FET: Medium: Latch Ising Machines (LIM)

FET：介质：锁存机 (LIM)

基本信息

批准号：
2106944
负责人：
Jaijeet Roychowdhury
金额：
$ 80万
依托单位：
University of California-Berkeley
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2021
资助国家：
美国
起止时间：
2021-07-01 至 2025-06-30
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2106944&HistoricalAwards=false
关键词：
FET Medium Latch Ising Machines

项目摘要

Difficult computational (NP-complete) problems abound in today’s world, in areas as diverse as secure communications, protein folding, neural networks and healthcare. Large classes of these hard problems can be reduced to a form known as the Ising problem, which is closely related to the physics of ferromagnetic materials. The project team has devised a novel way of solving the Ising problem quickly and effectively in hardware, using networks of small, simple circuits, specifically, ``static'' memory cells, widely used in electronic devices of every kind. The concept significantly broadens the overall understanding of Ising machine schemes and their operational mechanisms. This project is developing this method (termed LIM) to practical fruition, including demonstration on real-world problems from communications. Being able to solve such real-world problems much more quickly and accurately than is currently practical can lead to broad benefits to society. The project's activities include a focus on students from traditionally disadvantaged backgrounds, as well as workshops for dissemination and interaction.More precisely, the team is showing that Ising machines, which have previously been realized using quantum/optical schemes as well as oscillator networks, can also be implemented using bi-stable elements such as CMOS-based latches. Unlike previous Ising machine approaches, which are large, expensive and ill-suited to low-cost mass production, the proposed approach is a purely classical scheme that does not rely on quantum phenomena or novel nano-devices. Using conventional CMOS electronics has many advantages: scalability/miniaturizability (i.e., very large numbers of spins in a physically small system), well-established design processes and tools that essentially guarantee first-time working hardware, very low power operation, seamless integration with control and I/O logic, easy programmability via standard interfaces like USB, and low cost mass production. Another key potential advantage stems from the continuous/analog nature of LIM (as contrasted with purely digital algorithms). The researchers are developing LIM theoretically and computationally, implementing it in hardware, and demonstrating it on benchmark Ising problems as well as Ising forms of difficult communications-related problems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

在当今世界上，困难的计算（NP完整）问题比比皆是，在潜水员，例如安全通信，蛋白质折叠，神经网络和医疗保健等领域。这些硬问题的大量类别可以简化为一种称为ISIN问题的形式，该形式与铁磁材料的物理学密切相关。该项目团队设计了一种新颖的方法，可以使用小型，简单的电路网络在硬件中快速有效地解决ISIN问题，尤其是``静态''存储单元，该网络广泛用于各种电子设备。该概念大大扩展了对Ising机器方案及其运营机制的整体理解。该项目正在将此方法（称为LIM）开发为实用流，包括有关通信实际问题的演示。能够比目前实用的更快，准确地解决此类现实问题，从而为社会带来广泛的利益。该项目的活动包括关注传统上不利的背景的学生，以及用于传播和互动的研讨会。更确切地说，该团队表明，以前已使用量子/光学方案以及振动剂网络实现的Ising机器也可以使用基于CMOS的诸如CMOS latches latches latches latches latches latche元素实现。与以前的Ising机器方法不同，这些方法是大型，昂贵且不适合低成本质量生产的方法，而拟议的方法是一种纯粹的经典方案，不依赖量子现象或新颖的纳米devices。使用常规的CMOS电子设备具有许多优势：可伸缩性/微型可辨认力（即，在物理上很小的系统中的旋转非常大），完善的设计过程和工具，这些过程和工具基本上可以保证首次工作硬件，非常低的功率操作，与控制和I/O的无缝集成以及I/O逻辑，可通过标准交易量使用USB质量生产，以及诸如USB质量质量和低成本的质量质量和低成本的质量。另一个关键的潜在优势源于LIM的连续/模拟性质（与纯数字算法形成对比）。研究人员正在在硬件中开发LIM理论和计算，并在基准中实施它，并在基准的问题上以及与沟通相关的问题的形式进行证明。这项奖项反映了NSF的法定任务，并通过使用基金会的知识分子优点和更广泛的影响审查标准来通过评估来诚实地支持。