Not all applications have boring communication patterns: Profiling message matching with BMM
| Autor: | David Trebotich, Brandon Cook, Noel Keen, Naveen Ravichandrasekaran, Taylor Groves, Nicholas J. Wright, Duncan Roweth, Bob Alverson, Keith Underwood |
|---|---|
| Rok vydání: | 2023 |
| Předmět: |
Profiling (computer programming)
Matching (statistics) Artificial Intelligence and Image Processing Computer Networks and Communications Computer science offload NIC tag matching computer.software_genre Computer Science Applications Theoretical Computer Science Computer Software message matching Computational Theory and Mathematics MPI Data mining Distributed Computing computer Software |
| Zdroj: | Concurrency and Computation Practice and Experience, vol 35, iss 15 |
| Popis: | Message matching within MPI is an important performance consideration for applications that utilize two-sided semantics. In this work, we present an instrumentation of the CrayMPI library that allows the collection of detailed message-matching statistics as well as an implementation of hashed matching in software. We use this functionality to profile key DOE applications with complex communication patterns to determine under what circumstances an application might benefit from hardware offload capabilities within the NIC to accelerate message matching. We find that there are several applications and libraries that exhibit sufficiently long match list lengths to motivate a Binned Message Matching approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|