AI processor startup Quadric turns to IP licensing with MegaChips
AI processor startup Quadric.io Inc. (Burlingame, Calif.) has struck a strategic deal with ASIC and SoC services company MegaChips Co. Ltd. (Osaka, Japan) around intellectual property licensing.
MegaChips will develop chips based on Quadric’s edge AI processor, which is described as a general-purpose neural processing unit or (GPNPU).
Quadric has also announced that Steve Roddy, a former vice president with ARM’s machine learning group, has joined the company as chief marketing officer. Roddy’s appointment coincides with the announcement of the decision to bring the edge AI processor architecture to market as a licensable intellectual property (IP) product.
Quadric was founded in 2016.
MegaChips announced an equity stake in Quadric in January 2022 and is also a major investor in a $21M Series B funding round announced in March through their MegaChips LSI USA Corporation subsidiary. The round aims to help Quadric release the next version of its processor architecture, improve the performance and breadth of the Quadric software development kit (SDK), and roll out IP products to be integrated in MegaChips’ ASICs and SoCs.
The Quadric architecture is capable of both neural backbones and dynamic data-parallel algorithms in a unified architecture. It can also combine inference with a limited number of graph operators, the company claims. The ability to run C++ code and DSP routines alongside neural network inference and graph theory operations avoids the need for multiple processors and separate hardware accelerators in an application.
“Quadric’s stellar team, market traction with key customers and innovative edge AI solution contributed to our decision to invest in Quadric,” said Douglas Fairbairn, director of business development at MegaChips, in a statement issued by Quadric.
Target applications for MegaChips’ ASICs and SoCs based on Quadric’s IP include autonomous driving (ADAS/LiDAR), industrial robotics, factory automation, automated guided vehicles (AGV) and advanced medical equipment.
“While the AI market is saturated with rigid accelerators that only address a portion of the machine learning compute challenge, our processing platform fills the void with a fully programmable, multi-kernel processing architecture,” said Veerbhan Kheterpal, co-founder and CEO of Quadric, in the same statement.
Related links and articles: