Introducing a New Cache Design for Vector Processing

Warning! Under constructing....

Description

We introduce an innovative cache design for vector computers, called prime-mapped cache. By utilizing the special properties of a Mersenne prime, the new design does not increase the critical path length of a processor, nor does it increase the cache access time as compared to existing cache organizations. The prime-mapped cache minimizes cache miss ratio caused by line interferences that have been shown to be critical for numerical applications by previous investigators. With negligibly additional hardware cost, we observe significant performance gains by adding the proposed cache memory into an existing vector computer. We study the performance of the new design analytically based on a generic vector computation model. The analytical model is validated through extensive simulation experiments. Our performance analysis on various vector access patterns shows that the prime-mapped cache performs significantly better than conventional cache organizations in the vector processing environment. The performance gain will increase with the increase of the speed gap between processors and memories.

To download the full paper in ps format (Over 0.3 MBytes compressed) Or To read the full paper in PDF format

IEEE-Copyrighted material: Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Funding

This project is sponsored by National Science Fundation.

People

Publications

Here are related publications for the cache project.

  • Full paper of prime-mapped cache (pdf file)
    Copyright-IEEE, Copyright (c) 1993 by IEEE
  • Full paper of 1's complement cache (pdf file)

    • Return to HPCL home page...