SVR: A Shard-aware Vertex Reordering Method for Efficient GNN Execution and Memory Access

被引：0
|
作者：
Hu, Xingyuan [1 ]
Shao, Zhuang [1 ]
Xie, Chenjia [1 ]
Du, Li [1 ]
Du, Yuan [1 ]
机构：
[1] Nanjing University, Nanjing, China
来源：
Proceedings - International SoC Design Conference 2022, ISOCC 2022 | 2022年
关键词：
Compendex;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Graph neural networks
引用
收藏
页码：165 / 166
相关论文
共 16 条
  • [1] SVR: A Shard-aware Vertex Reordering Method for Efficient GNN Execution and Memory Access
    Hu, Xingyuan
    Shao, Zhuang
    Xie, Chenjia
    Du, Li
    Du, Yuan
    2022 19TH INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC), 2022, : 165 - 166
  • [2] Efficient Execution of Memory Access Phases Using Dataflow Specialization
    Ho, Chen-Han
    Kim, Sung Jin
    Sankaralingam, Karthikeyan
    2015 ACM/IEEE 42ND ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2015, : 118 - 130
  • [3] Efficient MIP volume rendering via fast SIMD interpolation and memory access reordering
    Lee, Sehee
    Kye, Heewon
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (07) : 10515 - 10534
  • [4] Efficient MIP volume rendering via fast SIMD interpolation and memory access reordering
    Sehee Lee
    Heewon Kye
    Multimedia Tools and Applications, 2023, 82 : 10515 - 10534
  • [5] Energy-efficient fairness-aware memory access scheduling
    Modgil, Aastha
    Sehgal, Vivek Kumar
    Chanderwal, Nitin
    INTERNATIONAL JOURNAL OF SERVICES TECHNOLOGY AND MANAGEMENT, 2020, 26 (06) : 520 - 537
  • [6] A systematic reordering mechanism for on-chip networks using efficient congestion-aware method
    Daneshtalab, Masoud
    Ebrahimi, Masoumeh
    Liljeberg, Pasi
    Plosila, Juha
    Tenhunen, Hannu
    JOURNAL OF SYSTEMS ARCHITECTURE, 2013, 59 (4-5) : 213 - 222
  • [7] MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization
    Zhu, Zeyu
    Li, Fanrong
    Li, Gang
    Liu, Zejian
    Mo, Zitao
    Hu, Qinghao
    Liang, Xiaoyao
    Cheng, Jian
    2024 IEEE INTERNATIONAL SYMPOSIUM ON HIGH-PERFORMANCE COMPUTER ARCHITECTURE, HPCA 2024, 2024, : 124 - 138
  • [8] MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization
    Institute of Automation, Chinese Academy of Sciences, China
    不详
    不详
    不详
    不详
    Proc. Int. Symp. High Perform. Comput. Archit., 1600, (124-138): : 124 - 138
  • [9] A Scalable and Efficient NTT/INTT Architecture Using Group-Based Pairwise Memory Access and Fast Interstage Reordering
    Wang, Zihang
    Yang, Yushu
    Wang, Jianfei
    Hou, Jia
    Su, Yang
    Yang, Chen
    IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2025, 33 (02) : 588 - 592
  • [10] MEMORY ACCESS REDUCTION METHOD FOR EFFICIENT IMPLEMENTATION OF FAST COSINE TRANSFORM PRUNING ON DSP
    Liu, Xiangyang
    2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 1490 - 1493
12