EXPLOITING OPERATING SYSTEM SUPPORT FOR DYNAMIC PAGE PLACEMENT ON A NUMA SHARED MEMORY MULTIPROCESSOR

被引:0
|
作者
LAROWE, RP [1 ]
WILKES, JT [1 ]
ELLIS, CS [1 ]
机构
[1] DUKE UNIV,DEPT COMP SCI,DURHAM,NC 27706
来源
SIGPLAN NOTICES | 1991年 / 26卷 / 07期
关键词
D O I
暂无
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Shared memory multiporcessors are attractive because they are programmed in a manner similar to uniprocessors. The UMA class of shared memory multiprocessors is the most attractive, from the programmer's point of view, since the programmer need not be concerned with the placement of code and data in the physical memory hierarchy. Scalable shared memory multiprocessors, on the other hand, tend to present at least some degree of non-uniformity of memory access to the programmer, making the NUMA class an important one to consider. In this paper, we investigate the role that DUnX, an operating system supporting dynamic page placement on a BBN GP1000, might play in simplifying the memory model presented to the applications programmer. We consider a case study of psolu, a real scientific application originally targeted for a NUMA architecture. We find that dynamic page placement can dramatically improve the performance of a simpler implementation of psolu targeted for an UMA memory architecture. The addition of a phase change hint to the UMA version of psolu enables the operating system to further improve performance, approaching that of the hand-tuned NUMA implementation.
引用
收藏
页码:122 / 132
页数:11
相关论文
共 50 条
  • [41] Optimizing the performance of in-memory file system by thread scheduling and file migration under NUMA multiprocessor systems
    Wu, Ting
    He, Jingting
    Qian, Ying
    Liu, Weichen
    JOURNAL OF SYSTEMS ARCHITECTURE, 2025, 159
  • [42] Multiple subtyping in a persistent Distributed Shared Memory operating system
    Schoettner, M
    Schirpf, O
    Wende, M
    Schulthess, P
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-V, 2000, : 565 - 571
  • [43] Chameleon: Operating System Support for Dynamic Processors
    Panneerselvam, Sankaralingam
    Swift, Michael M.
    ACM SIGPLAN NOTICES, 2012, 47 (04) : 99 - 110
  • [44] Chameleon: Operating System Support for Dynamic Processors
    Panneerselvam, Sankaralingam
    Swift, Michael M.
    ASPLOS XVII: SEVENTEENTH INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS, 2012, : 99 - 110
  • [45] User-level dynamic page migration for multiprogrammed shared-memory multipropcessors
    Nikolopoulos, DS
    Papatheodorou, TS
    Polychronopoulos, CD
    Labarta, J
    Ayguadé, E
    2000 INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, PROCEEDINGS, 2000, : 95 - 103
  • [46] DESIGN OF THE SHARED MEMORY SYSTEM FOR MULTIPROCESSOR LISP MACHINES AND ITS IMPLEMENTATION ON THE EVLIS MACHINE
    YASUI, H
    SAKAGUCHI, T
    KUDO, K
    HIRONISHI, N
    LECTURE NOTES IN COMPUTER SCIENCE, 1990, 441 : 348 - 352
  • [47] Hardware transactional memory with Operating System support, HTMOS
    Tomic, Sasa
    Cristal, Adrian
    Unsal, Osman
    Valero, Mateo
    EURO-PAR 2007 WORKSHOPS: PARALLEL PROCESSING, 2008, 4854 : 8 - 17
  • [48] Exploiting page write pattern for power management of hybrid DRAM/PRAM memory system
    School of Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou
    310018, China
    不详
    310027, China
    J. Inf. Sci. Eng., 5 (1633-1646):
  • [49] Exploiting Page Write Pattern for Power Management of Hybrid DRAM/PRAM Memory System
    Zhang, Tiefei
    Xing, Jianguo
    Zhu, Jixiang
    Chen, Tianzhou
    JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 2015, 31 (05) : 1633 - 1646
  • [50] Shortcut interconnection: New Multistage Interconnection Network for the locality of reference in shared memory multiprocessor system
    Choi, CH
    Kim, SC
    SECOND AIZU INTERNATIONAL SYMPOSIUM ON PARALLEL ALGORITHMS/ARCHITECTURE SYNTHESIS, PROCEEDINGS, 1997, : 216 - 224