ARS: an adaptive runtime system for locality optimization

  • Authors:

  • Jie Tao;Martin Schulz;Wolfgang Karl

  • Affiliations:

  • LRR-TUM, Institut für Informatik, Technische Universität München, 80290 München, Germany;LRR-TUM, Institut für Informatik, Technische Universität München, 80290 München, Germany;LRR-TUM, Institut für Informatik, Technische Universität München, 80290 München, Germany

  • Venue:
  • Future Generation Computer Systems - Tools for program development and analysis
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Shared memory programs running on Non-Uniform Memory Access (NUMA) machines usually face inherent performance problems stemming from excessive remote memory accesses. A solution, called the Adaptive Runtime System (ARS), is presented in this paper. ARS is designed to adjust the data distribution at runtime through automatic page migrations. It uses memory access histograms gathered by hardware monitors to find access hot spots and, based on this detection, to dynamically and transparently modify the data layout. In this way, incorrectly allocated data can be moved to the most appropriate node and hence data locality can be improved. Simulations show that this allows to achieve a performance gain of as high as 40%.