课题基金 / 基金详情

Expeditions: DISCoVER: Design and Integration of Superconducting Computation for Ventures beyond Exascale Realization

Expeditions: DISCoVER: Design and Integration of Superconducting Computation for Ventures beyond Exascale Realization
探险:DISCoVER:超导计算的设计和集成,为超越百亿亿级实现的企业提供超导计算
批准号:
2124453
负责人:
Massoud Pedram
金额:
$1499.99万
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2022
资助国家:
美国
项目状态:
未结题
起止时间:
2022-04-01 至 2029-03-31

项目摘要

项目成果

Massoud Pedram的其他基金

相似基金

相关文献

中文摘要
翻译
近几十年来,cmos的成功让几乎所有其他固态设备的创新黯然失色。随着基本的cmos扩展限制近在眼前,探索新兴颠覆性计算技术的时机现在已经成熟。发现探险队将探索新型超导电子学,作为一种可行的后CMOS计算技术。超导体电子学可以在规模上提供超高的性能和能效。向超导电子学的潜在转变将是革命性的,类似于20世纪70年代仅支持NMOS的逻辑向CMOS逻辑的转变。虽然能效是向cmos过渡的最初驱动力,但cmos的好处远远超出了能效的提高,还包括超大规模集成和更可靠的电路。类似地,这次发现探险将为集成电子学、可持续大规模计算和加速机器学习方面的开创性创新铺平道路。Discovery将使计算模式能够促进气候变化影响的建模、地下地质资源的探测、加强针对个性化药物和医疗保健的药物设计,以及创新智能材料和基础设施的开发。DISCOVE将帮助确保美国作为技术世界领先者的卓越地位,并指导未来的硬件和芯片制造投资。DISCOVE团队将设计并展示一种低温计算核心的超导系统(SuperSoCC),这是一种由超导电子元件制成的艺术品,能够在与cmos相同的性能下将能效提高100倍。该团队在超导材料和器件、可扩展的电路和架构、降低设计复杂性的先进设计自动化工具以及支持编译器和运行时系统方面的创新使系统演示成为可能。通过这一多方面的计划,探索探险队将有条不紊地降低与物理扩展、集成复杂性、工具支持和与室温电子设备接口相关的技术转让障碍。通过课程创新,Discovery将为新一代工程师和企业家提供动力,他们将把超导带入计算的主流。位于南加州大学的实践超导实验室,加上K-12合作伙伴机构的拓展,将使Discovery团队能够为未来几代员工带来计算硬件的兴奋。通过与南加州大学i-Corp和行业附属公司的创新合作,Discovery准备开启超导技术的力量,以应对关键的社会挑战。发现探险队由南加州大学领导,包括来自奥本大学、康奈尔大学、东北大学、西北大学、罗切斯特大学和横滨国立大学(作为国际学术合作伙伴)的教职员工和研究人员。这一奖项反映了NSF的法定使命,并通过使用基金会的智力价值和更广泛的影响审查标准进行评估,被认为值得支持。
英文摘要
The success of CMOS has overshadowed nearly all other solid-state device innovations over recent decades. With fundamental CMOS scaling limits close in sight, time is now ripe for an expedition to explore emerging disruptive computing technologies. The DISCoVER Expedition will explore novel superconductor electronics as a viable post-CMOS computing technology. Superconductor electronics can deliver ultra-high performance and energy efficiency at scale. The potential transition to superconductor electronics will be revolutionary, analogous to the transition of NMOS-only logic to CMOS logic in the 1970s. While energy efficiency was the initial driver for the transition to CMOS, the benefits of CMOS went far beyond energy-efficiency gains and included ultra-scale integration and more reliable circuits. In a similar vein, this DISCoVER Expedition will pave the way for seminal innovations in integrated electronics, sustainable exa-scale computing, and acceleration of machine learning. DISCoVER will enable computing paradigms that can facilitate modeling of climate-change effects, detection of underground geological resources, enhancement of pharmaceutical drug design for personalized medicines and healthcare, and development of innovative smart materials and infrastructure. DISCoVER will help ensure the preeminence of the US as a technological world leader and guide future hardware and chip-manufacturing investments.The DISCoVER team will design and demonstrate a superconductive system of cryogenic computing cores (SuperSoCC), an artifact built from superconductive electronic components capable of yielding 100x improved energy efficiency at the same performance as CMOS. The system demonstration pursuit is enabled by the team’s innovations in superconducting materials and devices, circuits and architectures that scale, advanced design-automation tools for easing design complexity, and supporting compilers and runtime systems. Through this multi-faceted program, the DISCoVER Expedition will methodically lower the technology-transfer barriers related to physical scaling, integration complexity, tool support, and interfacing to room-temperature electronics. Through its curriculum innovations, DISCoVER will empower a new generation of engineers and entrepreneurs who will bring superconducting to the mainstream of computing. The hands-on superconducting labs housed at USC, combined with K-12 outreach across partner institutions, will allow the DISCoVER team to bring the excitement of computing hardware to future generations of the workforce. With innovative collaboration with USC’s I-Corp and industry affiliates, DISCoVER is poised to open the power of superconducting technology for tackling critical societal challenges. The DISCoVER Expedition is led by the University of Southern California and includes faculty and researchers from Auburn, Cornell, Northeastern, Northwestern, Rochester, and Yokohama National University (as an international academic partner).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.
期刊论文(6)
专著(0)
科研奖励(0)
会议论文
SFQ/DQFP Interface Circuits
SFQ/DQFP 接口电路
DOI: 10.1109/tasc.2023.3264575
发表时间: 2023
期刊: IEEE Transactions on Applied Superconductivity
影响因子: 1.8
作者: [Jabbari, Tahereh, Friedman, Eby G.]
通讯作者: Friedman, Eby G.
High-density superconductive logic circuits utilizing 0 and π Josephson junctions
利用 0 和 Ω 约瑟夫森结的高密度超导逻辑电路
DOI: 10.1088/2631-8695/ad27f5
发表时间: 2024
期刊: Engineering Research Express
影响因子: 1.7
作者: [Razmkhah, Sasan, Pedram, Massoud]
通讯作者: Pedram, Massoud
Stripline Topology for Flux Mitigation
用于缓解通量的带状线拓扑
DOI: 10.1109/tasc.2023.3249641
发表时间: 2023
期刊: IEEE Transactions on Applied Superconductivity
影响因子: 1.8
作者: [Jabbari, Tahereh, Friedman, Eby G.]
通讯作者: Friedman, Eby G.
All-JJ Logic Based on Bistable JJs
基于双稳态 JJ 的全 JJ 逻辑
DOI: 10.1109/tasc.2023.3260774
发表时间: 2023
期刊: IEEE Transactions on Applied Superconductivity
影响因子: 1.8
作者: [Jabbari, Tahereh, Bocko, Mark, Friedman, Eby G.]
通讯作者: Friedman, Eby G.
共 6 条
    Collaborative Research: Workshop Series on Sustainable Computing
    • 批准号:
      2126020
    • 项目类别:
      Standard Grant
    • 资助金额:
      $0.8万
    • 财政年份:
      2021
    • 负责人:
      Massoud Pedram
    • 依托单位:
    FET: SHF: Small: Collaborative: Advanced Circuits, Architectures and Design Automation Technologies for Energy-efficient Single Flux Quantum Logic
    • 批准号:
      2009064
    • 项目类别:
      Standard Grant
    • 资助金额:
      $30.0万
    • 财政年份:
      2020
    • 负责人:
      Massoud Pedram
    • 依托单位:
    SHF: Medium: Collaborative Research: ADMM-NN: A Unified Software/Hardware Framework of DNN Computation and Storage Reduction Using ADMM
    • 批准号:
      1901440
    • 项目类别:
      Continuing Grant
    • 资助金额:
      $45.0万
    • 财政年份:
      2019
    • 负责人:
      Massoud Pedram
    • 依托单位:
    SHF: Small: Computer Aided Design Methodologies and Tools for Superconducting Single Flux Quantum Technology
    • 批准号:
      1619473
    • 项目类别:
      Standard Grant
    • 资助金额:
      $45.0万
    • 财政年份:
      2016
    • 负责人:
      Massoud Pedram
    • 依托单位:
    海外基金