Auto-tuning 2D Stencil Applications on Multi-core Parallel Machines

Zhengxiong Hou 1, * Christian Pérez 1, *
* Corresponding author
1 AVALON - Algorithms and Software Architectures for Distributed and HPC Platforms
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : On multi-core clusters or supercomputers, how to get good performance when running high performance computing (HPC) applications is a main concern. In this report, performance oriented auto-tuning strategies and experimental results are presented for stencil HPC applications on multi-core parallel machines. A typical 2D Jacobi benchmark is chosen as the experimental stencil application. The main tuning strategies include data partitioning within a multi-core node, number of threads within a multi-core node, data partitioning for a number of nodes, number of nodes in a multi-core cluster system. The results of the experiments are based on multi-core parallel machines from PRACE or Grid'5000, such as Curie, and Stremi cluster.
Document type :
Other publications
Complete list of metadatas

https://hal.inria.fr/hal-00862270
Contributor : Christian Perez <>
Submitted on : Monday, September 16, 2013 - 12:46:42 PM
Last modification on : Friday, February 1, 2019 - 8:24:50 PM

Identifiers

  • HAL Id : hal-00862270, version 1

Collections

Citation

Zhengxiong Hou, Christian Pérez. Auto-tuning 2D Stencil Applications on Multi-core Parallel Machines. 2013. ⟨hal-00862270⟩

Share

Metrics

Record views

254