课题基金 / 基金详情

Switching Techniques and Architectures for Performance-Adaptive, Power-Aware Hybrid Opto-Electronic Interconnects

Switching Techniques and Architectures for Performance-Adaptive, Power-Aware Hybrid Opto-Electronic Interconnects
性能自适应、功耗感知混合光电互连的开关技术和架构
批准号:
0725765
负责人:
Ahmed Louri
金额:
$30.0万
依托单位:
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2007
资助国家:
美国
项目状态:
已结题
起止时间:
2007-09-15 至 2014-08-31

项目摘要

项目成果

Ahmed Louri的其他基金

相似基金

相关文献

中文摘要
翻译
点击翻译按钮获取中文摘要
英文摘要
Switching Techniques and Architectures for Performance-Adaptive, Power-Aware Hybrid Opto-Electronic InterconnectsAhmed Louri, University of Arizona0725765Intellectual Merits: To address the performance and power requirements of future interconnects for High Performance Computing (HPC) systems, this research proposes to exploit the recent significant advances in optical device technology to develop new bandwidth-reconfigurable and power-efficient photonic switching techniques, reliable interconnect architectures, and efficient reconfiguration control management strategies. These switching techniques, interconnect architectures, and management strategies will be seamlessly integrated with current HPC systems. This will enable HPC architectures to dynamically adapt to communication traffic patterns and re-allocate bandwidth at run-time. Power consumption will also be monitored and dynamically managed to optimize its use. Reliability and scalability will be addressed through the selection of appropriate optical devices, effective use of dynamic bandwidth and power management techniques, and innovative interconnect topologies. On the technology side, this research explores both active and passive optical technology design space. For passive technology, we propose to extend the switching capabilities of arrayed waveguide gratings (AWGs) to implement dynamic reconfiguration. For active technology, we propose the use of silicon based optical ring resonators, which have a small footprint, reduced power consumption, and high bandwidth characteristics, appropriate for HPC systems. Broader Impact: The success of this research is likely to have a significant impact on the design of next generation HPC and communication systems. The proposed research will provide novel solutions to fundamental communication problems facing future HPC systems and will make significant advances in understanding the interplay between the performance and power consumption. Additionally, it will offer valuable insight and solutions to critical design problems in the use of integrated hybrid systems for high-speed computation and communications. It is also likely to spawn new areas of research such as power-aware opto-electronic systems, fault-tolerant opto-electronic networks and systems, and high-speed on-chip optical interconnects. The proposed research will also provide multi-disciplinary training to undergraduate and graduate students by combining device technology, computer architecture, modeling and simulation, and physical demonstration.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Collaborative Research: CSR: Small: Cross-layer learning-based Energy-Efficient and Resilient NoC design for Multicore Systems
  • 批准号:
    2321224
  • 项目类别:
    Standard Grant
  • 资助金额:
    $37.5万
  • 财政年份:
    2023
  • 负责人:
    Ahmed Louri
  • 依托单位:
Collaborative Research: DESC: Type II: Multi-Function Cross-Layer Electro-Optic Fabrics for Reliable and Sustainable Computing Systems
  • 批准号:
    2324644
  • 项目类别:
    Standard Grant
  • 资助金额:
    $100.0万
  • 财政年份:
    2023
  • 负责人:
    Ahmed Louri
  • 依托单位:
Collaborative Research: SHF: Medium: EPIC: Exploiting Photonic Interconnects for Resilient Data Communication and Acceleration in Energy-Efficient Chiplet-based Architectures
  • 批准号:
    2311543
  • 项目类别:
    Continuing Grant
  • 资助金额:
    $60.0万
  • 财政年份:
    2023
  • 负责人:
    Ahmed Louri
  • 依托单位:
SHF: Small: Holistic Design of High-performance and Energy-efficient Accelerators for Graph Neural Networks
  • 批准号:
    2131946
  • 项目类别:
    Standard Grant
  • 资助金额:
    $50.0万
  • 财政年份:
    2021
  • 负责人:
    Ahmed Louri
  • 依托单位:
国内基金
海外基金
EstimatingLarge Demand Systems with MachineLearning Techniques
  • 批准号:
    --
  • 项目类别:
    外国学者研究基金
  • 资助金额:
    --
  • 批准年份:
    2024
  • 负责人:
    IoshuaAlex
  • 依托单位: