Ultra low power inference engine
Overview
Innatera's ultra-efficient neuromorphic processors mimic the brain's mechanisms for processing sensory data. Based on a proprietary analog-mixed signal computing architecture, Innatera's processors leverage the computing capabilities of spiking neural networks to deliver ground-breaking cognition performance within a narrow power envelope. With an unprecedented combination of ultra-low power consumption and short response latency, these devices enable high-performance always-on pattern recognition capabilities in applications at the sensor-edge.
Key Features
- Neuromorphic processor
- Sub milliwatt power
- Ultra-low power AI processing
- Intelligent edge products
Benefits
- 500x lower energy: Always-on pattern recognition within an extremely narrow power envelope
- 100x shorter latency: Blazingly fast recognition of spatial and temporal patterns in complex sensor data
- Pattern recognition simplified: Simple to program and deploy with Innatera's powerful SDK
Block Diagram
Applications
- Smartphones
- Wearables
- Hearables
- Smart speakers
- Health sensing
- IOT
- Automotive
- AR/VR/Gaming
- Cameras
Deliverables
- Hardware design
- Spiking neural networks
- Powerful SDK
Technical Specifications
Maturity
Silicon proven
Related IPs
- I2C Controller IP – Slave, SCL Clock, Parameterized FIFO, APB Bus. For low power requirements in I2C Slave Controller interface to CPU
- AHB Low Power Subsystem - ARM Cortex M0
- OSC Crystal Oscillator Low Power Series
- DC-DC Buck Ultra Low Iq Series (Vin=1.62-3.6V; Vo=1.4V; IL=100mA)
- DC-DC Buck Ultra Fast Response High Power Series (Vin=1.6-1.98V; Vo=0.725-1.325V; IL=6A)
- 14-bit, 1200 MSPS Ultra Low Power ADC in 28nm CMOS