Hybrid dot-product design for FP-enabled FPGAs

被引:3
|
作者
Pasca, Bogdan [1 ]
机构
[1] Intel Corp, Programmable Solut Grp, Paris, France
关键词
D O I
10.1109/ARITH.2019.00045
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
引用
收藏
页码:194 / 196
页数:3
相关论文
共 50 条
  • [1] A Fused Hybrid Floating-Point and Fixed-Point Dot-Product for FPGAs
    Lopes, Antonio Roldao
    Constantinides, George A.
    [J]. RECONFIGURABLE COMPUTING: ARCHITECTURES, TOOLS AND APPLICATIONS, 2010, 5992 : 157 - 168
  • [2] Hybrid Dot-Product Calculation for Convolutional Neural Networks in FPGA
    Vestias, Mario
    Duarte, Rui Policarpo
    de Sousa, Jose T.
    Neto, Horacio
    [J]. 2019 29TH INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE LOGIC AND APPLICATIONS (FPL), 2019, : 350 - 353
  • [3] Regularization with dot-product kernels
    Smola, AJ
    Ovári, ZL
    Williamson, RC
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 13, 2001, 13 : 308 - 314
  • [4] A Spectral Analysis of Dot-product Kernels
    Scetbon, Meyer
    Harchaoui, Zaid
    [J]. 24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
  • [5] TRACES OF AGREEMENT - ON THE DOT-PRODUCT AS A COEFFICIENT OF AGREEMENT
    POPPING, R
    [J]. QUALITY & QUANTITY, 1983, 17 (01) : 1 - 18
  • [6] Hardware Performance of Complex Dot-Product Implementations
    DeBrunner, Linda S.
    DeBrunner, Victor
    [J]. 2022 56TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2022, : 141 - 144
  • [7] Fault-Tolerant Dot-Product Engines
    Roth, Ron M.
    [J]. 2018 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT), 2018, : 2197 - 2201
  • [8] Fault-Tolerant Dot-Product Engines
    Roth, Ron M.
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2019, 65 (04) : 2046 - 2057
  • [9] A FAST DOT-PRODUCT ALGORITHM WITH MINIMAL ROUNDING ERRORS
    KOBBELT, L
    [J]. COMPUTING, 1994, 52 (04) : 355 - 369
  • [10] A Floating-Point Fused Dot-Product Unit
    Saleh, Hani H.
    Swartzlander, Earl E., Jr.
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON COMPUTER DESIGN, 2008, : 427 - +