Coral TPU M.2 Edge Accelerator B+M Module
Coral TPU M.2 Edge Accelerator B+M Module is a small ASIC that uses the Edge TPU coprocessor for existing systems and products. It provides high-performance ML inferencing with low power requirements. Capable of performing 4 trillion operations (tera-operations) per second (TOPS), the M.2 Accelerator uses only 0.5 watts for each TOPS (2 TOPS per watt). Can execute state-of-the-art mobile vision modules such as MobileNet v2 at 400 FPS, in a power-efficient manner.
The Edge TPU on-device processing reduces latency, increases data privacy, and removes the need for constant high-bandwidth connectivity. The M.2 Accelerator is a dual-key M.2 card, designed to fit any compatible M.2 slot, allowing easy integration into ARM and x86 platforms.
Coral, a division of Google, helps build intelligent ideas with their platform for local AI.
Features
- Small 22mm x 80mm x 2.3mm
- PCB size 22mm x 80mm x 0.8mm
- Google Edge TPU ML accelerator coprocessor
- Dual B&M keyed
- High-speed TensorFlow Lite inferencing
- Supports Debian Linux on host CPU
Applications
- Add to products that have a compatible M.2 card slot
- Embedded platforms
- Mini-PCs
- Industrial gateways
Specifications
- 22.00 x 80.00 x 2.35 mm
- 5.8g
- M.2 B+M key (M.2-2280-B-M-S3)
- PCIe Gen 2 x1 serial interface
- 3.3v +/- 10% DC supply
- -40 to +85°C storage temp
- -20 to +85°C operating temp
- 0 to 90% (non-condensing) relative humidity
- Shock
- 100 G, 11 ms (persistent)
- 1000 G, 0.5 ms (stress)
- 1000 G, 1.0 ms (stress)
- Vibration (random/sinusoidal)
- 0.5 Grms, 5 - 500 Hz (persistent)
- 3 Grms, 5 - 800 Hz (stress)
- 1kV HBM, 250V CDM ESD
Dimensions in mm
See all Coral Accelerators
Coral Edge TPU ML Accelerator Modules
Designed to execute neural network processing for machine learning at high speed and low power cost.
Resources
Veröffentlichungsdatum: 2019-09-05
| Aktualisiert: 2023-07-27