Performance and Power Benefits of Sharing Execution Units between a High Performance Core and a Low Power Core

被引:5
|
作者
Rodrigues, Rance [1 ]
Koren, Israel [1 ]
Kundu, Sandip [1 ]
机构
[1] Univ Massachusetts, Dept Elect & Comp Engn, Amherst, MA 01003 USA
关键词
Asymmetric Multicore Processor (AMP); Symmetric Multicore Processor (SMP); resource sharing; performance; performance/Watt;
D O I
10.1109/VLSID.2014.42
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Several studies and real world designs have advocated the sharing of large execution units between pairs of cores in Symmetric Multicore Processors (SMP) for area and power savings. Such sharing was shown to have negligible impact on performance. Recently, a number of Asymmetric Multicore Processor (AMP) designs have become available. The objective of this paper is to investigate whether sharing of resources across AMPs offers similar benefits. Our study shows that while the area and the power savings remain similar, the performance of the smaller core in the AMP can improve significantly making sharing even more attractive for AMPs. Simulation results indicate that for certain workloads, the performance of the small core may improve by as much as 54% by sharing certain large execution resources of the big core, while affecting the performance of the big core by only similar to 4%, resulting in an overall gain in system performance of 20%. The corresponding improvement in aggregate performance/Watt is 12% while the area savings is about 7%.
引用
收藏
页码:204 / 209
页数:6
相关论文
共 50 条
  • [31] Low Dynamic Power High Performance Adder
    Senejani, M. Nadi
    Ghadiry, M. Hossein
    Miryahyaei, M.
    EXPERIENCE OF DESIGNING AND APPLICATION OF CAD SYSTEMS IN MICROELECTRONICS: PROCEEDINGS OF THE XTH INTERNATIONAL CONFERENCE CADSM 2009, 2009, : 242 - +
  • [32] Reconfigurable Routers for Low Power and High Performance
    Matos, Debora
    Concatto, Caroline
    Kreutz, Marcio
    Kastensmidt, Fernanda
    Carro, Luigi
    Susin, Altamiro
    IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2011, 19 (11) : 2045 - 2057
  • [33] Trends in high performance computing with low power
    Nakamura, Tadao
    INFORMATION-AN INTERNATIONAL INTERDISCIPLINARY JOURNAL, 2007, 10 (05): : 587 - 596
  • [34] Low Dynamic Power High Performance Adder
    Senejani, M. Nadi
    Hosseinghadiry, M.
    Miryahyaei, M.
    INTERNATIONAL CONFERENCE ON FUTURE COMPUTER AND COMMUNICATIONS, PROCEEDINGS, 2009, : 482 - +
  • [35] The design of a high performance low power microprocessor
    Dobberpuhl, D
    1996 INTERNATIONAL SYMPOSIUM ON LOW POWER ELECTRONICS AND DESIGN - DIGEST OF TECHNICAL PAPERS, 1996, : 11 - 16
  • [36] High performance, low impedance power interconnects
    Wood, DE
    DiBene, JT II
    APEC 2003: EIGHTEENTH ANNUAL IEEE APPLIED POWER ELECTRONICS CONFERENCE AND EXPOSITION, VOLS 1 AND 2, 2003, : 747 - 750
  • [37] Transistor sizing for high performance and low power
    Fishburn, JP
    Taneja, S
    PROCEEDINGS OF THE IEEE 1997 CUSTOM INTEGRATED CIRCUITS CONFERENCE, 1997, : 591 - 594
  • [38] The XTREM power and performance simulator for the Intel XScale core: Design and experiences
    Contreras, Gilberto
    Martonosi, Margaret
    Peng, Jinzhang
    Lueh, Guei-Yuan
    Ju, Roy
    ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, 2007, 6 (01) : 4
  • [39] Profit: Priority and Power/Performance Optimization for Many-Core Systems
    Chen, Zhuo
    Stamoulis, Dimitrios
    Marculescu, Diana
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2018, 37 (10) : 2064 - 2075
  • [40] Other factors contributing to the core loss performance of power and distribution transformers
    teNyenhuis, EG
    Girgis, RS
    Mechler, GF
    IEEE TRANSACTIONS ON POWER DELIVERY, 2001, 16 (04) : 648 - 653