytes
  Maximum Texture Dimension Size (x, y, z) 1D = (65536), 2D = (65536, 65536), 3D = (4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers 1D = (16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers 2D = (16384, 16384), 2048 layers
  Total amount of constant memory: 65536 bytes
  Total amount of shared memory per block: 49152 bytes
  Total number of registers available per block: 65536
  Warp size: 32
  Maximum number of threads per multiprocessor: 2048
  Maximum number of threads per block: 1024
  Max dimension size of a thread block (x, y, z): (1024, 1024, 64)
  Max dimension size of a grid size (x, y, z): (2147483647, 65535, 65535)
  Maximum memory pitch: 2147483647 bytes
  Texture alignment: 512 bytes
  Concurrent copy and kernel execution: Yes with 1 copy engine (s)
  Run time limit on kernels: Yes
  Integrated GPU sharing Host Memory: No
  Support host page-locked memory mapping: Yes
  Alignment requirement for Surfaces: Yes
  Device has ECC support: Disabled
  Device supports Unified Addressing (UVA): Yes
  Device PCI Bus ID / PCI location ID: 4/0
  Compute Mode:
    < Default (multiple host threads can use :: cudaSetDevice () with device simultaneously)>
> Peer access from Tesla K20c (GPU0) -> Quadro K4000 (GPU1): No
> Peer access from Quadro K4000 (GPU1) -> Tesla K20c (GPU0): No
 
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 6.5, CUDA Runtime Version = 6.5, NumDevs = 2, Device0 = Tesla K20c, Device1 = Quadro K4000
Result = PASS

Thus, cuda on the installation was successful.
     
         
         
         
  More:      
 
- grep command Series: grep command to search for multiple words (Linux)
- C ++ runtime environment built on CentOS 6.6 and Oracle database connection (Database)
- Samhain: Powerful intrusion detection system under Linux (Linux)
- Add local search to your Android app (Programming)
- Testing Oracle 11g RMAN replicate database (Database)
- MySQL optimization of the relevant Group By (Database)
- Shell Programming Regular Expressions (Programming)
- LogStash log analysis display system (Linux)
- Linux and hardware (Linux)
- Sleuth Kit: used to analyze a disk image and restore files open source forensics tools (Linux)
- Ubuntu uses conky add desktop control (Linux)
- Boot-Repair Tool - repair of frequent start-up problems (Linux)
- CentOS7 minimized installation can not find the 'ifconfig' command - Repair Tips (Linux)
- History and Statistics tuptime use tools to view Linux server system boot time (Server)
- Openfire achieve load balancing cluster by Nginx (Server)
- NIC configuration parameters under Linux (Linux)
- JavaScript function definition mode (Programming)
- MySQL Data Types (Database)
- MySQL service failed to start thinking of settlement under CentOS7 (Database)
- Use Docker / LXC quickly launch a desktop system (Linux)
     
           
     
  CopyRight 2002-2020 newfreesoft.com, All Rights Reserved.