CSR: Small: ARTEMIS: Algorithm-Hardware Co-Design for Efficient Machine Learning Systems

CSR：小型：ARTEMIS：高效机器学习系统的算法硬件协同设计

• 批准号: 1815780
• 负责人: Gauri Joshi
• 金额: $ 50万
• 依托单位: Carnegie-Mellon University
• 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 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1815780&HistoricalAwards=false
• 关键词: CSR; Small; ARTEMIS; Algorithm; Hardware

With the increased popularity of machine learning algorithms deployed on a variety of hardware systems, the problem of identifying the best model among numerous possible configurations has drawn significant attention. The problem is compounded by the need to select the right platform to run these applications, under given power or latency constraints. This "hardware wall" forces machine learning service providers to constantly redesign the underlying hardware fabric to satisfy certain constraints. This project develops tools for automatic and efficient co-design of machine learning algorithms and hardware platforms that will result in significant cost and time-to-market reduction for machine learning systems.The project introduces efficient meta-learning for machine learning systems and algorithm-hardware platform co-design. Specifically, the project will develop meta-learning algorithms for the optimization of machine learning models under system hardware constraints and formulate the hardware design of efficient machine learning systems as a machine learning problem itself, that can be effectively solved by meta-learning optimization algorithms. Finally, the project will develop multi-objective algorithms for the co-design of machine learning applications and hardware platforms they need to run on, and exploit domain knowledge from hardware engineering and design schemes to substantially accelerate hardware-aware model optimization.The results of the project seek to change the landscape of modeling, optimization, and design methodologies for efficient machine learning systems. Furthermore, the work aims to have an important educational and mentoring component by potentially changing how engineers are trained in a multidisciplinary fashion for dealing with next generation technological advances in general, and the problem of efficiently and intelligently co-designing machine learning algorithms and the hardware platforms they are running on, in particular. The project will involve a diverse graduate and undergraduate trainee population, while expanding the project's outreach to high-school and middle-school students.The data, code, results, and simulators developed in this project will be made available publicly throughout the duration of the project and for at least four years after the end of the project. The location of the repository is on the website of Carnegie Mellon University's Energy Aware Computing group (www.ece.cmu.edu/~enyac).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.

随着在各种硬件系统上部署的机器学习算法的普及越来越多，在许多可能的配置中识别最佳模型的问题引起了极大的关注。在给定功率或延迟约束下，选择正确的平台来运行这些应用程序的需要，问题更加复杂。这种“硬件墙”迫使机器学习服务提供商不断重新设计基础硬件面料以满足某些约束。该项目开发了用于机器学习算法和硬件平台的自动和高效共同设计的工具，这些工具将导致机器学习系统的大幅成本和市场缩短的成本和时间缩短。该项目介绍了机器学习系统和算法 - 硬件平台的高效元学习。具体而言，该项目将开发用于在系统硬件约束下优化机器学习模型的元学习算法，并将有效的机器学习系统的硬件设计作为机器学习问题本身，可以通过元学习优化算法有效地解决。最后，该项目将开发多目标算法，以针对他们需要运行的机器学习应用程序和硬件平台的共同设计，并利用域知识从硬件工程和设计方案来实质上加速了硬件吸引模型优化。项目的结果旨在改变建模，优化方法和设计机器系统的模型景观。此外，这项工作的目的是通过有可能改变工程师的多学科培训，以应对一般的下一代技术进步，并有效，智能地共同设计机器学习算法及其运行的硬件平台，以应对下一代技术进步的问题。该项目将涉及多样化的毕业生和本科学员人口，同时将项目的宣传扩展到高中生和中学生。该项目中开发的数据，代码，结果和模拟器将在该项目的整个过程中公开提供，并在该项目结束后至少四年。存储库的位置位于卡内基·梅隆大学的能源意识计算集团（www.ece.cmu.edu/~enyac)网站上。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子优点和更广泛的影响审查标准来通过评估来通过评估来获得支持的。

项目成果

Designing Adaptive Neural Networks for Energy-Constrained Image Classification

• DOI: 10.1145/3240765.3240796
• 发表时间: 2018-08
• 期刊: 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
• 作者: Dimitrios Stamoulis;Ting-Wu Chin;Anand P. Krishnan;Haocheng Fang;S. Sajja;Mitchell Bognar;Diana Marculescu

DeepNVM++: Cross-Layer Modeling and Optimization Framework of Nonvolatile Memories for Deep Learning

• DOI: 10.1109/tcad.2021.3127148
• 发表时间: 2020-12
• 期刊: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
• 影响因子: 2.9
• 作者: A. Inci;Mehmet Meric Isgenc;Diana Marculescu

Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization

• DOI: 10.1109/jstsp.2020.2971421
• 发表时间: 2019-07
• 期刊: IEEE Journal of Selected Topics in Signal Processing
• 影响因子: 7.5
• 作者: Dimitrios Stamoulis;Ruizhou Ding;Di Wang;Dimitrios Lymberopoulos;B. Priyantha;Jie Liu;Diana Marculescu

Single-Path NAS: Device-Aware Efficient ConvNet Design

• 发表时间: 2019-05
• 期刊: ArXiv
• 作者: Dimitrios Stamoulis;Ruizhou Ding;Di Wang;Dimitrios Lymberopoulos;B. Priyantha;Jie Liu-;Diana Marculescu

Single-Path NAS: Designing Hardware-Ecient ConvNets in less than 4 Hours

单路径 NAS：在 4 小时内设计硬件高效的卷积网络

• 发表时间: 2019
• 期刊: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
• 作者: Stamoulis, Dimitrios;Ding, Ruizhou;Wang, Di;Lymberopoulos, Dimitrios;Priyantha, Bodhi;Liu, Jie;Marculescu, Diana
• 通讯作者: Marculescu, Diana