CAREER: Efficient, Dynamic, Robust, and On-Device Continual Deep Learning with Non-Volatile Memory based In-Memory Computing System

该奖项的全部或部分资金来自《2021年美国救援计划法案》(公法117-2)。在过去的几十年里，为大数据处理开发高性能和高能效的计算解决方案一直存在巨大的挑战。同时，由于人工智能(AI)特别是深度神经网络(DNN)的蓬勃发展，这种大数据处理需要高效、智能、快速、动态、健壮和设备上的自适应认知计算。然而，由于硅基半导体器件中众所周知的电源墙、传统冯-诺伊曼计算体系结构中的存储墙以及计算/存储密集型DNN计算算法，这些要求不能被现有的计算解决方案充分满足。该项目旨在通过合作开发混合内存计算(IMC)硬件平台，整合新兴的非易失性电阻存储器(RRAM)和静态随机存取存储器(SRAM)技术的优势，以及融入支持IMC的深度学习算法创新，促进在开发AI-in-Memory计算系统方面的系统性突破。该项目的总体目标是设计、实现和实验验证一种新的混合内存计算系统，该系统针对能效、推理精度、时空动力学、健壮性和在设备学习进行了协同优化，将极大地促进基于人工智能的大数据处理领域，如计算机视觉、自动驾驶、机器人等。该研究还将扩展为一个教育平台，提供一个用户友好的学习框架，并将服务于K-12学生、本科生、研究生、这个项目将为AI-in-Memory计算的新范式提供知识和科学原理和工具，其特点是在能效、速度、动力学、稳健性和设备学习能力方面有显著改进。这个跨层项目横跨从设备、电路和架构到DNN算法探索。首先，将设计、优化和制造一种基于RRAM-SRAM的混合内存计算芯片。其次，基于这一新的计算平台，将开发设备上时空动态神经网络结构，以提供增强的运行时计算配置文件(延迟、资源分配、工作负载、功率预算等)，并提高系统对硬件固有噪声和对抗性噪声注入的鲁棒性。然后，将利用开发的计算平台来研究高效的设备学习方法。在最后的推力中，将开发一个端到端的DNN培训、优化、映射和评估CAD工具，集成开发的硬件平台和算法创新，优化软硬件协同设计，以实现用户定义的延迟、能效、动态、准确性、健壮性、设备自适应等多目标。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).Over past decades, there have existed grand challenges in developing high performance and energy-efficient computing solutions for big-data processing. Meanwhile, owing to the boom in artificial intelligence (AI), especially Deep Neural Networks (DNNs), such big-data processing requires efficient, intelligent, fast, dynamic, robust, and on-device adaptive cognitive computing. However, those requirements are not sufficiently satisfied by existing computing solutions due to the well-known power wall in silicon-based semiconductor devices, the memory wall in traditional Von-Neuman computing architectures, and computation-/memory-intensive DNN computing algorithms. This project aims to foster a systematic breakthrough in developing AI-in-Memory computing systems, through collaboratively developing ahybrid in-memory computing (IMC) hardware platform integrating the benefits of emerging non-volatile resistive memory (RRAM) and Static Random Access Memory (SRAM) technologies, as well as incorporating IMC-aware deep-learning algorithm innovations. The overarching goal of this project is to design, implement, and experimentally validate a new hybrid in-memory computing system that is collaboratively optimized for energy efficiency, inference accuracy, spatiotemporal dynamics, robustness, and on-device learning, which will greatly advance AI-based big-data processing fields such as computer vision, autonomous driving, robotics, etc. The research will also be extended into an educational platform, providing a user-friendly learning framework, and will serve the educational objectives for K-12 students, undergraduate, graduate, and under-represented students.This project will advance knowledge and produce scientific principles and tools for a new paradigm of AI-in-Memory computing featuring significant improvements in energy efficiency, speed, dynamics, robustness, and on-device learning capability. This cross-layer project spans from device, circuit, and architecture to DNN algorithm exploration. First, a hybrid RRAM-SRAM based in-memory computing chip will be designed, optimized, and fabricated. Second, based on this new computing platform, the on-device spatiotemporal dynamic neural network structure will be developed to provide an enhanced run-time computing profile (latency, resource allocation, working load, power budget, etc.), as well as improve the robustness of the system against hardware intrinsic and adversarial noise injection. Then, efficient on-device learning methodologies with the developed computing platform will be investigated. In the last thrust, an end-to-end DNN training, optimization, mapping, and evaluation CAD tool will be developed that integrates the developed hardware platform and algorithm innovations, for optimizing the software and hardware co-designs to achieve the user-defined multi-objectives in latency, energy efficiency, dynamics, accuracy, robustness, on-device adaption, etc.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.