Polymorphous Computing Architecture (PCA) Kernel-Level Benchmarks

Abstract

This document describes a series of kernel benchmarks for the PCA program. Each kernel benchmark is an operation of importance to DoD sensor applications making use of a PCA architecture. The kernel-level benchmarks have been chosen to stress both computation and communication aspects of the architecture. "Computation" aspects include floating-point and integer performance, as well as the memory hierarchy, while the "communication" aspects include the network, the memory hierarchy, and the 110 capabilities. The particular benchmarks chosen are based on the frequency of their use in current and future applications. They are drawn from the areas of signal processing, communication, and information and knowledge processing. Source code for most of the kernel-level benchmarks is provided in the MATLAB programming language, with a C and C++ version to be released in the summer of 2003. The specification of the benchmarks in this document is meant to be high-level and largely independent of the implementation. MATLAB code is not provided for the corner-turn or database kernels. The corner-turn kernel is described in the C language, as it involves explicit memory operation. The database kernel is described relative to a generic database interface.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 23, 2004
Accession Number
ADA419630

Entities

People

  • A. Reuther
  • Elissa W.P. Wong
  • J. Lebak

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Application Software
  • C Programming Language
  • Computations
  • Computer Architecture
  • Computer Programming
  • Computer Programs
  • Computing System Architectures
  • Databases
  • Detection
  • Domain Specific Programming Languages
  • Floating Point Operations
  • Frequency
  • Language
  • Programming Languages
  • Signal Processing
  • Standards
  • Synthetic Aperture Radar

Fields of Study

  • Computer science

Readers

  • Parallel and Distributed Computing.