Eta Compute Inc. announces the first shipment of production silicon for its ECM3532, the world’s first AI multicore processor for embedded sensor applications. This unique multicore device features the company’s patented Continuous Voltage Frequency Scaling (CVFS) and delivers power consumption of microwatts for many sensing applications.
Eta Compute’s ECM3532 is a Neural Sensor Processor (NSP) for always-on image and sensor applications. It will be on display at the 2020 tinyML Summit, February 12-13 at Samsung Electronics in San Jose, California. Eta Compute is a Gold Sponsor of tinyML and will demonstrate the ECM3532 for image recognition and other edge sensing applications. The objective of the entire tinyML community is to enable ultra-low power machine learning at the network edge.
Eta Compute’s ECM3532 family brings AI to edge devices and transforms sensor data into actionable information for voice, activity, gesture, sound, image, temperature, pressure, and bio-metrics applications, among others. The platform solves issues for the most important issues in edge computing: longer battery life, shorter response time, increased security and higher accuracy.
The company’s standalone AI platform includes a multicore processor, that includes flash memory, SRAM, I/O, peripherals and a machine learning software development platform. The patented CVFS substantially increases performance and efficiency for edge devices. The self-timed CVFS architecture automatically and continuously adjusts internal clock rate and supply voltage to maximize energy efficiency for the given workload. The ECM3532 multicore NSPcombines an MCU and a DSP, both with CVFS, to optimize execution for the best efficiency making it an ideal solution for IoT sensor nodes.
- 5 x 5 mm 81 ball BGA
- As low as 100μW active power consumption in always-on applications
- Arm Cortex-M3 processor with 256KB SRAM, 512KB Flash
- 16b Dual MAC DSP with 96KB dedicated SRAM for ML acceleration
- Neural Development SDK with TensorFlow interface for seamless model integration into the ECM3532