Soon available again! See here for more information.
The Google Coral System-on-Module (SoM) is a fully integrated system module for hardware-accelerated machine learning applications, consisting of CPU, GPU, Edge TPU, Wi-Fi, Bluetooth, and memory in a mere 40mm x 48mm size.
This module can be easily designed into your own hardware (and application). For example, it is the core of the Coral Dev Board (in the 4GB variant).
Your advantages:
- Designing a suitable carrier board for your machine learning application is significantly more cost-effective and faster.
- You receive a coordinated hardware platform with good software support.
- With the three memory variants, you can choose the one best suited for your application - offering options to your customers, or optimizing costs
Tip: we offer you hardware and software design from a single source, centered around Coral and the Raspberry Pi platform. If interested, please contact us for a non-binding and free initial consultation.
Note on availability
Coral 1GB SoM available on request!
Coral SoM
In addition to the EdgeTPU, the Google Coral SoM contains the most important components of an embedded PC:
- NXP i.MX 8M SoC (CPU + GPU)
- Google Edge TPU ML accelerator
- Crypto co-processor
- Wi-Fi + Bluetooth
- 8 or 16 GB eMMC
- 1, 2, or 4 GB LPDDR4
- USB 3.0 interface
- Gigabit Ethernet interface
- HDMI and MIPI-DSI
- MIPI-CSI-2
- up to 95 x GPIO (including SPI, I2C, PWM, UART, SAI and SDIO)
In the prototyping stage, you can implement your application using the 4GB Coral Development Board, which is based on this SoM module - and then easily realize your own hardware design that is optimized for your application.
The Edge TPU
With the Edge TPU, Tensor Flow Lite models can be used quickly and energy-efficiently for inference.
A special advantage of this solution: your data remains local. This helps with latency, and of course with data protection! (And accordingly, in compliance with relevant laws, for example the General Data Protection Regulation (GDPR)).
Google increasingly uses artificial intelligence (AI) and machine learning (ML) to implement its services. For this purpose, it developed specialized processors for its data centers called TPU ("tensor processing unit"), which can execute algorithms with the TensorFlow framework faster and more energy-efficiently. For example, Google Maps is improved by street signs recorded by Street View, which are analyzed with the help of a TensorFlow-based neural network. The trick: TensorFlow can be easily programmed in Python.
The Edge TPU supports the TensorFlow Lite Framework. The Edge TPU can perform up to 4 trillion operations per second with only 2 W consumption . TensorFlow Lite is a modified variant of TensorFlow, specially adapted to the needs of mobile devices and embedded devices. Many TensorFlow applications can also be realized in TensorFlow Lite.
Technical data Coral SoM (System-on-Module)
NXP i.MX 8M SoC
- Quad-Core ARM Cortex-A53 (@1.5 GHz, 64-bit ARMv8-A) + Cortex-M4F
- Vivante GC7000Lite GPU (supports Vulkan), 32 GFLOPs 32-bit or 64 GFLOPs 16-bit
- 4Kp60 HEVC/H.265 main and main 10 decoder
- 4Kp60 VP9, 4Kp30 AVC/H.264 decoder (requires full system performance)
- 1080p/60fps MPEG-2, MPEG-4, MJPEG, H.263 decoder
Memory
- Flash: 8GB or 16 GB eMMC (4GB RAM variant only)
- RAM: 1GB / 2GB / 4GB LPDDR4 variants
- SDIO interface supports boot from SD card (if present in your design)
EdgeTPU
- Google Edge TPU ML accelerator coprocessor
- 4 TOPS (int8); 2 TOPS per Watt
- connected to NXP i.MX 8M SoC via PCIe (Gen2 x1) and I2C/GPIO
Tip: the connection via PCIe enables the maximum transfer rate to the EdgeTPU module, which is why the Coral System-on-Module is particularly well suited for applications with high frame rates / high performance requirements.
Network & USB
The Coral SoM has the following network interfaces:
- Wi-Fi 2x2 MIMO (802.11a/b/g/n/ac 2.4/5GHz), Murata LBEE5U91CQ Module
- Bluetooth 4.2 and BLE (Bluetooth Low Energy), Murata LBEE5U91CQ Module
- 2x USB 3.0/2.0 controllers with integrated PHYs
- 1x Gigabit Ethernet controller, supports EEE, Ethernet AVB, and IEEE 1588, via RGMII (Reduced gigabit media-independent interface)
HDMI Display Interface
- HDMI 2.0a (standard size), supports one display with up to 1080p resolution
- Upscaling & downscaling between 4K and HD video (uses full system resources)
- 20+ Audio interfaces 32-bit @ 384 kHz fs, with Time Division Multiplexing (TDM) support
- SPDIF input and output
- Audio Return Channel (ARC) via HDMI is supported
MIPI-DSI Display Interface
- MIPI-DSI 4 Lanes, supports one display, resolutions up to 1920 x 1080 @ 60 Hz
- LCDIF Display Controller
- Output: LCDIF or DC display controller output
Audio
- 1x SPDIF input and output
- 2x synchronous audio interface (SAI) modules, support I2S, AC97, TDM and codec/DSP interfaces
- 1x SAI for 8 Tx channels for HDMI audio output
- 1x SPDIF input for HDMI Arc input
Camera
- 2 x MIPI-CSI2 camera inputs (4-lane each)
GPIO Interface
-
2x UART interface
-
2x I2C interface
-
2x SPI interfaces
-
16x GPIOs with interrupt capability
-
4x PWM outputs
Connectivity & Interfaces: Miscellaneous
- 1x uSDHC Interface
- IOMUXC (Input/output multiplexing controller) for pad control
Note: the SoM uses some of the SoC GPIOs / interfaces internally, e.g., to connect the Coral Edge TPU. The interfaces listed here already take this into account and are fully available to you.
Security
- Resource Domain Controller (RDC), supports four domains and up to eight regions
- Arm TrustZone (TZ) architecture
- On-Chip RAM (OCRAM) secure region protection using OCRAM controller
- High Assurance Boot (HAB)
- Cryptographic acceleration and assurance (CAAM) module
- Secure non-volatile storage (SNVS): Secure real-time clock (RTC)
- Secure JTAG controller (SJC)
- Crypto coprocessor Microchip ATECC608A
Power Supply
The Coral SoM requires a 5 V power supply and generates all other necessary voltages itself with an on-board PMIC.
Power consumption of the SoM approx.:
- idle: 2.6 W
- idle with HDMI output: 3.0 W
- High performance: 6.2 W
Further Information
- Dimensions of the Coral SoM: 40 mm x 48 mm x 5.11 mm
- Weight: 13 g
- Connection to carrier board: the SoM is connected to the carrier board via three 100-pin connectors (Hirose DF40C-100DP-0.4V).
Software Support
Mendel Linux
Mendel Linux is a Debian derivative developed by Google, specifically for the Coral platform. A bootloader is pre-installed on the SoM ex-works; you must install Mendel Linux manually. Here you can find instructions.
Mendel Linux uses Debian's upstream binary packages to maintain maximum compatibility and enable timely security updates. It currently only supports the Coral Dev Boards (also known as "enterprise" or "phanbell") and the Coral SoM modules (System-on-Module).
TensorFlow Lite
The Coral System-on-Module supports the execution of (compiled) TensorFlow Lite models on its EdgeTPU.
The Coral System-on-Module supports AutoML Vision Edge, to quickly deploy models for image classification.
Recommended further accessories:
Potential for industrial applications & Consulting
The Google Coral TPU & TensorFlow Lite are a revolutionary product platform for machine learning applications! This enables embedded solutions that can, for example, detect problems with workpieces, recognize traffic situations, and much more.
The Coral SoM (System-on-Module) is suitable if you are aiming for your own hardware solution that places higher demands on machine learning inference and at the same time requires optimized power consumption.
As an alternative to the SoM, which offers its own platform, Coral by Google also offers PCI Express modules and M.2 modules that can extend your existing or off-the-shelf hardware. We would be happy to advise you on the possibilities.
Consulting
We (pi3g GmbH & Co. KG) are happy to advise you as Google's European general distributor for Google's Coral product range.
We will honestly tell you if we see potential for your application, and if in our opinion another solution would be more suitable.
If interested, please contact us
Hardware & Software Development
We offer you hardware & software development from a single source.
We also offer software development related to artificial intelligence. It is a young field with massive value creation potential for you and your company - please contact us if you are interested in this forward-looking field.
Additional Information
| Coral System-on-Module with | Google Part Numbers | ASUS Part Number |
| 1GB RAM + 8GB eMMC | G650-04474-01 | 90AN00I4-M0XAY0 (Current Stock) 90AN00I4-B0XAY0 (New Production) |
| 2GB RAM + 8GB eMMC | G650-05369-01 | 90AN00I5-B0XAY0 |
| 4GB RAM + 16GB eMMC | G650-05370-01 | 90AN00I6-B0XAY0 |
Safety Information
- Read the user manual carefully before using the product.
- Ensure that all assembly and installation instructions from the manufacturer are carefully followed.
- Only use the product for its intended purpose.
- Improper use of this product can lead to serious injury or property damage.
- Not suitable for children under 10 years of age.
- There is a risk of injury if used improperly.
- This product complies with the applicable safety requirements of the European Union.
- This product has been tested in accordance with GPSR, which ensures that all relevant safety requirements for consumer goods are met.
Traceability Information
Each product has one or more of the following features:
- A CE mark indicating compliance with the European Union's safety, health, and environmental protection requirements.
- A unique serial or batch number to ensure traceability and support recall actions if necessary.
- Manufacturer and importer details for customer support and safety inquiries.
Monitoring and Reporting of Incidents
In the unlikely event of a product issue, we have implemented procedures to:
- Address customer complaints promptly.
- Report serious incidents via the EU Safety Gate/RAPEX system.
- Cooperate with market surveillance authorities to ensure public safety.
Contact:
- Email: support [@] pi3g.com
- Phone: 0341 / 392 858 40
This product is fully compliant with all applicable EU regulations to ensure the safety of our valued customers.