Reducing the Impact of Intensive Dynamic Memory Allocations in Parallel Multi-Threaded Programs

Frequent dynamic memory allocations (DyMAs) can significantly hinder the scalability of parallel multi-threaded programs. As the number of threads grows, DyMAs can even become the main performance bottleneck. We introduce modern tools and methods for evaluating the impact of DyMAs and present techni...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on parallel and distributed systems Jg. 31; H. 5; S. 1152 - 1164
Hauptverfasser: Langr, Daniel, Kocicka, Martin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.05.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Allocations
Benchmark testing
C++ languages
Computer simulation
Data structures
Dynamic memory allocation
Dynamic scheduling
Libraries
memory pooling
Message systems
multi-threading
Optimization
parallel program
Parallel programming
Runtime
scalable heap implementation
shared memory
small buffer optimization
Source code
ISSN:1045-9219, 1558-2183
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Frequent dynamic memory allocations (DyMAs) can significantly hinder the scalability of parallel multi-threaded programs. As the number of threads grows, DyMAs can even become the main performance bottleneck. We introduce modern tools and methods for evaluating the impact of DyMAs and present techniques for its reduction, which include scalable heap implementations, small buffer optimization, and memory pooling. Additionally, we provide a survey of state-of-the-art implementations of these techniques and study them experimentally by using a benchmark program, server simulator software, and a real-world high-performance computing application. As a result, we show that relatively small modifications in parallel program's source code or a way of its execution may substantially reduce the runtime overhead associated with the use of dynamic data structures.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1045-9219
1558-2183
DOI:10.1109/TPDS.2019.2960514