Integrating External Resources with a Task-Based Programming Model

Accessing external resources (e.g., loading input data, checkpointing snapshots, and out-of-core processing) can have a significant impact on the performance of supercomputer applications. However, no existing programming systems for high-performance computing directly manage and optimize these exte...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings, 24th IEEE International Conference on High Performance Computing : 18-21 December 2017, Jaipur, India S. 307 - 316
Hauptverfasser: Jia, Zhihao, Treichler, Sean, Shipman, Galen, Bauer, Michael, Watkins, Noah, Maltzahn, Carlos, McCormick, Patrick, Aiken, Alex
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.12.2017
Schlagworte:
Coherence
Computational modeling
Deferred Execution
External Resource
I/O
Iris recognition
Programming
Runtime
Semantics
Task analysis
Task Based Programming Model
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Accessing external resources (e.g., loading input data, checkpointing snapshots, and out-of-core processing) can have a significant impact on the performance of supercomputer applications. However, no existing programming systems for high-performance computing directly manage and optimize these external accesses. As a result, users must explicitly manage external accesses alongside their computation at the application level, which can result in both correctness and performance issues. We address this limitation by introducing Iris, a task-based programming model with semantics for external resources. Iris allows applications to describe their access requirements to external resources and the relationship of those accesses to the computation. Iris incorporates external I/O into a deferred execution model, reschedules external I/O to overlap I/O with computation, and reduces external I/O when possible. We evaluate Iris on three microbenchmarks representative of important workloads in HPC and a full combustion simulation, S3D. We demonstrate that the Iris implementation of S3D reduces the external I/O overhead by up to 20×, compared to the Legion and the Fortran implementations.
DOI:10.1109/HiPC.2017.00043