Towards Rapid Exploration of Heterogeneous TinyML Systems using Virtual Platforms and TVM's UMA

Author:

Ahmadifarsani Samira1ORCID,Stahl Rafael1ORCID,van Kempen Philipp1ORCID,Mueller-Gritschneder Daniel1ORCID,Schlichtmann Ulf1ORCID

Affiliation:

1. Technical University of Munich, Munich, Germany

Funder

German Ministry of Education and Research (BMBF)

Publisher

ACM

Reference11 articles.

1. Colby Banbury, Vijay Janapa Reddi, Peter Torelli, Jeremy Holleman, Nat Jeffries, Csaba Kiraly, Pietro Montino, David Kanter, Sebastian Ahmed, Danilo Pau, et al. 2021. Mlperf tiny benchmark. arXiv preprint arXiv:2106.07597 (2021).

2. Zhi Chen, Cody Hao Yu, Trevor Morris, Jorn Tuyls, Yi-Hsiang Lai, Jared Roesch, Elliott Delaye, Vin Sharma, and Yida Wang. 2021. Bring your own codegen to deep learning compiler. arXiv preprint arXiv:2105.03215 (2021).

3. Animesh Jain. [n. d.]. Convert Layout Pass. https://tvm.apache.org/docs/arch/convert_layout.html

4. Animesh Jain, Shoubhik Bhattacharya, Masahiro Masuda, Vin Sharma, and Yida Wang. 2020. Efficient execution of quantized deep learning models: A compiler approach. arXiv preprint arXiv:2006.10226 (2020).

5. M. J. Klaiber P. P. Bernardo and C. Gerum. 2022. Making your Hardware Accelerator TVM-ready with UMA. https://tvm.apache.org/docs/tutorial/uma.html

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