Kneron KL720 Arm Cortex-M4 AI SoC Delivers 1.5 TOPS at 1.2 Watts

We first came across Kneron AI processors last year, when we covered AAEON M.2 & mPCIe AI accelerator cards powered by Kneron KL520 dual-core Cortex-M4 processor and delivering 0.3 TOP AI acceleration performance at 0.5 Watt.

The company has now introduced a more powerful processor with Kneron KL720 single Arm Cortex-M4 AI processor delivering up to 1.5 TOPS at 1.2 Watts, or 0.9 TOPS for 1 Watt.

Kleron KL720 Cortex-M4 AI Processor

The company does not provide much other information in terms of specifications, but Kneron KL720 is said to be two to four times more power-efficient than competitors at a lower cost and is best suited for high-end IP cameras, Smart TVs, AI glasses & headsets, as well as AIoT Gateways.

The processor can process 4K images, full HD videos, and 3D sensing data for facial recognition and gesture control for gaming, shopping kiosks, etc.. Besides computer vision, the chip can also handle natural language processing (NLP) for translators and AI assistants.

If you are really interested in the solution you can watch the 3-hour video embedded below. Kneron KL720 introduction starts at the 5 minutes mark. A lot of the discussion involves talking with partners like DJI and AAEON, investors, and educators, so it’s probably not too technical. Sorry, I did not watch it all…

The company also introduced the “Kneron Neural network Edge AI Open platform” (aka KNEO). The platform creates a private mesh network leveraging blockchain technology to secure the network of Kneron-powered nodes and support sensor fusion. This removes the need for cloud access to process AI models and applications as instead multiple “sensors” that can be cameras, microphones, thermometers, etc.. communicate within the private mesh network.

There may eventually be more details about Kneron KL720 on the product page, but more information is already available about KNEO.

Via EE News

Share this:

Support CNX Software! Donate via PayPal or cryptocurrencies, become a Patron on Patreon, or buy review samples

Subscribe
Notify of
guest
The comment form collects your name, email and content to allow us keep track of the comments placed on the website. Please read and accept our website Terms and Privacy Policy to post a comment.
4 Comments
oldest
newest
yenda
yenda
1 year ago

I apologize, but what measure is “TOP”? I don’t wanna watch the 3-hours video :-/

willy
willy
1 year ago

It’s “TOPS” for “Tera Operations Per Second”, 1000 times higher than “GOPS” (giga ops per second)” by analogy with “GFLOPS” (giga floating point operation per second)” used in the floating point world. The operation in question is not really defined but usually it designates a basic operation that the industry agrees that is the smallest relevant one. For AI it will often be a MAC operation (multiply+accumulate such as in y += x*a). However the size of this smallest operation depends on the chips, I think by now most are 8 bits, likely with saturation. And I’m not at all… Read more »

yenda
yenda
1 year ago

I see. Thanks both of you — I’m familiar with GFLOPS and TFLOPS but somehow it didn’t click it could be a similar measure for fixed point math or ints or something like that.

Advertisement