Automatic Performance Debugging of SPMD-style Parallel Programs

TL;DR

AutoAnalyzer is a system that automatically detects, locates, and explains performance bottlenecks in SPMD-style parallel programs without prior knowledge, using lightweight data analysis and innovative algorithms.

Contribution

The paper introduces new clustering and searching algorithms, and a root cause analysis method based on rough set theory, for automated performance debugging of parallel programs.

Findings

Effective bottleneck detection and root cause identification demonstrated on real applications.

Lightweight data collection reduces overhead in performance analysis.

Automated debugging improves efficiency and accuracy in optimizing parallel programs.

Abstract

The simple program and multiple data (SPMD) programming model is widely used for both high performance computing and Cloud computing. In this paper, we design and implement an innovative system, AutoAnalyzer, that automates the process of debugging performance problems of SPMD-style parallel programs, including data collection, performance behavior analysis, locating bottlenecks, and uncovering their root causes. AutoAnalyzer is unique in terms of two features: first, without any apriori knowledge, it automatically locates bottlenecks and uncovers their root causes for performance optimization; second, it is lightweight in terms of the size of performance data to be collected and analyzed. Our contributions are three-fold: first, we propose two effective clustering algorithms to investigate the existence of performance bottlenecks that cause process behavior dissimilarity or code region behavior disparity, respectively; meanwhile, we present two searching algorithms to locate bottlenecks; second, on a basis of the rough set theory, we propose an innovative approach to automatically uncovering root causes of bottlenecks; third, on the cluster systems with two different configurations, we use two production applications, written in Fortran 77, and one open source code-MPIBZIP2 (http://compression.ca/mpibzip2/), written in C++, to verify the effectiveness and correctness of our methods. For three applications, we also propose an experimental approach to investigating the effects of different metrics on locating bottlenecks.