Expedera raises funds to advance deep learning accelerator IP

1 min read

Expedera has completed a $18m Series A funding round led by Dr. Sehat Sutardja and Weili Dai (founders of Marvell Technology Group) and other leading semiconductor industry investors.

So far, the company has raises $27m and it will be using this new funding to speed product development and expand sales and marketing to meet the demand for its high performance and energy-efficient deep learning accelerator (DLA) IP.

A growing number of semiconductor chip makers are adding AI (Artificial Intelligence) inference capabilities to applications, including smartphones, smart speakers, security cameras, PC/tablets, wearables, automotive, and edge servers.

“We expect shipments of AI-enabled edge devices to grow from about 600m units in 2020 to 2bn units in 2025, representing 26% annual growth,” said Linley Gwennap, Principal Analyst at The Linley Group. “Smartphones, a market where Expedera already has traction, represent about half of these units.”

“This financing underscores the success that Expedera has had so far and will enable us to expand our portfolio and team to meet the market needs,” said Da Chuang, CEO of Expedera. “We are incredibly happy to have Weili Dai and Sehat Sutardja lead this round. As highly respected veterans of the semiconductor industry, they have a unique understanding of the market and customer needs. I look forward to a long partnership.”

“Device makers have typically needed to build their own chips and usually, only the largest companies could afford to do so,” said Gwennap. “Expedera’s IP model provides a more cost effective way to address the sprawling edge AI market. A single IP supplier can license to any or all of the numerous chip vendors that supply a multitude of device makers in the edge market.”

According to Expedera, its deep learning accelerator IP provides the industry’s highest performance per watt, and is scalable up to 128 TOPS with a single core and to PetaOps with multi-core. This makes it suitable for a wide range of AI inference applications, particularly at the edge.

Expedera’s Origin IP and software platform supports popular AI frontends including TensorFlow, ONNX, Keras, Mxnet, Darknet, CoreML and Caffe2 through Apache TVM. By licensing its technology as a semiconductor IP, Expedera will enable any chip designer to add state-of-the-art AI functionality to their product.