Optimizing Memory Bandwidth on Stream Triad

Download Article

Download Optimizing Memory Bandwidth on Stream Triad [PDF 647KB]


This document demonstrates the best methods to obtain peak memory bandwidth performance on the Intel® Xeon Phi™ coprocessor using the de facto industry standard benchmark for the measurement of computer memory bandwidth - “STREAM.”

  • Sviluppatori
  • Professori
  • Studenti
  • Server
  • C/C++
  • Compilatore C++ Intel®
  • Karthik Raman
  • Syntetic Benchmarks
  • Intel® Xeon Phi™ Coprocessor
  • Architettura Intel® Many Integrated Core
  • HPCC-stream performance loss with the 11.0 and 12.0 compilers

    The STREAM component of the HPCC benchmark suite runs more slowly with the initial release of the 11.0 compiler compared to version 10.1. This can be worked around by disabling function inlining. The COPY component showed a similar issue in 12.0.
  • Linux*
  • Apple OS X*
  • Microsoft Windows* (XP, Vista, 7)
  • C/C++
  • Fortran
  • Compilatore C++ Intel®
  • Compilatore Fortran Intel®
  • ClosedSWDefect
  • Ottimizzazione
  • Dissecting STREAM benchmark with Intel® Performance Counter Monitor

    Intel® Performance Counter Monitor (Intel® PCM) is an API and a set of tools that should help developers to understand how their applications utilize the underlying compute platform. In this blog I will explain how to instrument the well-known STREAM benchmark with library functions of Intel® PCM reading statistics directly from integrated memory controllers available on the latest Intel® Xeon® 5500, 5600, 7500 and Core™ processor series.

    Iscriversi a STREAM