PCLVis: Visual Analytics of Process Communication Latency in Large-Scale Simulation

TL;DR

PCLVis is a visual analytics framework that helps users analyze process communication latency in large-scale simulations using MPI data, enabling better understanding and optimization of communication events without needing physical link layer info.

Contribution

The paper introduces PCLVis, a novel framework that analyzes process communication latency using MPI data, with new methods for event localization, propagation analysis, and interactive visualization.

Findings

Effective analysis of PCL events on supercomputers.

Improved simulation efficiency through PCL event insights.

Demonstrated success on TH-1A supercomputer.

Abstract

Large-scale simulations on supercomputers have become important tools for users. However, their scalability remains a problem due to the huge communication cost among parallel processes. Most of the existing communication latency analysis methods rely on the physical link layer information, which is only available to administrators. In this paper, a framework called PCLVis is proposed to help general users analyze process communication latency (PCL) events. Instead of the physical link layer information, the PCLVis uses the MPI process communication data for the analysis. First, a spatial PCL event locating method is developed. All processes with high correlation are classified into a single cluster by constructing a process-correlation tree. Second, the propagation path of PCL events is analyzed by constructing a communication-dependency-based directed acyclic graph (DAG), which can help users interactively explore a PCL event from the temporal evolution of a located PCL event cluster. In this graph, a sliding window algorithm is designed to generate the PCL events abstraction. Meanwhile, a new glyph called the communication state glyph (CS-Glyph) is designed for each process to show its communication states, including its in/out messages and load balance. Each leaf node can be further unfolded to view additional information. Third, a PCL event attribution strategy is formulated to help users optimize their simulations. The effectiveness of the PCLVis framework is demonstrated by analyzing the PCL events of several simulations running on the TH-1A supercomputer. By using the proposed framework, users can greatly improve the efficiency of their simulations.