Experimenting with Emerging RISC-V Systems for Decentralised Machine Learning

被引:5
|
作者
Mittone, Gianluca [1 ]
Tonci, Nicolo [2 ]
Birke, Robert [1 ]
Colonnelli, Iacopo [1 ]
Medic, Doriana [1 ]
Bartolini, Andrea [3 ]
Esposito, Roberto [1 ]
Parisi, Emanuele [3 ]
Beneventi, Francesco [3 ]
Polato, Mirko [1 ]
Torquati, Massimo [2 ]
Benini, Luca [3 ]
Aldinucci, Marco [1 ]
机构
[1] Univ Turin, Turin, Italy
[2] Univ Pisa, Pisa, Italy
[3] Univ Bologna, Bologna, Italy
关键词
Federated Learning; Edge Computing; RISC-V; Energy Consumption; Green Computing;
D O I
10.1145/3587135.3592211
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Decentralised Machine Learning (DML) enables collaborative machine learning without centralised input data. Federated Learning (FL) and Edge Inference are examples of DML. While tools for DML (especially FL) are starting to flourish, many are not flexible and portable enough to experiment with novel processors (e.g., RISC-V), non-fully connected network topologies, and asynchronous collaboration schemes. We overcome these limitations via a domain-specific language allowing us to map DML schemes to an underlying middleware, i.e. the FastFlow parallel programming library. We experiment with it by generating different working DML schemes on x86-64 and ARM platforms and an emerging RISC-V one. We characterise the performance and energy efficiency of the presented schemes and systems. As a byproduct, we introduce a RISC-V porting of the PyTorch framework, the first publicly available to our knowledge.
引用
收藏
页码:73 / 83
页数:11
相关论文
共 50 条
  • [32] A Security RISC: Microarchitectural Attacks on Hardware RISC-V CPUs
    Gerlach, Lukas
    Weber, Daniel
    Zhang, Ruiyi
    Schwarz, Michael
    2023 IEEE SYMPOSIUM ON SECURITY AND PRIVACY, SP, 2023, : 2321 - 2338
  • [33] Design of IOMMU Based on RISC-V
    Wang, Zhendao
    Ban, Guilong
    Hu, Jin
    Jiao, Xufeng
    Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences, 2024, 51 (06): : 187 - 194
  • [34] Using Embedded Xinu to Teach Operating Systems on Baremetal RISC-V
    Gebhard, Alexander
    Forden, Jack
    Laufenberg, Oliver
    Brylow, Dennis
    PROCEEDINGS OF THE 55TH ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION, SIGCSE 2024, VOL. 1, 2024, : 380 - 386
  • [35] A First Look at RISC-V Virtualization From an Embedded Systems Perspective
    Sa, Bruno
    Martins, Jose
    Pinto, Sandro
    IEEE TRANSACTIONS ON COMPUTERS, 2022, 71 (09) : 2177 - 2190
  • [36] Performance Evaluation of Various RISC Processor Systems: A Case Study on ARM, MIPS and RISC-V
    Liu, Yu
    Ye, Kejiang
    Xu, Cheng-Zhong
    CLOUD COMPUTING, CLOUD 2021, 2022, 12989 : 61 - 74
  • [37] Hardware Accelerated FrodoKEM on RISC-V
    Karl, Patrick
    Fritzmann, Tim
    Sigl, Georg
    2022 25TH INTERNATIONAL SYMPOSIUM ON DESIGN AND DIAGNOSTICS OF ELECTRONIC CIRCUITS AND SYSTEMS (DDECS), 2022, : 154 - 159
  • [38] RISC-V Extension for Lightweight Cryptography
    Tehrani, Etienne
    Graba, Tarik
    Merabet, Abdelmalek Si
    Danger, Jean-Luc
    2020 23RD EUROMICRO CONFERENCE ON DIGITAL SYSTEM DESIGN (DSD 2020), 2020, : 222 - 228
  • [39] A Compiler Comparison in the RISC-V Ecosystem
    Poorhosseini, Mehrdad
    Nebel, Wolfgang
    Gruettner, Kim
    2020 INTERNATIONAL CONFERENCE ON OMNI-LAYER INTELLIGENT SYSTEMS (IEEE COINS 2020), 2020, : 80 - 85
  • [40] A lightweight ISE for ChaCha on RISC-V
    Marshall, Ben
    Page, Daniel
    Thinh Hung Pham
    2021 IEEE 32ND INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS (ASAP 2021), 2021, : 25 - 32