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
  • [31] DAFDeTr: Deformable Attention Fusion Based 3D Detection Transformer
    Erabati, Gopi Krishna
    Araujo, Helder
    ROBOTICS, COMPUTER VISION AND INTELLIGENT SYSTEMS, ROBOVIS 2024, 2024, 2077 : 293 - 315
  • [32] Transformer Enhanced Hierarchical 3D Point Cloud Semantic Segmentation
    Liu, Yaohua
    Ma, Yue
    Xu, Min
    2ND INTERNATIONAL CONFERENCE ON APPLIED MATHEMATICS, MODELLING, AND INTELLIGENT COMPUTING (CAMMIC 2022), 2022, 12259
  • [33] nnFormer: Volumetric Medical Image Segmentation via a 3D Transformer
    Zhou, Hong-Yu
    Guo, Jiansen
    Zhang, Yinghao
    Han, Xiaoguang
    Yu, Lequan
    Wang, Liansheng
    Yu, Yizhou
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 4036 - 4045
  • [34] Real-Time 3D Single Object Tracking With Transformer
    Shan, Jiayao
    Zhou, Sifan
    Cui, Yubo
    Fang, Zheng
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 2339 - 2353
  • [35] Local Transformer Network on 3D Point Cloud Semantic Segmentation
    Wang, Zijun
    Wang, Yun
    An, Lifeng
    Liu, Jian
    Liu, Haiyang
    INFORMATION, 2022, 13 (04)
  • [36] CenterFormer: Center-Based Transformer for 3D Object Detection
    Zhou, Zixiang
    Zhao, Xiangchen
    Wang, Yu
    Wang, Panqu
    Foroosh, Hassan
    COMPUTER VISION, ECCV 2022, PT XXXVIII, 2022, 13698 : 496 - 513
  • [37] Dual-Path Transformer for 3D Human Pose Estimation
    Zhou, Lu
    Chen, Yingying
    Wang, Jinqiao
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (05) : 3260 - 3270
  • [38] Image attention transformer network for indoor 3D object detection
    Ren, Keyan
    Yan, Tong
    Hu, Zhaoxin
    Han, Honggui
    Zhang, Yunlu
    SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2024, 67 (07) : 2176 - 2190
  • [39] Learning 3D Skeletal Representation From Transformer for Action Recognition
    Cha, Junuk
    Saqlain, Muhammad
    Kim, Donguk
    Lee, Seungeun
    Lee, Seongyeong
    Baek, Seungryul
    IEEE ACCESS, 2022, 10 : 67541 - 67550
  • [40] DiffTF++: 3D-Aware Diffusion Transformer for Large-Vocabulary 3D Generation
    Cao, Ziang
    Hong, Fangzhou
    Wu, Tong
    Pan, Liang
    Liu, Ziwei
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2025, 47 (04) : 3018 - 3030