Idle Period Propagation in Message-Passing Applications

TL;DR

This paper investigates how idle periods propagate between processes in message-passing applications, revealing wave-like behavior and self-synchronization phenomena that impact performance.

Contribution

It introduces a methodology to trace idle periods in MPI applications and applies it to demonstrate propagation patterns and synchronization effects.

Findings

Idle periods propagate as waves between processes.

Different stages of idle period propagation are identified.

Self-synchronization phenomena occur on some systems.

Abstract

Idle periods on different processes of Message Passing applications are unavoidable. While the origin of idle periods on a single process is well understood as the effect of system and architectural random delays, yet it is unclear how these idle periods propagate from one process to another. It is important to understand idle period propagation in Message Passing applications as it allows application developers to design communication patterns avoiding idle period propagation and the consequent performance degradation in their applications. To understand idle period propagation, we introduce a methodology to trace idle periods when a process is waiting for data from a remote delayed process in MPI applications. We apply this technique in an MPI application that solves the heat equation to study idle period propagation on three different systems. We confirm that idle periods move between processes in the form of waves and that there are different stages in idle period propagation. Our methodology enables us to identify a self-synchronization phenomenon that occurs on two systems where some processes run slower than the other processes.

Full text

See pages 1-last of HPCCidle.pdf