HeTraX: Energy Efficient 3D Heterogeneous Manycore Architecture for Transformer Acceleration

被引:0
|
作者
Dhingra, Pratyush [1 ]
Doppa, Janardhan Rao [1 ]
Pande, Partha Pratim [1 ]
机构
[1] Washington State Univ, Pullman, WA 99164 USA
来源
PROCEEDINGS OF THE 29TH ACM/IEEE INTERNATIONAL SYMPOSIUM ON LOW POWER ELECTRONICS AND DESIGN, ISLPED 2024 | 2024年
基金
美国国家科学基金会;
关键词
Transformer; Heterogeneity; Accelerator; Thermal-aware; PIM;
D O I
10.1145/3665314.3670814
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Transformers have revolutionized deep learning and generative modeling to enable unprecedented advancements in natural language processing tasks and beyond. However, designing hardware accelerators for executing transformer models is challenging due to the wide variety of computing kernels involved in the transformer architecture. Existing accelerators are either inadequate to accelerate end-to-end transformer models or suffer notable thermal limitations. In this paper, we propose the design of a three-dimensional heterogeneous architecture referred to as HeTraX specifically optimized to accelerate end-to-end transformer models. HeTraX employs hardware resources aligned with the computational kernels of transformers and optimizes both performance and energy. Experimental results show that HeTraX outperforms existing state-of-the-art by up to 5.6x in speedup and improves EDP by 14.5x while ensuring thermally feasibility.
引用
收藏
页数:6
相关论文
共 50 条
  • [21] A High-Performance and Energy-Efficient Photonic Architecture for Multi-DNN Acceleration
    Li, Yuan
    Louri, Ahmed
    Karanth, Avinash
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2024, 35 (01) : 46 - 58
  • [22] A Heterogeneous and Reconfigurable Embedded Architecture for Energy-Efficient Execution of Convolutional Neural Networks
    Luebeck, Konstantin
    Bringmann, Oliver
    ARCHITECTURE OF COMPUTING SYSTEMS - ARCS 2019, 2019, 11479 : 267 - 280
  • [23] Transformer3D-Det: Improving 3D Object Detection by Vote Refinement
    Zhao, Lichen
    Guo, Jinyang
    Xu, Dong
    Sheng, Lu
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 31 (12) : 4735 - 4746
  • [24] Stray Losses Study for a Power Transformer Based on 3D FEM
    Song, Zhanhai
    Wang, Yifang
    Mou, Shuai
    Wu, Zhe
    Zhu, Yinhui
    Xiang, Bingfu
    Zhou, Ce
    MECHANICAL AND ELECTRONICS ENGINEERING III, PTS 1-5, 2012, 130-134 : 3374 - +
  • [25] DGFormer: Dynamic graph transformer for 3D human pose estimation
    Chen, Zhangmeng
    Dai, Ju
    Bai, Junxuan
    Pan, Junjun
    PATTERN RECOGNITION, 2024, 152
  • [26] WalkFormer: 3D mesh analysis via transformer on random walk
    Guo, Qing
    He, Fazhi
    Fan, Bo
    Song, Yupeng
    Dai, Jicheng
    Fan, Linkun
    NEURAL COMPUTING & APPLICATIONS, 2024, 36 (07) : 3499 - 3511
  • [27] Transformer based 3D semantic segmentation of urban bicycle infrastructure
    Niedermueller, Armin
    Beeking, Moritz
    JOURNAL OF LOCATION BASED SERVICES, 2024,
  • [28] 3D point cloud object detection algorithm based on Transformer
    Liu M.
    Yang Q.
    Hu G.
    Guo Y.
    Zhang J.
    Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University, 2023, 41 (06): : 1190 - 1197
  • [29] Research on 3D Face Reconstruction Algorithm Based on ResNet and Transformer
    Yaermaimaiti, Yilihamu
    Yan, Tianxing
    Zhao, Yuhang
    Kari, Tusongjiang
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS, 2024, 23 (01)
  • [30] WalkFormer: 3D mesh analysis via transformer on random walk
    Qing Guo
    Fazhi He
    Bo Fan
    Yupeng Song
    Jicheng Dai
    Linkun Fan
    Neural Computing and Applications, 2024, 36 : 3499 - 3511