Automated Scheduling Algorithm Selection and Chunk Parameter Calculation in OpenMP

doi:10.1109/TPDS.2022.3189270

2022-12-01

Ali Mohammed

Jonas H. Müller Korndörfer

Ahmed Eleliemy

Florina M. Ciorba *

DOI：10.1109/TPDS.2022.3189270

原文链接

原文求助

摘要

En 中文

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 (Korndorfer etal., 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 Auto4OMe 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 11% 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.

Keyword:

Automatic selection

algorithm selection problem

dynamic load balancing

self-scheduling

runtime library

OpenMP multithreaded programming

shared-memory systems