Kneron Boosts On-Device Edge AI Computing Performance With Cadence Tensilica IP


Reading time ( words)

Cadence Design Systems, Inc. announced that Kneron, a leading provider of on-device edge AI solutions, has integrated the Cadence® Tensilica® Vision P6 DSP in its next-generation KL720, a 1.4TOPS AI system-on-chip (SoC) targeted for AI of things (AIoT), smart home, smart surveillance, security, robotics and industrial control applications. Demonstrating its continued leadership in the low-power, high-performance vision DSP market, the Tensilica Vision P6 DSP provides Kneron with up to 2X faster performance for computer vision and neural network processing compared to its prior-generation SoC, while delivering the power efficiency crucial for edge AI.

In designing the KL720, Kneron prioritized design flexibility and configurability for its customers, promoting seamless AI development and deployment when using the new platform. Through its scalable Xtensa® architecture and the Xtensa Neural Network Compiler (XNNC), the Tensilica Vision P6 DSP provided Kneron with the flexibility and compute efficiency to easily adapt to the demands of the latest algorithms on the edge.

“Removing hurdles and making AI algorithm deployment on our platform easy is key for us and our customers’ success as our mission is to enable AI everywhere, for everyone,” said Albert Liu, founder and CEO of Kneron. “The Tensilica Vision P6 DSP packs a lot of compute capacity to tackle the latest AI challenges. Additionally, Cadence’s electronic design automation full flow along with on-site support helped tremendously to speed up IP integration and reduce time to market.”

Part of the broader Tensilica AI IP offering at Cadence, the Tensilica Vision P6 DSP has been adopted by a number of leading companies in the mobile, AR/VR, AIoT, surveillance and automotive markets. It supports the company’s Intelligent System Design strategy, delivering pervasive intelligence.

Share

Print


Suggested Items

Kirigami Inspires New Method for Wearable Sensors

10/22/2019 | University of Illinois
As wearable sensors become more prevalent, the need for a material resistant to damage from the stress and strains of the human body’s natural movement becomes ever more crucial. To that end, researchers at the University of Illinois at Urbana-Champaign have developed a method of adopting kirigami architectures to help materials become more strain tolerant and more adaptable to movement.

Worldwide Semiconductor Equipment Billings at $13.3 Billion in 2Q19; Down 20%

09/12/2019 | SEMI
Worldwide semiconductor manufacturing equipment billings reached $13.3 billion in the second quarter of 2019, down 20% from the same quarter of 2018 and 3% from than the previous quarter.

Designing Chips for Real Time Machine Learning

04/01/2019 | DARPA
DARPA’s Real Time Machine Learning (RTML) program seeks to reduce the design costs associated with developing ASICs tailored for emerging ML applications by developing a means of automatically generating novel chip designs based on ML frameworks.



Copyright © 2020 I-Connect007. All rights reserved.