Collaborative Research:SHF:Medium:Machine Learning on the Edge for Real-Time Microsecond State Estimation of High-Rate Dynamic Events

合作研究：SHF：Medium：边缘机器学习，用于高速动态事件的实时微秒状态估计

• 批准号: 1955820
• 负责人: David Andrews
• 金额: $ 50.91万
• 依托单位: University of Arkansas
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-01 至 2025-07-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1955820&HistoricalAwards=false
• 关键词: Collaborative; Research; SHF; Medium; Machine

Computer control of dynamic systems from the manufacturing, robotics, and aviation fields traditionally operate on timescales of 10s or 100s of milliseconds. For example, an avionics system traveling at 1000 kilometers per hour and operating at 10 milliseconds per control decision will move three meters in the time allocated to each control decision. However, emerging hypersonic, space, and military systems require active control while operating at extreme velocities or while being subjected to accelerations or decelerations caused by explosions or high-speed collisions. These applications require control at timescales on the order of microseconds. Making control decisions for such systems often requires that the controller estimate the state of the system from indirect measurements such as vibration. Traditional methods for state prediction are based on first principles using finite element analysis (FEA), whose execution time scales as a square of the number of elements. This makes it impractical to evaluate FEA models at microsecond timescales. Models derived from machine learning can estimate the state of the system based on pre-curated datasets and require less workload as compared to an equivalent FEA model. Such models, when combined with domain-specific processors, could provide equivalent accuracy with higher throughput than FEA models, making microsecond-scale state modeling possible. However, there are currently no suitable development methodologies for systematic generation of machine-learning models at such extreme performance constraints. The objective of this research is to develop a structural model compiler that meets a given accuracy constraint, as well as a corresponding overlay generator on which the generated model meets a given microsecond-scale latency constraint. This research will advance the fundamental knowledge and skills required for the real-time decision-making and control of active structures that experience high-rate dynamic events.This project addresses two distinct but synergistic problems: (1) technologies to enable real-time decision-making and control of active structures that experience dynamic events at the microsecond timescale and (2) development of tools for optimization and synthesis of domain-specific processors for trained models. Recent academic and industrial work focusing on development of specialized architectures for evaluating Long Short Term Memory (LSTM) models generally yield “one-off” designs tuned to a specific Field Programmable Gate Array (FPGA)--often a server class FPGA--and have rigid, “baked in” design decisions. This makes it difficult to compare alternative or competing optimization techniques for a desired target FPGA platform. To solve this, this project is developing a generalized programmable processor architecture that incorporates a repertoire of optional features designed to accelerate specific aspects of LSTMs and support associated model optimizations. The architecture is both programmable and customizable, allowing it to serve as a common platform for evaluating different approaches for accelerating LSTM models. Concurrently, the investigators are developing a set of benchmark datasets for structural state estimation with accuracy and performance requirements. The project is also developing useful artifacts for subsequent research in edge-based machine learning, including a method for comparing different LSTM model-pruning and compression approaches and comparing different microarchitecture designs. Code and hardware designs developed from this project are open-source.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.

来自制造业、机器人和航空领域的动态系统的计算机控制传统上在10毫秒或100毫秒的时间尺度上操作。 例如，一个以每小时1000公里的速度运行的航空电子系统，每个控制决策的工作时间为10毫秒，在分配给每个控制决策的时间内，该系统将移动3米。 然而，新兴的高超音速，空间和军事系统需要主动控制，同时以极高的速度运行，或受到爆炸或高速碰撞引起的加速或减速。 这些应用需要以微秒量级的时间尺度进行控制。 为这样的系统做出控制决策通常需要控制器根据诸如振动的间接测量来估计系统的状态。 用于状态预测的传统方法基于使用有限元分析（FEA）的第一原理，其执行时间按元素数量的平方缩放。 这使得在微秒时间尺度上评估FEA模型变得不切实际。 从机器学习中导出的模型可以基于预先策划的数据集来估计系统的状态，并且与等效的FEA模型相比，需要更少的工作量。当与特定于域的处理器结合时，这样的模型可以提供与FEA模型相同的精度和更高的吞吐量，从而使微秒级的状态建模成为可能。 然而，目前还没有合适的开发方法来在这种极端的性能约束下系统地生成机器学习模型。 本研究的目的是开发一个结构模型编译器，满足给定的精度约束，以及相应的覆盖生成器上生成的模型满足给定的微秒级的延迟约束。 本研究将推进经历高速率动态事件的主动结构的实时决策和控制所需的基本知识和技能。本项目解决两个不同但协同的问题：（1）能够对在微秒时间尺度上经历动态事件的主动结构进行实时决策和控制的技术，以及（2）开发用于优化和综合域的工具，用于训练模型的特定处理器。 最近的学术和工业工作专注于开发用于评估长短期存储器（LSTM）模型的专用架构，通常会产生针对特定现场可编程门阵列（FPGA）（通常是服务器级FPGA）的“一次性”设计，并且具有严格的“内置”设计决策。 这使得很难比较用于所需目标FPGA平台的替代或竞争优化技术。为了解决这个问题，该项目正在开发一种通用的可编程处理器架构，该架构包含一系列可选功能，旨在加速LSTM的特定方面并支持相关的模型优化。 该架构是可编程和可定制的，使其能够作为评估加速LSTM模型的不同方法的通用平台。同时，研究人员正在开发一套基准数据集的精度和性能要求的结构状态估计。该项目还为基于边缘的机器学习的后续研究开发了有用的工件，包括一种比较不同LSTM模型修剪和压缩方法以及比较不同微架构设计的方法。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Making BRAMs Compute: Creating Scalable Computational Memory Fabric Overlays

让 BRAM 进行计算：创建可扩展的计算内存结构覆盖

• 发表时间: 2023
• 期刊: Proceedings of the International Symposium on Field-Programmable Custom Computing Machines
• 作者: M. Kabir;J. Hollis;A. Panahi;J. Bakos;M. Huang;D. Andrews
• 通讯作者: D. Andrews

A Customizable Domain-Specific Memory-Centric FPGA Overlay for Machine Learning Applications

适用于机器学习应用的可定制、特定领域、以内存为中心的 FPGA 叠加

• 发表时间: 2021
• 期刊: The International Conference on Field-Programmable Logic and Applications (FPL
• 作者: Atiyehsadat Panahi, Suhail Basalama