SHF: Medium: Collaborative Research: Predictive Modeling for Next-generation Heterogeneous System Design

SHF：媒介：协作研究：下一代异构系统设计的预测建模

• 批准号: 1763848
• 负责人: Andreas Gerstlauer
• 金额: $ 67.94万
• 依托单位: University of Texas at Austin
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-10-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1763848&HistoricalAwards=false
• 关键词: SHF; Medium; Collaborative; Research; Predictive

With semiconductor scaling reaching physical limits, performance and power consumption are ever more critical aspects in the design of emerging computer systems. Fast and accurate design models and tools are critical to support future computer system designers in evaluating design options before they can be built. Traditional simulation-based or analytical models are often too slow or inaccurate to effectively support design processes. This project instead develops novel machine learning-based, predictive methodologies to rapidly estimate the performance and power consumption of future generation products at early design stages using observations obtained on commercially available silicon today. Such techniques will allow efficient design cycles ensuring that the next-generation computing infrastructure meets the needs and expectations of consumers and continues to meet them over the product lifecycle. Along with research activities, course material on predictive modeling will be integrated into the university courses taught by the investigators, technology will be transferred to industrial partners through training and tutorials, and tools and models developed in this project will be released as open source software. In addition to training of graduate students, emphasis will be paid to undergraduate student training, towards including federally recognized under-represented groups, training of STEM teachers, and to run summer code camps to increase access for middle school and high school students. This project specifically investigates use of advanced machine learning techniques for prediction of power and performance of any machine based on hardware-dependent and independent application characteristics obtained by running on any existing other machine, focusing on large-scale data center and accelerator technologies, namely multi-core CPUs, GPUs and FPGAs. Specific research tasks include the investigation of: (1) fast and accurate models for system designers and system programmers to perform rapid, early hardware and software design space exploration; (2) fast online prediction models that can be integrated into modern operating systems and virtual machine; and (3) fast yet accurate model training procedures that can create new predictive models while applications run. This research is expected to also allow semiconductor companies to better understand the scenarios under which predictive modeling is sufficiently accurate to be deployed during an industrial design process.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.

随着半导体缩放达到物理极限，性能和功耗在新兴计算机系统的设计中变得越来越重要。快速准确的设计模型和工具对于支持未来的计算机系统设计师在设计方案构建之前对其进行评估至关重要。传统的基于仿真或分析的模型通常太慢或不准确，无法有效地支持设计过程。该项目开发了一种基于机器学习的新型预测方法，利用目前在市售硅上获得的观察结果，在早期设计阶段快速估计下一代产品的性能和功耗。这些技术将允许有效的设计周期，确保下一代计算基础设施满足消费者的需求和期望，并在产品生命周期中继续满足它们。随着研究活动的开展，预测建模的课程材料将被整合到研究人员教授的大学课程中，技术将通过培训和教程转移给工业合作伙伴，该项目开发的工具和模型将作为开源软件发布。除了对研究生的培训外，还将重点放在本科生的培训上，包括联邦政府认可的代表性不足的群体，STEM教师的培训，以及举办暑期代码训练营，以增加初中生和高中生的机会。该项目专门研究使用先进的机器学习技术来预测任何机器的功率和性能，该技术基于运行在任何现有机器上获得的硬件依赖和独立应用程序特征，重点关注大规模数据中心和加速器技术，即多核cpu， gpu和fpga。具体的研究任务包括：(1)为系统设计人员和系统程序员进行快速、早期的硬件和软件设计空间探索提供快速、准确的模型；(2)可集成到现代操作系统和虚拟机的快速在线预测模型；(3)快速而准确的模型训练程序，可以在应用程序运行时创建新的预测模型。预计这项研究还将使半导体公司更好地了解在工业设计过程中部署预测建模足够准确的情况。该奖项反映了美国国家科学基金会的法定使命，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

Hardware-aware 3D Model Workload Selection and Characterization for Graphics and ML Applications

• DOI: 10.1109/isqed54688.2022.9806296
• 发表时间: 2022-04
• 期刊: 2022 23rd International Symposium on Quality Electronic Design (ISQED)
• 作者: Ruihao Li;Aman Arora;Sikan Li;Qinzhe Wu;L. John

Virtual-Link: A Scalable Multi-Producer Multi-Consumer Message Queue Architecture for Cross-Core Communication

• DOI: 10.1109/ipdps49936.2021.00027
• 发表时间: 2020-12
• 期刊: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)
• 作者: Qinzhe Wu;J. Beard;Ashen Ekanayake;A. Gerstlauer;L. John

CoMeFa: Deploying Compute-in-Memory on FPGAs for Deep Learning Acceleration

• DOI: 10.1145/3603504
• 发表时间: 2023-06
• 期刊: ACM Transactions on Reconfigurable Technology and Systems
• 影响因子: 2.3
• 作者: Aman Arora;Atharva Bhamburkar;Aatman Borda;T. Anand;Rishabh Sehgal;Bagus Hanindhito;P. Gaillardon;J. Kulkarni;L. John

HLSDataset: Open-Source Dataset for ML-Assisted FPGA Design using High Level Synthesis

HLSDataset：使用高级综合进行 ML 辅助 FPGA 设计的开源数据集

• DOI: 10.1109/asap57973.2023.00040
• 发表时间: 2023
• 期刊: Architectures and Processors
• 作者: Wei, Zhigang;Arora, Aman;Li, Ruihao;John, Lizy
• 通讯作者: John, Lizy

Lightweight ML-based Runtime Prefetcher Selection on Many-core Platforms

多核平台上基于 ML 的轻量级运行时预取器选择

• 发表时间: 2023
• 期刊: Workshop on Machine Learning for Computer Architecture and Systems
• 作者: Alcorta, Erika S.;Yadwadkar, Neeraja J.;Gerstlauer, Andreas
• 通讯作者: Gerstlauer, Andreas