(原创) jetson tk1 初始化
1. 相关的网站:
1. Jetson TK1 support https://developer.nvidia.com/jetson-tk1-support
2.official Wiki for embedded Tegra & the Jetson TK1 board, maintained by both the community and NVIDIA: http://elinux.org/Jetson_TK1
3. blog NVIDIA Jetson TK1开发板上手:http://blog.csdn.net/Pyen/article/details/27563819
4.台湾网站的评测 http://www.coolpc.com.tw/phpBB2/viewtopic.php?f=70&t=147025
5. youtube 上的Jetson Tegra K1 Devkit - Setting up Desktop GUI https://www.youtube.com/watch?v=ghqM8pzJZxg
6. NVIDIA Nsight Eclipse Edition for Jetson TK1:http://devblogs.nvidia.com/parallelforall/nvidia-nsight-eclipse-edition-for-jetson-tk1/
2. 相关名词解释
Cross compiling: means the target executable is built on the host machine, not on the target. Therefore, the target executable must be compatible with (in particular with the libraries on) the target machine. This compatibility is achieved by having the correct version of nvcc as well as the correct library versions (CUDA version and target OS) to link against, that match your target.
3. 开发方法
对于jetson 有2种开发方法:
- 原生开发:在jetson tk1 上进行开发
- 交叉编译:在host计算机上进行编译
4. 初始化方法
0. 初始化
连上显示器上电后,出来的是arm-ubuntu14.04的字符界面,账号和密码均为ubuntu。如果你喜欢GUI,那么请进入/home/ubuntu/NVIDIA-INSTALLER(也就是~/NVIDIA_INSTALLER目录),运行./installer.sh,待安装完重启后即可获得图形界面。
要特别注意的是,Jetson-TK1是arm架构的ubuntu,和普通我们见到的ubuntu(x86架构)有本质的区别(编译器完全是不同的),因此x86 ubuntu的所有程序都不可直接拿到TK1上用!
注意:如果更新之后出现黑屏,那么ctrl+alt+f1 然后login,然后进入/home/ubuntu/NVIDIA-INSTALLER,最后运行./installer.sh ,就可以看到图形界面
1. 进入
Jetson TK1 support https://developer.nvidia.com/jetson-tk1-support 下载
CUDA 6.0 Toolkit for L4T Rel -19.2(注意:CUDA 6.0 Toolkit for Ubuntu12.04 x86 64-bit (with TK1 cross-development support 是为了在ubuntu 主机上进行Corss Compiling)
2.设置网络链接
使用电脑作为无限网卡,通过网线和jetson tk1 进行网络共享。
设置方法:在network connection --> wired --> edit --> IPv4 Settings --> method --> shared to other computers
3. 安装
cd Downloads (进入下载目录)
ls (显示当前文件夹中的文件)
sudo dpkg -i package.deb (安装程序)
sudo apt-get update (更新系统源)
sudo apt-get install cuda-samples-6-0 (安装samples)
sudo apt-get install cuda-toolkit-6-0 (安装toolkit)
sudo usermod -a -G video ubuntu (这里的ubuntu是用户名,如果不是这个用户名,那么输入其他的用户名) (Update your permissions for directFB access , DirectFB 全名是 Direct Frame Buffer。DirectFB是德国Convergence公司推动的开放源代码计划,是 GNU/Linux 操作系统上的库,提供硬件图形加速(hardware graphics acceleration)与 translucent windows 等功能。授权方式为GNU宽通用公共许可证。)
cd
echo "# Add CUDA bin & library paths:" >> ~/.bashrc (编辑bashrc文件)
echo "export PATH=/usr/local/cuda-6.0/bin:$PATH" >> ~/.bashrc
echo "export LD_LIBRARY_PATH=/usr/local/cuda-6.0/lib:$LD_LIBRARY_PATH" >> ~/.bashrc
source ~/.bashrc
cd /usr/local/cuda (进入cuda安装路径,进行查看)
ls (查看安装路径下的文件)
nvcc -V (查看版本)
cuda-install-samples-6.0.sh /home/ubuntu(将samples 拷贝到放特定的目录下面,这里输入的是 /home/ubuntu)
cd ~/NVIDIA_CUDA-6.0_Samples
ls (查看各种例子程序)
make (对各个例子进行编译)
./deviceQuery (进行设备性质的查看)
【推荐】还在用 ECharts 开发大屏?试试这款永久免费的开源 BI 工具!
【推荐】国内首个AI IDE,深度理解中文开发场景,立即下载体验Trae
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步