A full-stack search technique for domain optimized deep learning accelerators

Author:

Zhang Dan1ORCID,Huda Safeen2,Songhori Ebrahim1ORCID,Prabhu Kartik3,Le Quoc1,Goldie Anna1ORCID,Mirhoseini Azalia1

Affiliation:

1. Google Brain, USA

2. Google, USA

3. Stanford University, USA

Publisher

ACM

Reference113 articles.

1. 2020. Electric Power Monthly with Data for May 2021 . https://www.eia.gov/electricity/monthly/current_month/july2021.pdf Accessed: 2021-08-09 2020. Electric Power Monthly with Data for May 2021. https://www.eia.gov/electricity/monthly/current_month/july2021.pdf Accessed: 2021-08-09

2. 2021. Developer Guide - NVIDIA Deep Learning cuDNN. https://web.archive.org/web/20210520075036/https://docs.nvidia.com/deeplearning/cudnn/developer-guide/index.html##op-fusion 2021. Developer Guide - NVIDIA Deep Learning cuDNN. https://web.archive.org/web/20210520075036/https://docs.nvidia.com/deeplearning/cudnn/developer-guide/index.html##op-fusion

3. 2021. Software Engineer Salaries in San Francisco Bay Area. https://www.levels.fyi/Salaries/Software-Engineer/San-Francisco-Bay-Area/ Accessed: 2021-08-09 2021. Software Engineer Salaries in San Francisco Bay Area. https://www.levels.fyi/Salaries/Software-Engineer/San-Francisco-Bay-Area/ Accessed: 2021-08-09

4. Mohamed S. Abdelfattah , Lukasz Dudziak , Thomas Chau , Royson Lee , Hyeji Kim , and Nicholas D . Lane . 2020 . Best of Both Worlds: Auto ML Codesign of a CNN and Its Hardware Accelerator. In Proceedings of the 57th ACM/EDAC/IEEE Design Automation Conference (DAC ’20). IEEE Press , Article 192, 6 pages. isbn:9781450367257 https://dl.acm.org/doi/abs/10.5555/3437539.3437731 Mohamed S. Abdelfattah, Lukasz Dudziak, Thomas Chau, Royson Lee, Hyeji Kim, and Nicholas D. Lane. 2020. Best of Both Worlds: AutoML Codesign of a CNN and Its Hardware Accelerator. In Proceedings of the 57th ACM/EDAC/IEEE Design Automation Conference (DAC ’20). IEEE Press, Article 192, 6 pages. isbn:9781450367257 https://dl.acm.org/doi/abs/10.5555/3437539.3437731

5. Amirali Abdolrashidi , Qiumin Xu , Shibo Wang , Sudip Roy , and Yanqi Zhou . 2019 . Learning to Fuse . Workshop on ML for Systems at NeurIPS. Amirali Abdolrashidi, Qiumin Xu, Shibo Wang, Sudip Roy, and Yanqi Zhou. 2019. Learning to Fuse. Workshop on ML for Systems at NeurIPS.

Cited by 14 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. Highly Efficient Self-Checking Matrix Multiplication on Tiled AMX Accelerators;ACM Transactions on Architecture and Code Optimization;2023-11-22

2. MultiFuse: Efficient Cross Layer Fusion for DNN Accelerators with Multi-level Memory Hierarchy;2023 IEEE 41st International Conference on Computer Design (ICCD);2023-11-06

3. DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators;56th Annual IEEE/ACM International Symposium on Microarchitecture;2023-10-28

4. Sia: Heterogeneity-aware, goodput-optimized ML-cluster scheduling;Proceedings of the 29th Symposium on Operating Systems Principles;2023-10-23

5. Quickloop: An Efficient, FPGA-Accelerated Exploration of Parameterized DNN Accelerators;2023 32nd International Conference on Parallel Architectures and Compilation Techniques (PACT);2023-10-21

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