Design a Novel Memory Network for Processor-in-Memory Architectures

被引:0
|
作者
Chu, Slo-Li [1 ]
Ho, Wen-Chih [1 ]
Chen, Chien-Fang [1 ]
Ceng, Kai-Wei [1 ]
Liu, Ming-Han [1 ]
机构
[1] Chung Yuan Christian Univ, Dept Informat & Comp Engn, Chungli, Taiwan
关键词
Memory Network; Processor-in-Memory Architecture; Multicore Architecture;
D O I
10.1109/SKG.2017.00018
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The growing requirement of data-intensive computing makes the problem of insufficient memory bandwidth more critical. The advantages of multicore architectures and advanced parallel computers are limited. The new kind of architecture, Processor-in-Memory (NM), is developed to solve the above challenge by integrating the computing logics and tiny processors into the DRAM chip. The data processing capability of the memory subsystem can be improved. However, the bandwidth of the conventional interconnection networks can not satisfy the bandwidth consumption of multiple PIM modules. Therefore, a new memory network, MemGrid, is proposed for connecting multiple PIM memory modules and CPUs. The proposed MemGrid network has the capabilities of high scalability and low diameter. The connection topologies of MemGrid network with the corresponding network switch architecture are discussed. The experimental results show that the MemGrid network can achieve better performance than other interconnection networks in variant accessing patterns and configurations.
引用
收藏
页码:56 / 61
页数:6
相关论文
共 50 条
  • [1] A statement based parallelizing framework for processor-in-memory architectures
    Huang, TC
    Chu, SL
    INFORMATION PROCESSING LETTERS, 2003, 85 (03) : 159 - 163
  • [2] A processor-in-memory architecture for multimedia compression
    Jasionowski, Brandon J.
    Lay, Michelle K.
    Margala, Martin
    IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2007, 15 (04) : 478 - 483
  • [3] Optimizing data scheduling on processor-in-memory arrays
    Tian, Y
    Sha, EHM
    Chantrapornchai, C
    Kogge, PM
    FIRST MERGED INTERNATIONAL PARALLEL PROCESSING SYMPOSIUM & SYMPOSIUM ON PARALLEL AND DISTRIBUTED PROCESSING, 1998, : 57 - 61
  • [4] Variant Calling Parallelization on Processor-in-Memory Architecture
    Lavenier, Dominique
    Cimadomo, Remy
    Jodin, Romaric
    2020 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2020, : 204 - 207
  • [5] Processor-in-Memory Support for Artificial Neural Networks
    Schabel, Joshua
    Baker, Lee
    Dey, Sumon
    Li, Weifu
    Franzon, Paul D.
    2016 IEEE INTERNATIONAL CONFERENCE ON REBOOTING COMPUTING (ICRC), 2016,
  • [6] An efficient PIM (Processor-In-Memory) architecture for BLAST
    Kang, JY
    Gupta, S
    Gaudiot, JL
    CONFERENCE RECORD OF THE THIRTY-EIGHTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1 AND 2, 2004, : 503 - 507
  • [7] DNA Mapping using Processor-in-Memory Architecture
    Lavenier, Dominique
    Roy, Jean-Francois
    Furodet, David
    2016 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2016, : 1429 - 1435
  • [8] Memory-side prefetching for linked data structures for processor-in-memory systems
    Hughes, CJ
    Adve, SV
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2005, 65 (04) : 448 - 463
  • [9] Embedded Processor-In-Memory Architecture for Accelerating Arithmetic Operations
    Muri, Richard
    Fortier, Paul
    2019 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE (HPEC), 2019,
  • [10] An efficient PIM (processor-in-memory) architecture for motion estimation
    Kang, JY
    Gupta, S
    Shah, S
    Gaudiot, JL
    IEEE INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES, AND PROCESSORS, PROCEEDINGS, 2003, : 282 - 292