A HETEROGENEOUS VON NEUMANN/EXPLICIT DATAFLOW PROCESSOR

被引：0
|
作者：
Nowatzki, Tony [1 ]
Gangadhar, Vinay [2 ]
Sankaralingam, Karthikeyan [1 ,2 ]
机构：
[1] Univ Wisconsin Madison, Dept Comp Sci, Madison, WI 53706 USA
[2] Univ Wisconsin Madison, Dept Elect & Comp Engn, Madison, WI USA
来源：
IEEE MICRO | 2016年 / 36卷 / 03期
基金：
美国国家科学基金会;
关键词：
dataflow; heterogeneous execution; OoO; out of order; Von Neumann;
D O I：
10.1109/MM.2016.34
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
DECADES-OLD EXPLICIT DATAFLOW ARCHITECTURES ELIMINATE MANY OF THE OVERHEADS OF GENERAL-PURPOSE PROCESSORS BUT HAVE NOT BEEN SUCCESSFUL BECAUSE OF THEIR LACK OF SUFFICIENT CONTROL SPECULATION AND THE LATENCY OVERHEAD OF EXPLICIT COMMUNICATION. THIS ARTICLE OBSERVES A SYNERGY BETWEEN OUT-OF-ORDER AND EXPLICIT DATAFLOW PROCESSORS, IN WHICH DYNAMICALLY SWITCHING BETWEEN THEM ACCORDING TO PROGRAM PHASES CAN GREATLY IMPROVE PERFORMANCE AND ENERGY EFFICIENCY.
引用
收藏
页码：20 / 30
页数：11
相关论文
共 50 条
  • [1] Heterogeneous Von Neumann/Dataflow Microprocessors
    Nowatzki, Tony
    Gangadhar, Vinay
    Sankaralingam, Karthikeyan
    COMMUNICATIONS OF THE ACM, 2019, 62 (06) : 83 - 91
  • [2] Exploring the Potential of Heterogeneous Von Neumann/Dataflow Execution Models
    Nowatzki, Tony
    Gangadhar, Vinay
    Sankaralingam, Karthikeyan
    2015 ACM/IEEE 42ND ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2015, : 298 - 310
  • [3] Allocation and Scheduling of Dataflow Graphs on Hybrid Dataflow/von Neumann Architectures
    Bhagyanath, Anoop
    Kercher, Nadine
    Schneider, Klaus
    2023 21ST ACM-IEEE INTERNATIONAL SYMPOSIUM ON FORMAL METHODS AND MODELS FOR SYSTEM DESIGN, MEMOCODE, 2023, : 59 - 70
  • [4] Hybrid Dataflow/von-Neumann Architectures
    Yazdanpanah, Fahimeh
    Alvarez-Martinez, Carlos
    Jimenez-Gonzalez, Daniel
    Etsion, Yoav
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2014, 25 (06) : 1489 - 1509
  • [5] The Heterogeneous Deep Neural Network Processor With a Non-von Neumann Architecture
    Shin, Dongjoo
    Yoo, Hoi-Jun
    PROCEEDINGS OF THE IEEE, 2020, 108 (08) : 1245 - 1260
  • [6] Consistency Constraints for Mapping Dataflow Graphs to Hybrid Dataflow/von Neumann Architectures
    Schneider, Klaus
    Bhagyanath, Anoop
    ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, 2023, 22 (05)
  • [7] Control Flow Coalescing on a Hybrid Dataflow/von Neumann GPGPU
    Voitsechov, Dani
    Etsion, Yoav
    PROCEEDINGS OF THE 48TH ANNUAL IEEE/ACM INTERNATIONAL SYMPOSIUM ON MICROARCHITECTURE (MICRO-48), 2015, : 216 - 227
  • [8] hAP: A Spatial-von Neumann Heterogeneous Automata Processor with Optimized Resource and IO Overhead on FPGA
    Wang, Xuan
    Gong, Lei
    Cao, Jing
    Lou, Wenqi
    Wang, Weiya
    Wang, Chao
    Zhou, Xuehai
    PROCEEDINGS OF THE 2023 ACM/SIGDA INTERNATIONAL SYMPOSIUM ON FIELD PROGRAMMABLE GATE ARRAYS, FPGA 2023, 2023, : 185 - 196
  • [9] Explicit large N von Neumann algebras from matrix models
    Gesteau, Elliott
    Santilli, Leonardo
    ADVANCES IN THEORETICAL AND MATHEMATICAL PHYSICS, 2024, 28 (07)
  • [10] NOTE ON THE VON-NEUMANN STABILITY OF THE EXPLICIT FTCS CONVECTIVE DIFFUSION EQUATION
    LEONARD, BP
    APPLIED MATHEMATICAL MODELLING, 1980, 4 (05) : 401 - 402
12345