BURLINGAME, Calif.–(BUSINESS WIRE)–Quadric™, a leading processor technology intellectual property (IP) licensor, today announced that Steve Roddy, former vice president of Arm’s machine learning group, has joined the company’s management team as Chief Marketing Officer (CMO). Coinciding with this leadership appointment, Quadric also announced that it is commercializing its state-of-the-art artificial intelligence processor architecture as a licensed intellectual property (IP) product.
Roddy brings over 30 years of marketing and product management expertise in the areas of machine learning (ML), neural network processor (NPU), microprocessor, digital signal processor (DSP) and Semiconductor IP. He joined ARM in 2018 as vice president of the Machine Learning group. Prior to Arm, Roddy held VP positions in the IP licensing businesses at Tensilica (Cadence Design Systems) and Amphion Semiconductor, as well as previous product management roles at Synopsys, LSI Logic and AMCC. Roddy holds a Bachelor of Science in Electrical Engineering from the University of California, Berkeley and an MBA from UCLA.
“Steve’s exceptional knowledge of IP products and his vision for bringing licensing to market will strengthen our continued momentum to become one of the world’s leading processor architectures for on-device ML inference,” said Veerbhan. Kheterpal, co-founder and CEO of Quadric. “As Quadric launches the availability of its processor architecture as a licensed IP product and expands its reach into global markets, Steve’s expertise and leadership will be critical in taking the business to the next level.”
“Joining Quadric represents a tremendous opportunity to apply my NPU and DSP expertise to what lies ahead for both Quadric and the industry as a whole,” said Steve Roddy. “Quadric’s architecture, already proven in silicon, is the only new processor capable of efficiently running both DSP code and machine learning graph inference on the same core. The massive increase in software developer productivity achieved by having only one toolchain and one kernel to program, manage, and debug is changing the market. I am thrilled to join the highly accomplished and committed team at Quadric at a time when on-device AI computing is catapulting the processor market forward.
GPNPU – A new category of processor IP
The Quadric architecture is the industry’s first General Purpose Neural Processing Unit (GPNPU). Quadric’s architecture provides high ML inference performance, but unlike other neural network accelerators that support a limited number of ML graph operators, the Quadric solution also has the ability to control and general-purpose signal processing, combining the best attributes of NPU accelerators with DSPs. Quadric GPNPUs can run both neural network graphs and C++ code for signal pre- and post-processing.
“In embedded applications, neural networks are typically found alongside classic computer vision, image processing, and signal processing algorithms,” said Jeff Bier, founder of Edge AI and Vision Alliance. “Quadric’s approach of processing both the neural network and other types of algorithms with a single processor is quite interesting. I look forward to hearing more about Quadric’s GPNPU when they showcase later this week at the Embedded Vision Summit.
Quadric’s unique ability to manage both neural backbones and classic data-parallel dynamic algorithms in a unified architecture will help create AI for everyone, everywhere. Quadric’s unified architecture is flexible enough to accelerate the entire data pipeline without the need for complex multi-core subsystems and multiple tool chains.
Future-proof SoC designs
The Quadric GPNPU offers an unparalleled degree of flexibility to semiconductor companies selecting processor IP for their new system-on-chip (SoC) developments. Silicon vendors today must select and license processor engines that will ship in devices sold years from now and programmed by developers for years to come. As machine learning algorithms evolve, Quadric’s GPNPU provides future-proof programmability to run new neural network operators or new C++ code to meet the future needs of data scientists and embedded developers .
Quadric builds a unified hardware and software architecture optimized for on-device AI computing. Quadric offers a full-stack integrated software and hardware platform with optimized algorithms and next-generation GPNPU processor technology that delivers unmatched capabilities and efficiency in applications for a variety of devices. As AI becomes a business necessity in the global economy, customers need comprehensive AI solutions deployed at scale. Quadric’s unique ability to manage both neural backbones and classic dynamic data parallel algorithms in a unified architecture helps create AI for everyone, everywhere. Learn more about quadric.io.