The world of machine learning keeps getting tinier and tinier — and with their second ECM3532-based board, Eta Compute have shrunken machine vision applications to a diminutive 1.5-inch square!
Eta Compute claims that the ECM3532 is the industry’s first AI multicore processor for embedded sensor applications. It features the company’s patented continuous voltage frequency scaling (CVFS) with dynamic voltage and frequency scaling and near-threshold voltage operation, delivering power consumption of microwatts (as low as 100-μW active power consumption in always-on applications) for many sensing applications.
Electronic Engineering Journal
That was the tall order facing Eta Compute. One of many, in fact. The small startup took on all sorts of self-imposed burdens. It invented a new MCU for AI inferencing. It invented a new low-power circuit design methodology it called DIAL (delay-insensitive asynchronous logic). It developed the chip’s compiler from scratch. Then it reinvented DIAL to create CVFS (continuous voltage and frequency scaling), which it then used to create an entirely new second-generation chip, the ECM3532. Then it had to redo the compiler for the new chip. And, when all of that was done, it had to go beat the bushes looking for customers who wanted an ultra-low-power MCU for “ML at the edge” from a new company nobody had ever heard of.
The company’s secret sauce is in a proprietary voltage and frequency scaling technique achieved without a phase locked loop (PLL), combined with Arm Cortex-M3 and NXP CoolFlux DSP cores which both operate voltage and frequency scaling independently.
The impact on the semiconductor industry is profound and it is nowhere more visible than on low-power, low-cost processors, micro-controllers, and DSP.