首页|Studies from University of Texas Austin Describe New Findings in Machine Learning (Isop Plus : Machine Learning-assisted Inverse Stack-up Optimization for Advanced Package Design)
Studies from University of Texas Austin Describe New Findings in Machine Learning (Isop Plus : Machine Learning-assisted Inverse Stack-up Optimization for Advanced Package Design)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
IEEE
Researchers detail new data in Machine Learning. According to news reporting originating in Austin, Texas, by NewsRx journalists, research stated, “The future of computing requires heterogeneous integration, including the recent adoption of chiplet methodology, where high-speed cross-chip interconnects and packaging are critical for the overall system performance. As an example of advanced packaging, a high-density interconnect (HDI) printed circuit board (PCB) has been widely used in complex electronics ranging from cell phones to computing servers.” Financial support for this research came from National Science Foundation (NSF). The news reporters obtained a quote from the research from the University of Texas Austin, “A modern HDI PCB may have over 20 layers, each with its unique material properties and geometrical dimensions, i.e., stack-up, to meet various design constraints and performance requirements. Stack-up design is usually done manually in the industry, where experienced designers may devote many hours adjusting the physical dimensions and materials in order to meet the desired specifications. This process, however, is timeconsuming, tedious, and suboptimal, largely depending on the designer’s expertise. In this article, we propose to automate the stack-up design with a new framework, ISOP+, using machine learning (ML) for inverse stack-up optimization for advanced package design with adaptive weight adjustment and multilevel optimization. Given a target design specification, ISOP+ automatically searches for ideal stack-up design parameters while optimizing performance. A novel ML-assisted hyperparameter optimization method is developed to make the search efficient and reliable. Experimental results demonstrate that ISOP+ is better in figure-of-merit (FoM) than conventional simulated annealing and Bayesian optimization algorithms, with all our design targets met with a shorter runtime.”
AustinTexasUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine LearningUniversity of Texas Austin
NETL
NSTL
IEEE
