• DocumentCode
    3375425
  • Title

    Reducing memory traffic with CRegs

  • Author

    Dahl, Peter ; O´Keefe, Matthew

  • Author_Institution
    Dept. of Electr. Eng., Minnesota Univ., Minneapolis, MN, USA
  • fYear
    1994
  • fDate
    30 Nov.-2 Dec. 1994
  • Firstpage
    100
  • Lastpage
    104
  • Abstract
    Array and pointer references are often ambiguous in that compile time analysis cannot always determine if distinct references are to the same object. Ambiguously aliased objects are not allocated to registers by conventional compilers due to the cost of the loads and stores required to keep register copies consistent with memory and each other. There are several hardware and software strategies that can be used to solve the ambiguous alias problem; we have implemented one such scheme called CRegs in a compiler and instruction level simulator. We present a modification to Briggs´ Optimistic Coloring Algorithm that allows us to allocate local and parameter arrays to CRegs. The CRegs register file operation and instruction set modifications required to implement this scheme are discussed. Underlying hardware issues such as pipeline impact and chip area are briefly discussed. Several benchmarks are compared in terms of dynamic instructions executed for two CReg set sizes. The measured reduction in memory operations is significant, averaging 23% for the benchmarks shown.
  • Keywords
    file organisation; graph colouring; instruction sets; program compilers; storage allocation; CRegs; Optimistic Coloring Algorithm; array references; benchmarks; chip area; compile time analysis; compilers; dynamic instructions; instruction level simulator; instruction set; memory operations; memory traffic reduction; pipeline impact; pointer references; Contracts; Costs; Distributed computing; Hardware; Machinery; Military computing; Permission; Pipelines; Registers; Semiconductor device measurement;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Microarchitecture, 1994. MICRO-27. Proceedings of the 27th Annual International Symposium on
  • ISSN
    1072-4451
  • Print_ISBN
    0-89791-707-3
  • Type

    conf

  • DOI
    10.1109/MICRO.1994.717423
  • Filename
    717423