安装先决条件产品s manbetx 845- MATLAB & Simulink - MathWorks Switzerland

安装先决条件产品s manbetx 845

To use GPU Coder™ for CUDA^®代码生成，您必须安装和设置以下产品。s manbetx 845有关设置说明，请参阅Setting Up the Prerequisite Products。

数学工作Products and Support Packages

MATLAB^®(required).
MATLAB CODER™(required).
并行计算工具箱™（必需）。
万博1manbetx^®（从Simulink模型生成代码所需）。万博1manbetx
计算机视觉工具箱™（推荐）。
Deep Learning Toolbox™ (required for deep learning).
Embedded Coder^®(recommended).
图像处理工具箱™（推荐）。
Simulink Coder（从Simulink模型生成代码所需）。万博1manbetx
深度学习库的GPU编码器界面support package (required for deep learning).
MATLAB Coder Support Package for NVIDIA^®杰森^®和Nvidia Drive^®Platforms（部署到嵌入式目标（例如Nvidia Jetson和Drive）所必需的）。

For instructions on installing MathWorks^®s manbetx 845产品，请参阅您的平台MATLAB安装文档。如果您已经安装了MATLAB并想检查安装了其他Mathworks产品，请输入s manbetx 845ver在MATLAB命令窗口中。要安装支持软件包，请在MATL万博1manbetxAB中使用附加探索器。

如果包含非MATLAB是安装在一个路径7-bit ASCII characters, such as Japanese characters, GPU Coder does not work because it cannot locate code generation library functions.

Third-Party Hardware

NVIDIA GPU启用了兼容图形驱动程序的CUDA。有关更多信息，请参阅CUDA GPU（NVIDIA）。

To see the CUDA compute capability requirements for code generation, consult the following table.

Target	计算能力
Cuda Mex	看GPU Support by Release。
Source code, static or dynamic library, and executables	3.2或更高。
8位整数精度的深度学习应用	6.1、7.0或更高。
Deep learning applications in half-precision (16-bit floating point)	5.3, 6.0, 6.2 or higher.

手臂^®马里graphics processor.
对于马里设备，GPU编码器仅支持深度学习网络的代码生成。万博1manbetx

第三方软件

Required

C/C++ Compiler:

Linux^®	Windows^®
GCC C/C++ compiler. For supported versions, seeSupported and Compatible Compilers。	Microsoft^®视觉工作室^®2013
	Microsoft Visual Studio2015
	Microsoft Visual Studio2017
	Microsoft Visual Studio2019

可选的

For CUDA MEX, the code generator uses the NVIDIA compiler and libraries installed with MATLAB. Standalone code (static library, dynamically linked library, or executable program) generation has additional software requirements.

软件名称	Information
CUDA工具包	GPU Coder has been tested with CUDA Toolkit v9.x-v11.2. To download the CUDA Toolkit, seeCUDA工具包存档（NVIDIA）。
NVIDIA NSIGHT™系统	Generate an execution profiling report for the generated CUDA code. The report provides metrics that help you analyze your application algorithms and identify opportunities to optimize performance. GPU Coder has been tested with Nsight 2021.1.1
nvidia库达deep neural network library (cuDNN) for NVIDIA GPUs	For the host GPU device, GPU Coder has been tested with cuDNN v8.1.1. To download cuDNN, seecudnn（nvidia）。
nvidiaTensorRT™ high performance inference optimizer and runtime library	For the host GPU device, GPU Coder has been tested with TensorRT v7.2.3. 要下载Tensorrt，请参阅张力（nvidia）。
马里GPU的手臂计算库	GPU Coder has been tested with v19.05. 有关更多信息，请参阅Compute Library (ARM)。
开源计算机视觉库（OPENCV）	深度学习的例子所需。对于针对主机开发计算机上NVIDIA GPU的示例，请使用OpenCV v3.1.0。对于针对ARM GPU的示例，请在ARM目标硬件上使用OpenCV v2.4.9。有关更多信息，请参阅OpenCV。