Review Review videos : NVIDIA Jetson Nano

[NicoD]

Hi all. I've finished my review video about the NVIDIA Jetson Nano.
I kept it simple, more videos to come on gameplay and neural network self learning. 
Here's the review video.

I like it a lot. Does Blender great, and works well as light desktop. Loving the graphics drivers and hoping soon the other SBC's can have simular good drivers. 
It is close to being my favorite. If only the cpu had more power...
Here my gathered data.
 

Spoiler

Check power mode        : sudo nvpmodel -q
Set 5W mode             : sudo nvpmodel -m1
Set 10W mode            : sudo nvpmodel -m0
config file             : sudo nano /etc/nvpmodel.conf

5W Mode clocks to 921Mhz and disables 2 cores 

Show clocks mode        : sudo jetson_clocks --show
Set everything to max   : sudo jetson_clocks          (turns back to normal after reboot)

Youtube Playback
----------------
All browsers up to 1080p. Some 1440p.

Video Playback
--------------
No 4K GUI player/Even not KODI in 4k - 1440p ok
4K in terminal : nvgstplayer -i <video-filename> 

Blender NicoD GPU render
------------------------
23m42s  1440p
17m14s  1080p    
17m00s   720p
CPU
---
17m22s   10W
35m24s @1.43Ghz   5W   1080p gpu 27m53s
19m for both CPU and GPU render

Blender NicoD Armbian Bionic CPU 
25m45s



SBC-Bench default 10W    : http://ix.io/22sS
SBC-Bench default 5W     : http://ix.io/22uy
SBC-Bench armbian Bionic : http://ix.io/22uc

USB3 Camera
-----------
git clone https://github.com/ksv1986/luvcview
cd luvcview
sudo apt-get install libsdl2-dev
sudo make

Check options           : ./luvcview -h
Preview 1920x1080@30fps : ./luvcview -d /dev/video0 -i 30 -s 1920x1080
                          ./luvcview -d /dev/video0 -i 30 -s 1920x1080 -o testVideo.mp4

Install PPSSPP
--------------
sudo add-apt-repository ppa:ppsspp/stable
sudo apt-get update
sudo apt install ppsspp
su   (if no superuser password has created yet, first make one with sudo passwd)
ppsspp

Storage Speeds
--------------
SD-card reader read   : 88 MB/s       0.42 ms
               write  : 70 MB/s
USB3-SSD       read   : 410 MB/s      0.26 ms
               write  : 380 MB/s               
ZRAM           read   : 1.7GB/s       0.01 ms      

Temperatures
------------
max No fan   : 78C
max 3V fan   : 43.5C

Problems
--------
USB seems unreliable. Not all USB3 devices are mounted as USB3 but as USB2. Problems with USB2 devices not being recognized at all.

 

 

[NicoD]

Here my 2nd video where I show more of the desktop experience with the Nano in the Ubuntu of NVIDIA.
I show Youtube playback and video playback and gives some tips for better playback. I do some photo editing with gimp, some 3d modeling and rendering with Blender. And video editing with KDEnlive.

 

[sfx2000]

6 hours ago, NicoD said:

I like it a lot. Does Blender great, and works well as light desktop. Loving the graphics drivers and hoping soon the other SBC's can have simular good drivers. 
It is close to being my favorite. If only the cpu had more power...

 

Nice work - which audience are you attempting to approach here?

 

Keep in mind that Jetson Nano is a gateway into the whole nVidia ecosystem/platform first - as a consumer/enthusiast SBC application, it's a secondary consideration.

 

With Nano - it gets complicated, and L4T has always been that way - seems like it's getting better,  but apt-update/upgrade can sometimes not be a good thing, based on prior experience with this platform.

[balbes150]

Good news. You can now use the main core to run on Jetson Nano. I have already added the necessary data to the build system and you can build an image for Jetson Nano using the official sources of the main core.

 

 

U-Boot 2020.04-g6b630d64fd (Feb 19 2021 - 08:37:46 -0800)

SoC: tegra210
Model: NVIDIA Jetson Nano Developer Kit
Board: NVIDIA P3450-0000
DRAM:  4 GiB
MMC:   sdhci@700b0000: 1, sdhci@700b0600: 0
Loading Environment from SPI Flash... SF: Detected mx25u3235f with page size 256 Bytes, erase size 4 KiB, total 4 MiB
*** Warning - bad CRC, using default environment

In:    serial
Out:   serial
Err:   serial
Net:   No ethernet found.
Hit any key to stop autoboot:  0 
switch to partitions #0, OK
mmc1 is current device
Scanning mmc 1:1...
Found /boot/extlinux/extlinux.conf
Retrieving file: /boot/extlinux/extlinux.conf
338 bytes read in 22 ms (14.6 KiB/s)
1:      Armbian
Retrieving file: /boot/uInitrd
11330177 bytes read in 512 ms (21.1 MiB/s)
Retrieving file: /boot/Image
31306240 bytes read in 1364 ms (21.9 MiB/s)
append: root=UUID=de820d8a-ca8e-4b1a-8e96-ce586b2422f3 console=ttyS0,115200 console=tty0 rootflags=data=writeback rw no_console_suspend consoleblank=0 fsck.fix=yes fsck.repair=yes net.ifnames=0 bootsplash.bootfile=bootsplash.armbian
Retrieving file: /boot/dtb/nvidia/tegra210-p3450-0000.dtb
42868 bytes read in 33 ms (1.2 MiB/s)
## Loading init Ramdisk from Legacy Image at 83200000 ...
   Image Name:   uInitrd
   Image Type:   AArch64 Linux RAMDisk Image (gzip compressed)
   Data Size:    11330113 Bytes = 10.8 MiB
   Load Address: 00000000
   Entry Point:  00000000
   Verifying Checksum ... OK
## Flattened Device Tree blob at 83000000
   Booting using the fdt blob at 0x83000000
   Using Device Tree in place at 0000000083000000, end 000000008300d773
copying carveout for /host1x@50000000/dc@54200000...
copying carveout for /host1x@50000000/dc@54240000...
Can't set DT prop /bpmp/carveout-start: FDT_ERR_BADOFFSET

Starting kernel ...

[    0.000000] Booting Linux on physical CPU 0x0000000000 [0x411fd071]
[    0.000000] Linux version 5.10.22-jetson-nano (root@vbox) (aarch64-linux-gnu-gcc (GNU Toolchain for the A-profile Architecture 8.3-2019.03 (arm-rel-8.36)) 8.3.0, GNU ld (GNU Toolchain for the A-profile Architecture 8.3-2019.03 (arm-re1
[    0.000000] Machine model: NVIDIA Jetson Nano Developer Kit
[    0.000000] efi: UEFI not found.


[   68.257514] systemd[1]: Starting Create System Users...
[   68.270413] systemd[1]: Mounted Kernel Configuration File System.

jetson-nano login: root (automatic login)

     _      _                     _   _                   
    | | ___| |_ ___  ___  _ __   | \ | | __ _ _ __   ___  
 _  | |/ _ \ __/ __|/ _ \| '_ \  |  \| |/ _` | '_ \ / _ \ 
| |_| |  __/ |_\__ \ (_) | | | | | |\  | (_| | | | | (_) |
 \___/ \___|\__|___/\___/|_| |_| |_| \_|\__,_|_| |_|\___/ 
                                                          
Welcome to Armbian 21.05.0-trunk Focal with Linux 5.10.22-jetson-nano

No end-user support: built from trunk

System load:   74%              Up time:       1 min
Memory usage:  6% of 3.80G      IP:            
Usage of /:    28% of 15G    

[ General system configuration (beta): armbian-config ]

Last login: Wed Mar 10 08:41:35 UTC 2021 on tty1
New to Armbian? Documentation: https://docs.armbian.com Support: https://forum.armbian.com

New root password: ******
Repeat password: ******

Choose default system command shell:

1) bash
2) zsh

Shell: BASH

Creating a new user account. Press <Ctrl-C> to abort

Desktop environment will not be enabled if you abort the new user creation

Please provide a username (eg. your forename): user
Create password: ******
Repeat password: ******

Please provide your real name: User

Dear User, your account user has been created and is sudo enabled.
Please use this account for your daily work from now on.


Now starting desktop environment...

 

[hexdump]

congratulations! ... the u-boot is still the original nvidia one from spl then? or a recompiled nvidia u-boot? or mainline u-boot (i guess not as v2020.04 looks too old for that)? are you able to use mbr partitions or do you have to use the usual jetson gpt partition setup?

[balbes150]

9 часов назад, hexdump сказал:

congratulations! ... the u-boot is still the original nvidia one from spl then? or a recompiled nvidia u-boot? or mainline u-boot (i guess not as v2020.04 looks too old for that)? are you able to use mbr partitions or do you have to use the usual jetson gpt partition setup?

I plan to open a new topic in the Board Bring Up section dedicated to Armbian support on Jetson Nano. Now there is a lot of interesting information.