Flexagon: A Multi-dataflow Sparse-Sparse Matrix Multiplication Accelerator for Efficient DNN Processing

Author:

Muñoz-Martínez Francisco1,Garg Raveesh2,Pellauer Michael3,Abellán José L.1,Acacio Manuel E.1,Krishna Tushar2

Affiliation:

1. Universidad de Murcia, Spain

2. Georgia Institute of Technology, USA

3. NVIDIA, USA

Funder

MCIN/AEI/10.13039/5011000110\\33

European Union NextGenerationEU/PRTR

Fundacion Seneca

U.S. Department of Energy (DOE) Office of Science, Advanced Scientific Computing Research program

Publisher

ACM

Reference36 articles.

1. [n. d.]. MAERI code v1. https://github.com/hyoukjun/MAERI. [n. d.]. MAERI code v1. https://github.com/hyoukjun/MAERI.

2. Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices

3. Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv : 1810.04805v2 (2019), May. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv: 1810.04805v2 (2019), May.

4. CoSPARSE: A Software and Hardware Reconfigurable SpMV Framework for Graph Analytics

5. Raveesh Garg , Eric Qin , Francisco Muñoz-Martínez , Robert Guirado , Akshay Jain , Sergi Abadal , José L Abellán , Manuel E Acacio , Eduard Alarcón , Sivasankaran Rajamanickam , and Tushar Krishna . 2022 . Understanding the Design-Space of Sparse/Dense Multiphase GNN dataflows on Spatial Accelerators . In 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS). Raveesh Garg, Eric Qin, Francisco Muñoz-Martínez, Robert Guirado, Akshay Jain, Sergi Abadal, José L Abellán, Manuel E Acacio, Eduard Alarcón, Sivasankaran Rajamanickam, and Tushar Krishna. 2022. Understanding the Design-Space of Sparse/Dense Multiphase GNN dataflows on Spatial Accelerators. In 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS).

Cited by 16 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Mentor: A Memory-Efficient Sparse-dense Matrix Multiplication Accelerator Based on Column-Wise Product;ACM Transactions on Architecture and Code Optimization;2024-08-26

2. SpDCache: Region-Based Reduction Cache for Outer-Product Sparse Matrix Kernels;2024 IEEE 35th International Conference on Application-specific Systems, Architectures and Processors (ASAP);2024-07-24

3. Sparm: A Sparse Matrix Multiplication Accelerator Supporting Multiple Dataflows;2024 IEEE 35th International Conference on Application-specific Systems, Architectures and Processors (ASAP);2024-07-24

4. Designing a Three-Phase Current Relay Protection System for Small Transient Periods of Power Fluctuations with Enhanced Control;2024 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA);2024-05-23

5. Cerberus: Triple Mode Acceleration of Sparse Matrix and Vector Multiplication;ACM Transactions on Architecture and Code Optimization;2024-05-21

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3