Use of SiFive’s Risc-V Core IP Enables Low Power AI IoT Edge and End Point Devices.
Aerendir Mobile Inc. will merge its mathematical deep learning cores and AI infrastructure with innovative SiFive, Inc., RISC-V Core IP to enable a new low-cost board format for deep learning. This combined, unique approach will radically decrease the cost of true AI, allowing it to be enabled at the IoT Edge and End Point inside affordable devices.
Aerendir and SiFive expect that the IoT market, bolstered by future 5G networks, will require the most cost-effective high-end distributed learning capabilities. As data collection continues to grow and outstrip the ability of datacenters to store, process and analyze new devices at the edge, end point can help to make accurate machine learning decisions. Local data analysis reduces network congestion and latency, improving local device performance and helping to send important data to the cloud for further analysis.
Aerendir will offer three versions of cloudless, on-device AI: a very high end allowing for high DSP performances, an intermediate and a low-cost one.
“A user-friendly connected IoT ecosystem requires ultra-smart, low-cost components that can perform adequately without relying on the cloud,” said Dr. Martin Zizi, CEO of Aerendir Mobile Inc. “Cloudless connectivity also enforces everyone’s privacy.”
“The need for custom SoCs designed with deep learning and scalability in mind is a key focus for SiFive,” said Naveed Sherwani, CEO of SiFive. “The potent combination of Aerendir’s IP with SiFive’s configurable RISC-V cores will help to drive the adoption of true AI at IoT edge and end point, where machine learning can benefit both industrial IoT and consumer device functionality.”