Collaborative Research: Integrated Sensing and Normally-off Computing for Edge Imaging Systems

合作研究：边缘成像系统的集成传感和常断计算

基本信息

批准号：
2216773
负责人：
Arman Roohi
金额：
$ 26.07万
依托单位：
University of Nebraska-Lincoln
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2022
资助国家：
美国
起止时间：
2022-08-01 至 2025-07-31
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2216773&HistoricalAwards=false
关键词：
Collaborative Research Integrated Sensing Normally

项目摘要

Internet of Things (IoT) devices are projected to exceed $1000B by 2025, with a web of interconnection projected to comprise approximately 75+ billion IoT devices. The large number of IoTs consists of sensory imaging systems that enable massive data collection from the environment and people. However, considerable portions of the captured sensory data are redundant and unstructured. Data conversion of such large raw data, storing in volatile memories, transmission, and computation in on-/off-chip processors, impose high energy consumption, latency, and a memory bottleneck at the edge. Moreover, because renewing batteries for IoT devices is very costly and sometimes impracticable, energy harvesting devices with ambient energy sources and low maintenance have impacted a wide range of IoT applications such as wearable devices, smart cities, and the intelligent industry. This project explores and designs new high-speed, low-power, and normally-off computing architectures for resource-limited sensory nodes by exploiting cross-layer post-CMOS approaches to overcome these issues. Successful completion of this research will have benefits to a variety of critical application domains, including medical monitoring, industrial and/or environmental sensors. This project will make a strong effort on developing undergraduate and graduate course modules, propagating transportable and open-source models, and broadening STEM participation through publications/presentations at conferences for knowledge dissemination.This project will follow two main research thrusts. Thrust 1 designs and analyzes a Processing-In-Sensor Unit (PISU) co-integrating always-on sensing and processing capabilities in conjunction with a Processing-Near-Sensor Unit (PNSU). The hybrid platform will feature real-time programmable granularity-configurable arithmetic operations to balance the accuracy, speed, and power-efficiency trade-offs under both continuous and energy-harvesting-powered imaging scenarios. This platform will enable resource-limited edge devices to locally perform data and compute-intensive applications such as machine learning tasks while consuming much less power than present state-of-the-art technology. The power profile of ambient energy sources imposes fundamental constraints on processing stability and duration. To achieve high sensing and computation parallelism under unstable power supply conditions, Intermittent-Robust Integrated Sensing Computation (IRISC) will be designed. During power failure, IRISC stores intermediate values in non-volatile spin-based devices, which will ensure uninterrupted operations. To meet the hardware constraints and mitigate the high write power of spin-based devices, they will be selectively and efficiently inserted within the datapaths through a novel NV-clustering methodology to create corresponding intermittent-robust IP cores that realize intermittent computation with lower power consumption while maintaining middleware coherence. This cross-layer devices-to-system research approach will be assessed by developing a comprehensive evaluation framework, a transportable energy-harvested computational workload suite, and FPGA-MRAM-based emulation platforms for IRISC.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.

到 2025 年，物联网 (IoT) 设备预计将超过 1000B 美元，互连网络预计将包含约 75 亿多个物联网设备。大量物联网由传感成像系统组成，可以从环境和人员中收集大量数据。然而，捕获的传感数据的相当一部分是冗余且非结构化的。如此大的原始数据的数据转换、存储在易失性存储器中、传输以及片上/片外处理器中的计算，会在边缘造成高能耗、延迟和内存瓶颈。此外，由于物联网设备的电池更新成本非常高，有时甚至不切实际，因此具有环境能源和低维护成本的能量收集设备已经影响了广泛的物联网应用，例如可穿戴设备、智慧城市和智能工业。该项目通过利用跨层后 CMOS 方法来克服这些问题，为资源有限的传感节点探索和设计新的高速、低功耗和常断计算架构。这项研究的成功完成将为各种关键应用领域带来好处，包括医疗监测、工业和/或环境传感器。该项目将大力开发本科生和研究生课程模块，传播可移植和开源模型，并通过在知识传播会议上发表出版物/演讲来扩大 STEM 参与。该项目将遵循两个主要研究方向。 Thrust 1 设计并分析了传感器内处理单元 (PISU)，该单元将始终在线的传感和处理功能与近传感器处理单元 (PNSU) 共同集成。该混合平台将采用实时可编程粒度可配置算术运算，以平衡连续成像和能量收集供电成像场景下的精度、速度和功效权衡。该平台将使资源有限的边缘设备能够在本地执行数据和计算密集型应用程序（例如机器学习任务），同时消耗比当前最先进技术少得多的功耗。环境能源的功率分布对处理稳定性和持续时间施加了基本限制。为了在不稳定的电源条件下实现高传感和计算并行性，将设计间歇鲁棒集成传感计算（IRISC）。在电源故障期间，IRISC 将中间值存储在非易失性基于自旋的设备中，这将确保不间断的操作。为了满足硬件限制并减轻基于自旋的设备的高写入功率，它们将通过一种新颖的NV集群方法有选择地、高效地插入到数据路径中，以创建相应的间歇性鲁棒IP核，以较低的功耗实现间歇性计算同时保持中间件的一致性。这种跨层设备到系统的研究方法将通过开发综合评估框架、可传输的能量收集计算工作负载套件以及基于 FPGA-MRAM 的 IRISC 仿真平台来进行评估。该奖项反映了 NSF 的法定使命，并已被通过使用基金会的智力优点和更广泛的影响审查标准进行评估，认为值得支持。

项目成果

期刊论文数量（10）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

LT-PIM: An LUT-Based Processing-in-DRAM Architecture With RowHammer Self-Tracking

LT-PIM：具有 RowHammer 自跟踪功能的基于 LUT 的 DRAM 处理架构

DOI：
10.1109/lca.2022.3220084
发表时间：
2022-07
期刊：
IEEE Computer Architecture Letters
影响因子：
2.3
作者：
Zhou, Ranyang;Tabrizchi, Sepehr;Roohi, Arman;Angizi, Shaahin
通讯作者：
Angizi, Shaahin

MR-PIPA: An Integrated Multilevel RRAM (HfO x )-Based Processing-In-Pixel Accelerator

MR-PIPA：基于集成多级 RRAM (HfO x ) 的像素内处理加速器

DOI：
10.1109/jxcdc.2022.3210509
发表时间：
2022-12
期刊：
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
影响因子：
2.4
作者：
Abedin, Minhaz;Roohi, Arman;Liehr, Maximilian;Cady, Nathaniel;Angizi, Shaahin
通讯作者：
Angizi, Shaahin

AppCiP: Energy-Efficient Approximate Convolution-in-Pixel Scheme for Neural Network Acceleration

AppCiP：用于神经网络加速的节能近似像素卷积方案