Design space exploration of heterogeneous MPSoCs with variable number of hardware accelerators

被引:4
|
作者
Xu, Siyuan [1 ]
Liu, Shuangnan [2 ]
Liu, Yidi [2 ]
Mahapatra, Anushree [2 ]
Villaverde, Monica [3 ]
Moreno, Felix [3 ]
Schafer, Benjamin Carrion [1 ]
机构
[1] Univ Texas Dallas, Dept Elect & Comp Engn, Richardson, TX 75083 USA
[2] Hong Kong Polytech Univ, Dept Elect & Informat Engn, Hong Kong, Peoples R China
[3] Univ Politecn Madrid, Ctr Elect Ind, Madrid, Spain
关键词
Design space exploration; Heterogeneous SoCs; Hardware accelerators; High-level synthesis; In-situ exploration; Simulation acceleration; SYSTEM;
D O I
10.1016/j.micpro.2019.01.010
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This work proposes three different methods to automatically characterize heterogeneous MPSoCs composed of a variable number of masters (in the form of processors) and hardware accelerators (HWaccs). These hardware accelerators are given as Behavioral IPs (BIPs) mapped as loosely coupled accelerators on a shared bus system (i.e. AHB, AXI). BIPs have a distinct advantage over traditional RT-level based IPs given VHDL or Verilog: The ability to generate micro-architectures with different area vs. performance trade-offs from the same description. This is usually done by specifying different synthesis directives in the form of pragmas. This in turn implies that using different mixes of the accelerators' micro-architectures lead to SoCs with unique area vs. performance trade-offs. Two of the three methods proposed are based on cycle-accurate simulations of the complete MPSoC, while the third method accelerates this exploration by performing it on a Configurable SoC FPGA. Extensive experimental results compare these three methods and highlight their strengths and weaknesses. (C) 2019 Elsevier B.V. All fights reserved.
引用
收藏
页码:169 / 179
页数:11
相关论文
共 50 条
  • [1] Characterization and Optimization of Behavioral Hardware Accelerators in Heterogeneous MPSoCs
    Liu, Yidi
    Villaverde, Monica
    Moreno, Felix
    Schafer, Benjamin Carrion
    2017 12TH INTERNATIONAL SYMPOSIUM ON RECONFIGURABLE COMMUNICATION-CENTRIC SYSTEMS-ON-CHIP (RECOSOC), 2017,
  • [2] A Mapping Framework Based on Packing for Design Space Exploration of Heterogeneous MPSoCs
    Ristau, Bastian
    Limberg, Torsten
    Fettweis, Gerhard
    JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2009, 57 (01): : 45 - 56
  • [3] A Mapping Framework Based on Packing for Design Space Exploration of Heterogeneous MPSoCs
    Bastian Ristau
    Torsten Limberg
    Gerhard Fettweis
    Journal of Signal Processing Systems, 2009, 57 : 45 - 56
  • [4] Distributed Thermal Management for Embedded Heterogeneous MPSoCs with Dedicated Hardware Accelerators
    Wu, Yen-Kuan
    Sharifi, Shervin
    Rosing, Tajana Simunic
    2011 IEEE 29TH INTERNATIONAL CONFERENCE ON COMPUTER DESIGN (ICCD), 2011, : 183 - 189
  • [5] DAMHSE: Programming heterogeneous MPSoCs with hardware acceleration using dataflow-based design space exploration and automated rapid prototyping
    Suriano, Leonardo
    Arrestier, Florian
    Rodriguez, Alfonso
    Heulot, Julien
    Desnos, Karol
    Pelcat, Maxime
    de la Torre, Eduardo
    MICROPROCESSORS AND MICROSYSTEMS, 2019, 71
  • [6] Hybrid Interconnect Design for Heterogeneous Hardware Accelerators
    Cuong Pham-Quoc
    Heisswolf, Jan
    Werner, Stephan
    Al-Ars, Zaid
    Becker, Juergn
    Bertels, Koen
    DESIGN, AUTOMATION & TEST IN EUROPE, 2013, : 843 - 846
  • [7] Partitioning Data-parallel Programs for Heterogeneous MPSoCs : Time and Energy Design Space Exploration
    Chandramohan, Kiran
    O'Boyle, Michael F. P.
    ACM SIGPLAN NOTICES, 2014, 49 (05) : 73 - 82
  • [8] Scenario-Based Design Space Exploration of MPSoCs
    van Stralen, Peter
    Pimentel, Andy
    2010 IEEE INTERNATIONAL CONFERENCE ON COMPUTER DESIGN, 2010, : 305 - 312
  • [9] Incorporating Energy and Throughput Awareness in Design Space Exploration and Run-time Mapping for Heterogeneous MPSoCs
    Nam Khanh Pham
    Singh, Amit Kumar
    Kumar, Akash
    Aung, Khin Mi Mi
    16TH EUROMICRO CONFERENCE ON DIGITAL SYSTEM DESIGN (DSD 2013), 2013, : 513 - 521
  • [10] Stream: Design Space Exploration of Layer-Fused DNNs on Heterogeneous Dataflow Accelerators
    Symons, Arne
    Mei, Linyan
    Colleman, Steven
    Houshmand, Pouya
    Karl, Sebastian
    Verhelst, Marian
    IEEE TRANSACTIONS ON COMPUTERS, 2025, 74 (01) : 237 - 249