Had the opportunity to get a briefing from executives at Eta Compute
. The company is based in Westlake Village offering very low power AI accelerator chips for a variety of AI edge inference applications most notably voice processing, sensor applications among others.
They have chosen a unique architectural philosophy and have shunned away from developing AI-specific custom compute arrays. instead, they utilize proven and popular processor and DSP IPs. The core of their chip consists of an ARM Cortex-M3 bolted to NXP Coolflux DSP processor IP. This approach has enabled them to utilize a tremendous amount of tools and resources that are available for both of these popular cores. No need to reinvent the wheel.
Impressive power numbers. Able to support voice recognition models with less than 1mW in active mode including the microphone and ADC and 1uA in rest mode . Remarkable power numbers have been achieved by leveraging Dynamic Voltage Scaling, asynchronous design techniques, and sub-threshold design methodology.
While their platform can cater to many edge applications, voice processing seems to be front and center. Their solution goes above and beyond just “keyword” detection and is able to tackle intense voice recognition use cases. They view the support for RNNs and LSTMs crucial for voice applications and have chosen an architecture augmented with elaborate tools serving such models.
Another major differentiation of their product is integrating various application specific building blocks such as analog to digital converts (ADC) for sensor interface, power management, as well as a plethora of interfaces (i.e. I2C, I2S, GPIOs, …).
They also have done well when it comes to strategic partnerships. They have forged a partnership with Rohm Semiconductor to enable their wireless sensor initiative as well as TDK and Vesper on the microphone for speech applications.
Another company in a crowded space that gets it.