Automated Scheduling Algorithm Selection and Chunk Parameter Calculation in OpenMP

Increasing node and cores-per-node counts in supercomputers render scheduling and load balancing critical for exploiting parallelism. OpenMP applications can achieve high performance via careful selection of scheduling kind and chunk parameters on a per-loop, per-application, and per-system basis fr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on parallel and distributed systems Ročník 33; číslo 12; s. 4383 - 4394
Hlavní autoři: Mohammed, Ali, Korndorfer, Jonas H. Muller, Eleliemy, Ahmed, Ciorba, Florina M.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
algorithm selection problem
Algorithms
Automatic selection
Automation
dynamic load balancing
Dynamic scheduling
Heuristic algorithms
Load balancing
Load management
Mathematical analysis
multithreaded programming
OpenMP
Parallel processing
Parameters
Runtime library
Schedules
Scheduling
Scheduling algorithms
self-scheduling
shared-memory systems
Supercomputers
ISSN:1045-9219, 1558-2183
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Increasing node and cores-per-node counts in supercomputers render scheduling and load balancing critical for exploiting parallelism. OpenMP applications can achieve high performance via careful selection of scheduling kind and chunk parameters on a per-loop, per-application, and per-system basis from a portfolio of advanced scheduling algorithms (Korndörfer et al. , 2022). This selection approach is time-consuming, challenging, and may need to change during execution. We propose Auto4OMP , a novel approach for automated load balancing of OpenMP applications. With Auto4OMP, we introduce three scheduling algorithm selection methods and an expert-defined chunk parameter for OpenMP's schedule clause's kind and chunk , respectively. Auto4OMP extends the OpenMP schedule(auto) and chunk parameter implementation in LLVM's OpenMP runtime library to automatically select a scheduling algorithm and calculate a chunk parameter during execution. Loop characteristics are inferred in Auto4OMP from the loop execution over the application's time-steps. The experiments performed in this work show that Auto4OMP improves applications performance by up to <inline-formula><tex-math notation="LaTeX">11\%</tex-math> <mml:math><mml:mrow><mml:mn>11</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="ciorba-ieq1-3189270.gif"/> </inline-formula> compared to LLVM's schedule(auto) implementation and outperforms manual selection. Auto4OMP improves MPI+OpenMP applications performance by explicitly minimizing thread- and implicitly reducing process-load imbalance.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1045-9219
1558-2183
DOI:10.1109/TPDS.2022.3189270