Spiking Neural Processor T1

The ultra-low power neuromorphic microcontroller for always-on sensing applications

The Spiking Neural Processor T1 is an ultra-low power microcontroller that brings intelligence closer to the sensor. It uses an ultra-low-power spiking neural network engine and a nimble RISC-V processor core to form a single-chip solution for processing sensor data quickly and efficiently. The result is a comprehensive companion to sensors enabling next-generation AI and signal processing capabilities within a narrow power envelope. T1 unlocks groundbreaking applications in battery-powered, power-limited and latency-critical devices.

Nimble on-chip RISC-V CPU
32-bit RISC-V core, 384 KB embedded SRAM

Fast sub-1mW pattern recognition based on spiking neural networks
Unprecedented power-performance on signal processing and pattern recognition tasks using event-driven spiking neural networks

Multi-faceted processing capabilities
Efficiently implement SNNs, DNNs, and conventional processing in the same device

Diverse Interfaces
QSPI, I2C, UART, JTAG, GPIO, front end ADC

2.16mm x 3mm, 35-pin WLCSP package

Get a headstart with the T1 Evaluation Kit (EVK)

The T1 EVK is the quickest way to get started with developing applications for the T1 silicon. The EVK incorporates a comprehensive development board that facilitates full end-to-end application development using the T1's heterogeneous processing capabilities, with extensive support for profiling performance and power dissipation in hardware. Use the Talamo SDK to generate application software for the T1, or use one our off-the-shelf applications. The EVK integrates a range of standard interfaces supported by commonly used sensors including microphones, radars, inertial measurement units, and image sensors, among others. 

Get in touch »