Sondrel has optimised the SFA 100 to make it perfect for AI at the Edge applications that are battery-powered. One of the five architectural platforms in the company’s chip design platform, Architecting the Future, is the SFA 100.
This platform offers a ready-made design baseline that the company utilizes to construct a customized solution for each customer considerably more quickly than having to start from scratch every time.
“The drive to AI everywhere was clear at this year’s CES,” said John Chubb, Sondrel’s CEO. “It enables companies to create better, more feature-rich products but augmenting with AI is not a simple task. It requires much more powerful processor cores than a standard version of a device to handle the large amounts of data involved which can’t just be added onto an existing design. It requires a design from scratch to make sure that the right processors, memory, DSPs, NoC and other components all fit together against the target Power, Performance, Area and Timing specifications.”
“This is where our Architecting the Future approach can save a significant amount of time and engineering effort. We don’t start from scratch every time as we use existing, proven blocks and layouts. By using one of our pre-defined starting architectures, such as the SFA 100, we can rapidly tailor this to create a unique, custom solution for each customer. Effectively we are re-using a framework or chassis and scalable entities such as cores that we have used before along with tools, flows, project management, etc. which reduces risk and, most importantly, time to silicon so that the customer can be fast to market with the AI empowered device added John.”
The Arm® subsystem used by the SFA 100 offers a selection of Arm cores together with the option of a security subsystem. Because of its low power consumption, it is touted as the perfect platform for edge AI applications that are battery-powered, which means sensor fusion devices, smart factories, and smart homes.
A machine-learning engine that supports a range of inference-based “smarts,” including gesture detection, voice activation, picture categorization, filtering, and more, can be included into the device, mentions Sondrel.
If necessary, a radio subsystem can also be included, such as WiFi or a Bluetooth IP block. Any IP belonging to the customer or a third party may be incorporated since Sondrel may wrap IP blocks to provide them all the interfaces they need to simply slide into the chassis. The SFA 200 or SFA 300 can be used as a starting point to generate more powerful solutions.
Edge AI Market
Transparency Market Research has projected that the Edge AI market would grow at a compound annual growth rate (CAGR) of 33.5%, reaching a valuation of $76 billion by 2031. The motivation to process data locally is crucial because it reduces delay associated with sending it to a centrally located cloud server for processing. Applications include real-time decision making in industry 4.0 and gadgets like vehicles, smartphones, drones, and more.
Further details on the Architecting the Future range can be found here.
For Further Info: CLICK HERE
