![[PukiWiki]](image/pukiwiki.png "[PukiWiki]")
#contents |SoC|Parker| |CPU|Cortex A57 4 core + Denver 2.0 2 core| |GPU|Pascal 256 Core| |Memory|8GB 128bit LPDDR4| |Storage|32GB eMMC| -[[Embedded Systems Developer Kits & Modules | NVIDIA Jetson | NVIDIA>http://www.nvidia.com/object/embedded-systems-dev-skits-modules.html]]¬e{embedded-systems-dev-kits-modules:[[Embedded Systems Developer Kits & Modules | NVIDIA Jetson | NVIDIA>http://www.nvidia.com/object/embedded-systems-dev-kits-modules.html]], 2017-03-24閲覧}; -[[Jetson TX2 Module | NVIDIA Developer>https://developer.nvidia.com/embedded/buy/jetson-tx2]]¬e{embedded-jetson-tx2-nvidia-official:[[Jetson TX2 Module | NVIDIA Developer>https://developer.nvidia.com/embedded/buy/jetson-tx2]], 2017-03-24閲覧}; -[[NVIDIA、Pascal GPUを採用した新型「Jetson TX2」を、AIエッジ向けに投入 - Car Watch>http://car.watch.impress.co.jp/docs/news/1048408.html]]¬e{jetson-tx2-impress:笠原一輝, [[NVIDIA、Pascal GPUを採用した新型「Jetson TX2」を、AIエッジ向けに投入 - Car Watch>http://car.watch.impress.co.jp/docs/news/1048408.html]], 2017-03-08公開(日本時間), 2017-03-24閲覧}; -SoCはTegra X2ではなく、Parkerというコードネームで呼ぶらしい¬e{name-of-tegra-x2-is-technically-parker:後藤弘茂, [[【後藤弘茂のWeekly海外ニュース】NVIDIAのTegraを採用する任天堂の新ゲーム機「Nintendo Switch」 - PC Watch>http://pc.watch.impress.co.jp/docs/column/kaigai/1026659.html]], 2016-10-26, 2017-03-24閲覧}; -[[NVIDIA，Pascal世代の新SoC「Tegra X2」を採用する組み込み向け開発キット「Jetson TX2」発表 - 4Gamer.net>http://www.4gamer.net/games/049/G004964/20170307048/]]¬e{release-of-jetson-tx2-4gamers:塩田紳二, [[NVIDIA，Pascal世代の新SoC「Tegra X2」を採用する組み込み向け開発キット「Jetson TX2」発表 - 4Gamer.net>http://www.4gamer.net/games/049/G004964/20170307048/]], 2017-03-08公開, 2017-03-24閲覧}; -[[Jetson TX2 – わっぜか株式会社>http://www.wazeka-inc.com/archives/category/iot/jetson-tx2]]¬e{jetson-tx2-arrived-wazeka-inc:[[Jetson TX2 – わっぜか株式会社>http://www.wazeka-inc.com/archives/category/iot/jetson-tx2]], 2017-03-31公開, 2017-04-03閲覧}; -[[菱洋エレクトロ株式会社|_SEO_DESCRIPTION>http://www.ryoyo-web.jp/semi/detail_solution/1491954005-627998/]]¬e{ryo-yo-jetson-tx2:[[菱洋エレクトロ株式会社|_SEO_DESCRIPTION>http://www.ryoyo-web.jp/semi/detail_solution/1491954005-627998/]], 2017-04-17閲覧}; *スペック [#d0761b5c] -CPU:Denver2 Dual cores + Cortex-A57 Quad cores 2.0GHz -cpuinfo nvidia@tegra-ubuntu:~$ cat /proc/cpuinfo processor : 0 model name : ARMv8 Processor rev 3 (v8l) BogoMIPS : 62.50 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 CPU implementer : 0x41 CPU architecture: 8 CPU variant : 0x1 CPU part : 0xd07 CPU revision : 3 processor : 1 model name : ARMv8 Processor rev 0 (v8l) BogoMIPS : 62.50 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 CPU implementer : 0x4e CPU architecture: 8 CPU variant : 0x0 CPU part : 0x003 CPU revision : 0 MTS version : 37620520 processor : 2 model name : ARMv8 Processor rev 0 (v8l) BogoMIPS : 62.50 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 CPU implementer : 0x4e CPU architecture: 8 CPU variant : 0x0 CPU part : 0x003 CPU revision : 0 MTS version : 37620520 processor : 3 model name : ARMv8 Processor rev 3 (v8l) BogoMIPS : 62.50 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 CPU implementer : 0x41 CPU architecture: 8 CPU variant : 0x1 CPU part : 0xd07 CPU revision : 3 processor : 4 model name : ARMv8 Processor rev 3 (v8l) BogoMIPS : 62.50 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 CPU implementer : 0x41 CPU architecture: 8 CPU variant : 0x1 CPU part : 0xd07 CPU revision : 3 processor : 5 model name : ARMv8 Processor rev 3 (v8l) BogoMIPS : 62.50 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 CPU implementer : 0x41 CPU architecture: 8 CPU variant : 0x1 CPU part : 0xd07 CPU revision : 3 -lscpu $ lscpu Architecture: aarch64 Byte Order: Little Endian CPU(s): 6 On-line CPU(s) list: 0-5 Thread(s) per core: 1 Core(s) per socket: 3 Socket(s): 2 Model name: ARMv8 Processor rev 3 (v8l) CPU max MHz: 2035.2000 CPU min MHz: 345.6000 Hypervisor vendor: (null) Virtualization type: full L1d cache: 32K L1i cache: 48K L2 cache: 2048K -cpufreq $ cat /sys/bus/cpu/devices/cpu?/cpufreq/cpuinfo_max_freq 2035200 2035200 2035200 2035200 2035200 2035200 -kernel (Jetpack 3.0 インストール後) nvidia@tegra-ubuntu:~$ uname -a Linux tegra-ubuntu 4.4.15-tegra #1 SMP PREEMPT Wed Mar 1 21:09:29 PST 2017 aarch64 aarch64 aarch64 GNU/Linux -OS nvidia@tegra-ubuntu:~$ lsb_release -a No LSB modules are available. Distributor ID: Ubuntu Description: Ubuntu 16.04 LTS Release: 16.04 Codename: xenial -auxv nvidia@tegra-ubuntu:~$ xxd -e -g8 /proc/self/auxv 00000000: 0000000000000021 0000007fa8d8c000 !............... 00000010: 0000000000000010 00000000000000ff ................ 00000020: 0000000000000006 0000000000001000 ................ 00000030: 0000000000000011 0000000000000064 ........d....... 00000040: 0000000000000003 000000558af14040 ........@@..U... 00000050: 0000000000000004 0000000000000038 ........8....... 00000060: 0000000000000005 0000000000000008 ................ 00000070: 0000000000000007 0000007fa8d61000 ................ 00000080: 0000000000000008 0000000000000000 ................ 00000090: 0000000000000009 000000558af163d8 .........c..U... 000000a0: 000000000000000b 00000000000003e9 ................ 000000b0: 000000000000000c 00000000000003e9 ................ 000000c0: 000000000000000d 00000000000003e9 ................ 000000d0: 000000000000000e 00000000000003e9 ................ 000000e0: 0000000000000017 0000000000000000 ................ 000000f0: 0000000000000019 0000007fc01507c8 ................ 00000100: 000000000000001f 0000007fc0150feb ................ 00000110: 000000000000000f 0000007fc01507d8 ................ 00000120: 0000000000000000 0000000000000000 ................ -gcc は5.4.0 (Jetpack 3.0 インストール前は5.3.1) nvidia@tegra-ubuntu:~$ gcc --version gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609 Copyright (C) 2015 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. -nvcc $ nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2016 NVIDIA Corporation Built on Mon_Jan_23_12:28:25_CST_2017 Cuda compilation tools, release 8.0, V8.0.62 *Jetpack 3.0 [#n6997d6a] -[[JetPack for L4T | NVIDIA Developer>https://developer.nvidia.com/embedded/jetpack]]¬e{jetpack-download-official:[[JetPack for L4T | NVIDIA Developer>https://developer.nvidia.com/embedded/jetpack]], Jetpack 3.0, 2017-04-24閲覧}; からダウンロード -2017年4月24日時点での最新版はJetpack 3.0, JetsonTX2はL4T 27.1が最新版 *CPUを全部オンラインにする [#mcdf2232] -[[参考サイト>https://devtalk.nvidia.com/default/topic/1000345/two-cores-disabled-/?offset=3]]¬e{two-cores-disabled-nvidia-developer:[[Two cores disabled. - NVIDIA Developer Forums>https://devtalk.nvidia.com/default/topic/1000345/two-cores-disabled-/?offset=3]], 2017-04-24閲覧};にかかれてあるが、インストールしただけだと、Cortex A57 の4core しか見えていない -以下のコマンドを叩いて、1番と2番をオンラインにしないと、６個のコア全部を使うことはできない sudo su echo 1 > /sys/devices/system/cpu/cpu1/online echo 1 > /sys/devices/system/cpu/cpu2/online -NVIDIA提供のnvpmodelコマンドでも設定できる sudo nvpmodel -m 2 -3がMAXP_ARM、2がMAXP_CORE_ALL、1がMAXQ、0がMAXN -suのcrontabに書いてしまったほうが便利 $ sudo crontab -l | tail -1 @reboot nvpmodel -m 2 $ sudo crontab -e *ファンを回す [#x71bf118] -とりあえず全力で回しておく $ sudo echo 255 > /sys/kernel/debug/tegra_fan/target_pwm -こちらもcrontabに書いておくと便利 $ sudo crontab -l | tail -1 @reboot echo 255 > /sys/kernel/debug/tegra_fan/target_pwm TBW -[[Jetson TK1]] -[[Jetson TX1]] -[[Arm]]
