• DocumentCode
    3038904
  • Title

    A 289 MFLOPS single-chip supercomputer

  • Author

    Iino, H. ; Takahashi, H. ; Sukemura, T. ; Kimura, M. ; Fujita, K. ; Mori, S.

  • Author_Institution
    Fujitsu Ltd., Kawasaki, Japan
  • fYear
    1992
  • fDate
    19-21 Feb. 1992
  • Firstpage
    112
  • Lastpage
    113
  • Abstract
    Reports on a single-chip supercomputer vector processing unit (VPU) which achieves peak performance of 149 MFLOPS for double-precision operation and 289 MFLOPS for single-precision operation with 560 MB/s bus bandwidth at 70 MHz. The VPU chip, fabricated using 0.5- mu m CMOS triple-metal-layer technology, contains about 1.5 million transistors on a 15.75*16.00 mm/sup 2/ die. The VPU uses a single instruction-stream multiple data-stream (SIMD) architecture on a single CMOS chip. The VPU implementation includes multiple vector pipelines operating concurrently, minimum pipeline latency, vectorized conditional branches, and an optimized instruction set for vector operations.<>
  • Keywords
    CMOS integrated circuits; microprocessor chips; parallel architectures; pipeline processing; vector processor systems; 0.5 micron; 149 MFLOPS; 289 MFLOPS; 560 Mbyte/s; 70 MHz; CMOS triple-metal-layer technology; bus bandwidth; double-precision operation; minimum pipeline latency; multiple vector pipelines; optimized instruction set; single instruction-stream multiple data-stream; single-chip supercomputer; single-precision operation; vector processing unit; vectorized conditional branches; Adders; CMOS technology; Delay; Driver circuits; Graphics; Laboratories; Pipelines; Registers; Supercomputers; Virtual reality;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Solid-State Circuits Conference, 1992. Digest of Technical Papers. 39th ISSCC, 1992 IEEE International
  • Conference_Location
    San Francisco, CA, USA
  • Print_ISBN
    0-7803-0573-6
  • Type

    conf

  • DOI
    10.1109/ISSCC.1992.200437
  • Filename
    200437