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

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 Val grind 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.

I. Introduction

Non-Uniform Memory Access (NUMA) architectures now dominate shared memory parallel computer platforms. In these systems a processing core can access nearby memory faster than remote memory. To achieve maximum aggregate memory bandwidth all processes must simultaneously access data from their closest memory location. As a consequence obtaining good performance from multithreaded codes in NUMA environments requires application codes to minimise access to remote data structures.