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
  • [41] MVTr: multi-feature voxel transformer for 3D object detection
    Lingmei Ai
    Zhuoyu Xie
    Ruoxia Yao
    Mengyao Yang
    The Visual Computer, 2024, 40 : 1453 - 1466
  • [42] BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer
    Pang, Kunkun
    Qin, Dafei
    Fan, Yingruo
    Habekost, Julian
    Shiratori, Takaaki
    Yamagishi, Junichi
    Komura, Taku
    ACM TRANSACTIONS ON GRAPHICS, 2023, 42 (04):
  • [43] TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer
    Xiong, Huimin
    Li, Kunle
    Tan, Kaiyuan
    Feng, Yang
    Zhou, Joey Tianyi
    Hao, Jin
    Ying, Haochao
    Wu, Jian
    Liu, Zuozhu
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2023, PT VI, 2023, 14225 : 421 - 432
  • [44] A 3D Medical Image Segmentation Framework Fusing Convolution and Transformer Features
    Zhu, Fazhan
    Lv, Jiaxing
    Lu, Kun
    Wang, Wenyan
    Cong, Hongshou
    Zhang, Jun
    Chen, Peng
    Zhao, Yuan
    Wu, Ziheng
    INTELLIGENT COMPUTING THEORIES AND APPLICATION (ICIC 2022), PT I, 2022, 13393 : 772 - 786
  • [45] Transformer-based weakly supervised 3D human pose estimation
    Wu, Xiao-guang
    Xie, Hu-jie
    Niu, Xiao-chen
    Wang, Chen
    Wang, Ze-lei
    Zhang, Shi-wen
    Shan, Yu-ze
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2025, 109
  • [46] Transformer Based Multi-model Fusion for 3D Facial Animation
    Chen, Benwang
    Luo, Chunshui
    Wang, Haoqian
    2023 2ND CONFERENCE ON FULLY ACTUATED SYSTEM THEORY AND APPLICATIONS, CFASTA, 2023, : 659 - 663
  • [47] Towards Accurate Microstructure Estimation via 3D Hybrid Graph Transformer
    Yang, Junqing
    Jiang, Haotian
    Tassew, Tewodros
    Sun, Peng
    Ma, Jiquan
    Xia, Yong
    Yap, Pew-Thian
    Chen, Geng
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2023, PT VIII, 2023, 14227 : 25 - 34
  • [48] HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation
    Cheng, Wencan
    Kim, Eunji
    Ko, Jong Hwan
    COMPUTER VISION - ECCV 2024, PT LXXXVIII, 2025, 15146 : 35 - 52
  • [49] BEV transformer for visual 3D object detection applied with retentive mechanism
    Pan, Jincheng
    Huang, Xiaoci
    Luo, Suyun
    Ma, Fang
    TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2025,
  • [50] ReAGFormer: Reaggregation Transformer with Affine Group Features for 3D Object Detection
    Lu, Chenguang
    Yue, Kang
    Liu, Yue
    COMPUTER VISION - ACCV 2022, PT I, 2023, 13841 : 262 - 279