CHI@Edge Deployment and Hardware Information

While the table linked below may reference multiple "locations", all devices are part of the same "virtual site". They communicate with each other by tunneling over the public internet, and appear to be on the same network, the same as all other Chameleon sites.

Visit the edge hardware discovery table to see the latest up-to-date hardware information about CHI@Edge devices

Deployment Profiles

Sandbox Deployment

During this initial preview period, we've deployed two "sandbox" sites near our offices and residences at UChicago and New Jersey. While hosted within office or residential networks, all devices are connected to the rest of the site by tunneling over the public internet, not via any special connections. Each sandbox site has a cluster of Raspberry Pi 4s and Jetson Nanos.

Raspberry Pi 4

  • Official Documentation
  • CPU cores: 4
  • Ram: 8gb
  • Disk: 32gb microsd card
  • Linux Kernel 5.10.17
  • CPU Architecture: arm64

Nvidia Jetson Nano

  • Official Documentation
  •  GPU: 128-core Maxwell 
  • CPU: Quad-core ARM A57 @ 1.43 GHz
  • Memory: 4 GB 64-bit LPDDR4 25.6 GB/s
  • Storage: 32gb microsd card
  • Linux Kernel 4.9-tegra

Nvidia Jetson Xavier NX

  • Official Documentation
  • GPU: NVIDIA Volta architecture with 384 NVIDIA CUDA® cores and 48 Tensor cores
  • CPU: 6-core NVIDIA Carmel ARM®v8.2 64-bit CPU 6 MB L2 + 4 MB L3
  • Memory: 8 GB 128-bit LPDDR4x @ 51.2GB/s
  • Storage: 32GB MicroSD
  • Kernel: 4.9-tegra

As it's a "sandbox", this deployment has no attached sensors (yet!).

Coming soon to a testbed near you

Candidate Locations

  • UChicago John Crerar Library (Live!)
  • Other spaces at UChicago
  • Lab Spaces at Rutgers University, NJ
  • Office / Residential spaces in NJ (Live!)
  • More to come!

 

Candidate Sensors and Peripherals

  • Raspberry Pi Cameras
  • Pixhawk flight controller
  • RTL-SDR software defined radio
  • Any Pi HAT compatible sensors
  • Indoor / Outdoor autonomous model cars

Candidate Devices

We're currently evaluating some additional devices for inclusion in the platform. We welcome suggestions and requests.

Jetson AGX Orin Developer Kit (Deployed and testing, will be available soon!)

  • Official Documentation
  • GPU: 2048-core NVIDIA Ampere architecture GPU with 64 Tensor Cores
  • CPU: 12-core Arm® Cortex®-A78AE v8.2 64-bit CPU 3MB L2 + 6MB L3
  • Memory: 64GB 256-bit LPDDR5 204.8GB/s
  • Storage: 64GB eMMC 5.1
  • Kernel: L4T-32.5.1

Coral Dev Board

  • Official Documentation
  • Google Edge TPU coprocessor: 4 TOPS (int8); 2 TOPS per watt
  • CPU: NXP i.MX 8M SoC (quad Cortex-A53, Cortex-M4F)
  • Memory: 4 GB LPDDR4
  • Storage: 8 GB eMMC, microSD expansion
  • Kernel: 4.14.98-linux-imx

Up Squared

  • Official Documentation
  • CPU: Intel Quad Core Atom, x86_x64
  • Memory: 8GB
  • Storage: 32GB eMMC
  • Kernel: x86_64, Linux mainline