Offers an average reduction of 5 times the compilation time and a 10% improvement in the quality of the results
SAN JOSE, California, June 22, 2021– (COMMERCIAL THREAD) – Xilinx, Inc. (NASDAQ: XLNX) today introduced Vivado® ML Editions, the industry’s first EDA FPGA tool suite based on machine learning (ML) optimization algorithms, as well as Advanced team design workflows for significant design savings in time and money. Vivado ML editions offer 5x faster build time and breakthrough results quality (QoR) improvements averaging 10% for complex designs, compared to current Vivado HLx editions.
This press release features multimedia. See the full version here: https://www.businesswire.com/news/home/20210622005291/en/
The new Xilinx Vivado® ML editions (Photo: Business Wire)
“Today’s EDA designers are faced with ever increasing design complexity. Machine learning is the next big step forward in accelerating the design process and delivering QoR gains, ”said Nick Ni, director of marketing, software and AI solutions at Xilinx. “Vivado ML will help developers reduce design cycles and deliver new levels of productivity from inception from design to closing. “
Vivado ML Editions enables ML-based algorithms that speed up design close. The technology includes ML-based logic optimization, lead time estimation, and intelligent design runs, which automate strategies to reduce sync close iterations.
“Vivado ML Editions’ smart new designs are game-changing,” said Robert Atkinson, senior hardware engineer at National Instruments. “By offering a push-button method to aggressively improve sync results, it generates QoR suggestions that bring maximum impact and deliver expert quality results with reduced user analysis – especially for designs that are difficult to close. “
Faster compilation time and team productivity
Xilinx also introduces the concept of an abstract shell, which allows users to define multiple modules within the system to be compiled incrementally and in parallel. This allows an average reduction in compilation time of 5x and, up to 17x, compared to traditional full system compilation. Abstract Shell also helps protect a customer’s intellectual property by hiding design details on the outside of modules, essential for applications such as FPGA-as-a-Service and value-added system integrators.
Additionally, Vivado ML Editions enhances collaborative design with Vivado IP Integrator, which enables modular design using the new “block design container” functionality. This capability fosters a team-based design methodology and enables a division-to-rule strategy to manage a large-scale design with multi-site cooperation.
Unique adaptability features such as Dynamic Function eXchange (DFX) to enable more efficient use of silicon resources by loading custom hardware accelerators, dynamically when running over the air. With DFX’s ability to load design modules in milliseconds, it opens up new use cases such as a car swapping different vision algorithms while processing an image, or genomic analysis swapping different algorithms over time. real when sequencing DNA.
Vivado ML Editions is now available in a Free Standard Edition and an Enterprise Edition starting at $ 2,995 MSRP. For more information visit: www.xilinx.com/vivado-ml.
Xilinx, Inc. develops highly flexible and adaptive processing platforms that enable rapid innovation across a variety of technologies – from the cloud, to the edge, to the endpoint. Xilinx is the inventor of the FPGA and Adaptive SoCs (including our Adaptive Compute Acceleration Platform, or ACAP), designed to deliver the most dynamic computing technology in the industry. We collaborate with our clients to create scalable, differentiated and intelligent solutions that enable the adaptable, intelligent and connected world of the future. For more information visit www.xilinx.com.
Source: Xilinx Newsroom
Category: Product announcements
© Copyright 2021 Xilinx, Inc. Xilinx, the Xilinx logo, Vivado, and other designated marks included herein are registered trademarks of Xilinx in the United States and other countries.
See the source version on businesswire.com: https://www.businesswire.com/news/home/20210622005291/en/