jetson

Connection to NVIDIA Jetson hardware

Description

This object represents a connection from the MATLAB^® software to the NVIDIA^® Jetson hardware. To create this object, use the jetson function. To interact with the Jetson hardware, use this object with the functions listed in Object Functions.

Creation

jetson

Properties

expand all

`BoardName` — Board name
character vector

This property is read-only.

The name of the target Jetson board, returned as a character vector.

Example: 'NVIDIA Jetson TX2'

`CUDAVersion` — CUDA^® toolkit version
character vector

This property is read-only.

Version number of the CUDA toolkit installed on the Jetson board, returned as a character vector.

Example: '9.0'

`cuDNNVersion` — cuDNN library version
character vector

This property is read-only.

Version number of the CUDA Deep Neural Network library (cuDNN) installed on the Jetson board, returned as a character vector.

Example: '7.0'

`DeviceAddress` — IP address or host name
character vector

This property is read-only.

The IP address or host name of the Ethernet port on the Jetson board, returned as a character vector.

Example: '169.254.0.2''gpucoder-tx2-1'

`GPUInfo` — GPU information
struct

This property is read-only.

Additional information on the GPU of the Jetson board, returned as a 1-by-1 structure. To access this structure use objectName.GPUInfo. The structure contains the following fields:

Name	Description
`Name`	Name of the CUDA device.
`Index`	Index of the selected GPU device.
`ComputeCapability`	Computational capability of the CUDA device.
`CUDADriverVersion`	The CUDA device driver version on the board currently in use.
`CUDAToolkitVersion`	Version of the CUDA toolkit on the board.
`MaxThreadsPerBlock`	Maximum supported number of threads per block during CUDA kernel execution.
`MaxSharedMemPerBlock`	Maximum amount of shared memory that a thread block can use during CUDA kernel execution.
`MaxThreadBlockSize`	Maximum size in each dimension for thread block.
`MaxGridSize`	Maximum size of grid of thread blocks.
`AvailableMemory`	Total amount of memory (in bytes) available for data.
`TotalConstMem`	Total amount of constant memory (in bytes) available for data.
`MultiprocessorCount`	The number of vector processors present on the device.
`TotalCUDACores`	Total number of CUDA cores available on the target board.
`MaxThreadsPerSM`	Maximum number of threads per symmetric multiprocessor.

For example, a Jetson TX2 board has the following values:

hwJetson.GPUInfo

ans = 

  struct with fields:

                    Name: 'NVIDIA Tegra X2'
                   Index: 0
       ComputeCapability: 6.2000
       CUDADriverVersion: 9
      CUDAToolkitVersion: 9
      MaxThreadsPerBlock: 1024
    MaxSharedMemPerBlock: 49152
      MaxThreadBlockSize: [1024 1024 64]
             MaxGridSize: [2.1475e+09 65535 65535]
         AvailableMemory: 8.2358e+09
           TotalConstMem: 65536
     MultiprocessorCount: 2
          TotalCUDACores: 256
         MaxThreadsPerSM: 2048

`GStreamerVersion` — GStreamer library version
character vector

This property is read-only.

Version number of the GStreamer library installed on the Jetson board, returned as a character vector.

Example: '1.14.5'

`Port` — SSH port number
positive integer

This property is read-only.

The SSH port number on the Jetson board, returned as an integer.

Example: 22

`SDLVersion` — SDL library version
character vector

This property is read-only.

Version number of the SDL library installed on the Jetson board, returned as a character vector.

Example: '1.2'

`TensorRTVersion` — TensorRT library version
character vector

This property is read-only.

Version number of the NVIDIA TensorRT library installed on the Jetson board, returned as a character vector.

Example: '3.0'

`V4L2Version` — Video for Linux library version
character vector

This property is read-only.

Version number of the V4L2 library installed on the Jetson board, returned as a character vector.

Example: '1.14.2-1'

`webcamlist` — Available USB web cameras
cell array

This property is read-only.

A list of the USB web cameras that are available, returned as a cell array of strings.

Example: {'Microsoft(R) LifeCam Cinema (TM)'}

Object Functions

`getFile`	Transfer file from NVIDIA hardware to host computer
`putFile`	Transfer file from host computer to target hardware
`deleteFile`	Delete file on target hardware
`openShell`	Open terminal on host computer to use a Linux shell on NVIDIA hardware
`system`	Run commands in a Linux shell on the NVIDIA hardware
`getL4TVersion`	Get the L4T version of the NVIDIA Jetson hardware
`getPdkorSdkVersion`	Get the version number of the DriveWorks SDK installed on the DRIVE hardware
`setupCodegenContext`	Select the target hardware to build code for from multiple live connection objects
`getCameraList`	Get a list of available cameras on the NVIDIA hardware
`webcam`	Create `webcam` object to acquire images from an USB webcam attached to the NVIDIA hardware
`updatePeripheralInfo`	Scan for and update the list of peripherals connected to the target hardware
`getLinuxVersion`	Get information about the Linux environment on the target
`imageDisplay`	Create an `imageDisplay` object for displaying images on NVIDIA targets
`getPILPort`	Get the TCP/IP port number used by the PIL execution
`getPILTimeout`	Get the timeout value that PIL uses for reading data
`setPILPort`	Set the TCP/IP port number used by the PIL execution
`setPILTimeout`	Set the timeout value that PIL uses for reading data
`killApplication`	Kill an application on the NVIDIA target by name
`killProcess`	Kill a process on the NVIDIA target by ID
`runApplication`	Launch an application on the NVIDIA target by name
`runExecutable`	Launch an executable on the NVIDIA target by name
`getDisplayEnvironment`	Get the display environment value used for redirecting the display on the target
`setDisplayEnvironment`	Set the display environment value used for redirecting the display on the target

Examples

collapse all

Connect to NVIDIA Hardware

This example shows you how to create a connection from the MATLAB software to the NVIDIA Jetson hardware. The Jetson hardware is connected to the same TCP/IP network as the host computer. This example uses the device address, user name, and password settings from the most recent successful connection to the Jetson hardware.

Create a connection, hwJetson, from the MATLAB software to NVIDIA Jetson hardware.

hwJetson = jetson

Checking for CUDA availability on the Target...
Checking for 'nvcc' in the target system path...
Checking for cuDNN library availability on the Target...
Checking for TensorRT library availability on the Target...
Checking for prerequisite libraries is complete.
Gathering hardware details...
Checking for third-party library availability on the Target...
Gathering hardware details is complete.
 Board name         : NVIDIA Jetson TX2
 CUDA Version       : 10.0
 cuDNN Version      : 7.5
 TensorRT Version   : 5.1
 GStreamer Version  : 1.14.5
 V4L2 Version       : 1.14.2-1
 SDL Version        : 1.2
 Available Webcams  : MicrosoftÂ® LifeCam Cinema(TM)
 Available GPUs     : NVIDIA Tegra X2

hwJetson = 

  jetson with properties:

       DeviceAddress: '192.168.1.15'
                Port: 22
           BoardName: 'NVIDIA Jetson TX2'
         CUDAVersion: '10.0'
        cuDNNVersion: '7.5'
     TensorRTVersion: '5.1'
          SDLVersion: '1.2'
         V4L2Version: '1.14.2-1'
    GStreamerVersion: '1.14.5'
             GPUInfo: [1×1 struct]
          WebcamList: {'MicrosoftÂ® LifeCam Cinema(TM)'}

The GPU Coder™ Support Package for NVIDIA GPUs establishes an SSH connection to the Jetson hardware using the settings stored in memory. It checks for the CUDA toolkit, cuDNN, and TensorRT libraries on the target hardware and displays this information on the MATLAB Command Window. To set up the environment variables on the board for the compiler and the libraries, see Install and Setup Prerequisites for NVIDIA Boards.

To get the L4T software version on the Jetson board, use the getL4TVersion method of the jetson connection object.

getL4TVersion(hwJetson);

Jetson L4T version is: L4T R28.2.0.

To start a PuTTY SSH terminal session on the Jetson board, use the openShell method of the jetson connection object.

openShell(hwJetson);

Using username "ubuntu".
Welcome to Ubuntu 16.04.5 LTS (GNU/Linux 4.4.38-tegra aarch64)

 * Documentation:  https://help.ubuntu.com
 * Management:     https://landscape.canonical.com
 * Support:        https://ubuntu.com/advantage

30 packages can be updated.
0 updates are security updates.

Last login: Sat Aug 11 19:38:08 2018 from 172.28.216.242
ubuntu@tegra-ubuntu:~$ ls
Desktop    gpucoderTX2       Music     remoteBuildDir  Videos
Documents  jetson_clocks.sh  Pictures  tegrastats      weston.ini
Downloads  MATLAB            Public    Templates
ubuntu@tegra-ubuntu:~$

After logging into the Linux^® shell, you execute shell commands such as ls as shown.

To close the connection, use clear to remove hwJetson and any other connections that use hwJetson.

clear hwJetson;

jetson

Description

Creation

Properties

`BoardName` — Board name
character vector

`CUDAVersion` — CUDA^® toolkit version
character vector

`cuDNNVersion` — cuDNN library version
character vector

`DeviceAddress` — IP address or host name
character vector

`GPUInfo` — GPU information
struct

`GStreamerVersion` — GStreamer library version
character vector

`Port` — SSH port number
positive integer

`SDLVersion` — SDL library version
character vector

`TensorRTVersion` — TensorRT library version
character vector

`V4L2Version` — Video for Linux library version
character vector

`webcamlist` — Available USB web cameras
cell array

Object Functions

Examples

Connect to NVIDIA Hardware

See Also

Functions

Objects

Topics

Introduced in R2018b

GPU Coder Support Package for NVIDIA GPUs Documentation

Support

Generating CUDA Code from MATLAB: Accelerating Embedded Vision and Deep Learning Algorithms on GPUs

jetson

Description

Creation

Properties

BoardName — Board name character vector

CUDAVersion — CUDA® toolkit version character vector

cuDNNVersion — cuDNN library version character vector

DeviceAddress — IP address or host name character vector

GPUInfo — GPU information struct

GStreamerVersion — GStreamer library version character vector

Port — SSH port number positive integer

SDLVersion — SDL library version character vector

TensorRTVersion — TensorRT library version character vector

V4L2Version — Video for Linux library version character vector

webcamlist — Available USB web cameras cell array

Object Functions

Examples

Connect to NVIDIA Hardware

See Also

Functions

Objects

Topics

Introduced in R2018b

GPU Coder Support Package for NVIDIA GPUs Documentation

Support

Generating CUDA Code from MATLAB: Accelerating Embedded Vision and Deep Learning Algorithms on GPUs

`BoardName` — Board name
character vector

`CUDAVersion` — CUDA^® toolkit version
character vector

`cuDNNVersion` — cuDNN library version
character vector

`DeviceAddress` — IP address or host name
character vector

`GPUInfo` — GPU information
struct

`GStreamerVersion` — GStreamer library version
character vector

`Port` — SSH port number
positive integer

`SDLVersion` — SDL library version
character vector

`TensorRTVersion` — TensorRT library version
character vector

`V4L2Version` — Video for Linux library version
character vector

`webcamlist` — Available USB web cameras
cell array