Scalability of Gaussian 03 on SGI Altix: The Importance of Data Locality on CC-NUMA Architecture

Gomperts, Roberto; Frisch, Michael J.; Panziera, Jean-Pierre

doi:10.1007/978-3-642-02303-3_8

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…G09 is chosen as an exemplar application since it is a complex code with over one million lines of source. It is widely used 2 and in previous work it has been shown to be sensitive to memory and thread placement on NUMA platforms [15]- [18].…”

Section: Introductionmentioning

confidence: 99%

Profiling Directed NUMA Optimization on Linux Systems: A Case Study of the Gaussian Computational Chemistry Code

Yang

Antony

Rendell

et al. 2011

2011 IEEE International Parallel &Amp; Distributed Processing Symposium

View full text Add to dashboard Cite

The parallel performance of applications running on Non-Uniform Memory Access (NUMA) platforms is strongly influenced by the relative placement of memory pages to the threads that access them. As a consequence there are Linux application programmer interfaces (APIs) to control this. For large parallel codes it can, however, be difficult to determine how and when to use these APIs. In this paper we introduce the NUMAgrind profiling tool which can be used to simplify this process. It extends the Valgrind binary translation framework to include a model which incorporates cache coherency, memory locality domains and interconnect traffic for arbitrary NUMA topologies. Using NUMAgrind, cache misses can be mapped to memory locality domains, page access modes determined, and pages that are referenced by multiple threads quickly determined. We show how the NUMAgrind tool can be used to guide the use of Linux memory and thread placement APIs in the Gaussian computational chemistry code. The performance of the code before and after use of these APIs is also presented for three different commodity NUMA platforms.

show abstract

Section: Introductionmentioning

confidence: 99%