• DocumentCode
    3296774
  • Title

    Connection Machine model CM-5 system overview

  • Author

    Palmer, John ; Steele, Guy L., Jr.

  • fYear
    1992
  • fDate
    19-21 Oct 1992
  • Firstpage
    474
  • Lastpage
    483
  • Abstract
    The Connection Machine model CM-5 provides high performance and ease of use for large data-intensive applications. The CM-5 architecture is designed to scale to teraflops performance on terabyte-sized problems. SPARC-based processing nodes, each with four vector pipes, are connected by two communications networks, the Data Network and the Control Network. The system combines the best features of SIMD (single-instruction multiple-data) and MIMD (multiple-instruction multiple-data) designs, integrating them into a single `universal´ parallel architecture. The processor nodes may be divided into independent computational partitions; each partition may be independently timeshared or devoted to batch processing. Programming languages include Fortran (with Fortran 90 array constructs) and C*, a parallel dialect of C. The PRISM programming environment supports source-level debugging, tracing, and profiling through a graphical interface based on X Windows
  • Keywords
    C language; FORTRAN; graphical user interfaces; parallel architectures; parallel machines; program debugging; CM-5 architecture; Connection Machine model CM-5 system; Control Network; Data Network; Fortran; MIMD; PRISM programming environment; SIMD; SPARC-based processing; X Windows; batch processing; communications networks; graphical interface; high performance; multiple-instruction multiple-data; overview; parallel architecture; parallel dialect of C; single-instruction multiple-data; source-level debugging; tracing; vector pipes; Bandwidth; Communication networks; Communication system control; Computer architecture; Computer languages; Concurrent computing; Control systems; Process control; Programming environments; Weight control;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Frontiers of Massively Parallel Computation, 1992., Fourth Symposium on the
  • Conference_Location
    McLean, VA
  • Print_ISBN
    0-8186-2772-7
  • Type

    conf

  • DOI
    10.1109/FMPC.1992.234877
  • Filename
    234877