Kneron Edge AI SoC Powered by Andes RISC-V Processor Core D25F

San Diego, CA, November 4, 2021 – Kneron Inc., the San Diego-based Edge AI solution provider, together with Andes Technology Corporation (TWSE: 6533; SIN: US03420C2089; ISIN: US03420C1099), a leading supplier of high-performance, low-power 32/64-bit RISC-V processor cores, today announced formal mass production of Kneron’s next-generation Edge AI SoC KL530, powered by Andes’ D25F processor in consideration of its efficient pipeline architecture, powerful Packed-SIMD DSP extension instructions, and IEEE754-compliant high-performance single/double precision floating RVFD extensions.

KL530 is the latest generation of heterogeneous AI chip from Kneron, with a brand new NPU architecture. It is the first of its kind in the industry to support INT4 precision and Transformer. Compared with other Edge AI chips, it has higher computing efficiency and lower power consumption. The use of heterogeneous AI chips embedded with RISC-V processors, powerful image processing capabilities and interfaces will further enable the application of Edge AI chips in ADAS, AIoT and other market.

The computing power of KL530 can reach 1 TOPS@INT 4, and the processing efficiency is up to 70% higher than that of INT 8 under the same hardware conditions. Its reconfigurable NPU design takes advantage of the high performance of the D25F RISC-V core, and supports multiple AI models such as CNN, Transformer, RNN Hybrid, etc. Its Smart ISP can optimize image quality based on AI, and powerful codec can achieve high-efficiency multimedia compression. In addition, its cold start time is less than 500ms, and average power consumption is less than 500mW.

The D25F CPU, one of the most popular cores from AndesCore™ 25-series, is equipped with RISC-V P-extension ISA draft to efficiently manipulate multiple data sets simultaneously in one instruction. Andes initiated the P-extension, chairs its Task Group in RISC-V International and leads the specification definition. D25F is accompanied with complete development tools including compiler with auto-generation of SIMD instructions based on vector data type, optimized DSP libraries, neural network libraries, and near cycle-accuracy simulator. It delivers near 9 times speedup for popular machine learning algorithms, including Tensorflow keyword spotting, CIFAR10 image classification, and P-net object detection.

“Kneron has a unique reconfigurable architecture, which can fit easily into different convolutional neural networks (CNN) without compromise, thus serves a wide variety of AI models seamlessly and accurately.” said Albert Liu, Kneron founder and CEO. “The D25F CPU core with its powerful DSP instruction set and development framework enables Kneron to explore the performance of its industry-leading AI algorithms to the fullest while keeping power consumption optimal. It is crucial to our customers, especially for those who develop products such as smart devices and Edge AI appliances. We are happy to cooperate with Andes, the leading computing expert specialized in RISC-V architecture. With Andes RISC-V core and its DSP support, Kneron is able to develop this cutting edge solution smoothly within a very short time frame. We are really proud to see KL530 in mass production now serving our customers.”

“We are glad that Kneron chose the D25F to power KL530, especially after it went through a series of comprehensive evaluations,” said Andes CEO and RISC-V International Board Director Frankwell Lin. “The D25F stands out distinctly in every aspect on key indexes such as product features, performance, core area, and power consumption. As a leading enterprise in providing Edge AI SoC solution embedded with RISC-V core, Kneron showed its efficiency to quickly launch KL530 and enter mass production. It is astonishing to learn the strong competitiveness of Kneron’s team. Thanks to the extraordinary cooperation between Kneron and Andes, we jointly achieved a complete and highly competitive solution to facilitate AI applications for a wide variety of products.”

Kneron KL530 Product Launch

Kneron KL530 online product launch conference will be held at 10:00-11:30 am, November 4^th (PDT). GSA CEO Jodi Shelton, Winbond President Pei-Ming Chan, and YouTube Founder Steven Chan are invited to have talks to offer their perspective on the next-generation Edge AI. Registration information https://www.kneron.com/en/event-registration/ab29527e

About Kneron

Kneron is a San Diego based technology company that was founded in 2015. It develops both hardware and software products, which are used in smart devices to run and power AI applications. Kneron is a single port of call for device manufacturers who want to integrate AI into their products. The products include hardware such as AI chips and software such as AI models, that device manufacturers can use in everything from autonomous cars, all the way down to a smart fridge, doorbell, or any Internet of Things device. Kneron primarily solves three main problems for smart devices running AI — security, energy and cost, thereby enabling AI everywhere and for everyone. Kneron’s solutions are reconfigurable, and will be as efficient at processing image and audio AI models in the future as they are now. It has raised over $100mn to date and is backed by Horizons Ventures, Alibaba, Qualcomm, Sequoia, and more. For further information about Kneron, please visit: http://www.kneron.com/about.php

About Andes Technology

Sixteen years in business and a Founding Premier member of RISC-V International, Andes is a leading supplier of high-performance/low-power 32/64-bit embedded processor IP solutions, and a main force to take RISC-V mainstream. Andes’ fifth-generation AndeStar™ architecture adopted the RISC-V as the base. Its V5 RISC-V CPU families range from tiny 32-bit cores to advanced 64-bit cores with DSP, FPU, Vector, Linux, superscalar, and/or multicore capabilities. The annual volume of Andes-Embedded SoCs has exceeded 2 billion since 2020 and continues to rise. To the end of 2020, the cumulative volume of Andes-Embedded™ SoCs has reached 7 billion. For more information, please visit https://www.andestech.com.