PARIS — Eta Compute, a startup that demonstrated last summer at Hot Chips a very low power microcontroller using asynchronous technology, has come up with a new spin that it calls “the industry’s first neuromorphic platform.”  

In announcing the availability of its latest SoC platform IC based on TSMC's 55nm ULP process, Paul Washkewicz, vice president of marketing and a co-founder of Eta Compute, Wednesday (March 15) pitched it as an ideal platform for “delivering neuromorphic computing based machine intelligence to mobile and edge devices.” 

But wait. When did Eta Compute’s 0.25V IoT chip, from Hot Chips last year, become a “neuromorphic computing” engine? Did the startup pivot slightly in strategy? Washkewicz explained that Eta ventured down the path of “machine intelligence,” when “customers started telling us that they want a little bit more intelligence on the edge.”

Two pillars of Eta Compute’s claim for neuromorphic computing consist of an event-driven, no-clock delay insensitive asynchronous logic (DIAL) architecture for its hardware and the company’s spiking neural network software. 

Eta Compute (Westlake Village, Calif.) had already developed DIAL, which uses a novel handshake to wake up circuits resting at a very low power level. The system quickly turns on devices without the set-up and wait times usually required for synchronous circuits.

The key for startup’s course correction was adding more intelligence, in part through luring Nara Srinivasa away from Intel last fall. Srinivasa was senior principal engineer and chief scientist at Intel Labs. At Intel, Srinivasa was working to develop self-learning, neuromorphic architecture, seeking to tackle a broader class of AI problems.  Last September when Srinivasa was still at Intel, Intel announced a neuromorphic artificial intelligence test chip named Loihi. Intel said the test chip was designed to mimic brain functions by absorbing data gained from its environment.

Srinivasa, now CTO of Eta Compute, said in a statement: “Our patented event driven processor architecture, DIAL, is combined with our fully customizable neuromorphic algorithms.” He said, “These will be the foundation of a diverse and wide-ranging set of applications that deliver machine intelligence to the network edge.”

The concept of a computer that mimics the brain isn't new. But Intel’s Loihi AI chip should not be confused with Eta Comupte’s IP, because the startup is not offering exactly that. Eta Compute’s intention is to marry asynchronous, no-clock, event-driving DIAL hardware architecture with spiking neural model-based algorithms developed by Srinvasa and his team, explained Washkewicz.

Linley Gwennap, principal analyst at the Linley Group, is skeptical. Admitting that he hasn’t talked to Eta, he deemed its announcement “confusing.” 

Gwennap explained, “Neuromorphic computing refers to the use of integrated circuits to mimic the structure of the brain. Typical neuromorphic systems feature artificial neurons that together can implement certain types of neural networks. Naturally, this approach to computing is completely different from traditional Von Neumann CPUs such as Cortex-M3.” 

Very Low-power embedded processor

In the end, what Eta Compute is really announcing is “a very low power Cortex-M3 CPU design and some other very low power IP cores,” Gwennap suspected. After all, “We do see growing demand for low-power processors for remote IoT sensors and for certain wearable designs. This is a small market today but could become sizable as IoT becomes more popular,” he added.

Included in Eta’s new 55nm IP portfolio are an Arm Cortex-M3 processor, NXP-developed CoolFlux DSP, 12-bit SAR analog-to-digital converter, power management voltage references optimized to deliver high efficiency voltage scaling and support for low power analog blocks.

During an interview, Washkewicz told EE Times that Eta Compute’s asynchronous Cortex-M3 embedded processor at 65MHz runs on 2 milliwatts (mW). Eta Compute added NXP’s DSP to its IP portfolio, he noted, because machine intelligence requires certain signal processing, and NXP’s CoolFlux is a very low power, asynchronous DSP.  

Eta Compute is not offering, at this point, a full-fledged software development environment for its licensees. Instead, “we are following almost an ASIC-like model,” said Washkewicz, “by hardwiring AI engine in ARM processor.” Meanwhile, training is done by Eta Compute’s inhouse software development team. 

Eta Compute is already sampling its new IP platform. The startup has “a few lead customers” who are all exploring ways to integrate IP cores into their silicon, Washkewicz said. 

Applications of such chips range from speech, sensor fusion to wearable, heart-rate monito and images (face identification but not face recognition), Washkeqicz explained.

Asked about potential licensees, he said, “We can help any users of Arm MCUs, looking to improve intelligence.” Further, he noted that ASIC houses and Chinese fabless chip vendors are good targets.

— Junko Yoshida, Chief International Correspondent, EE Times