Supporting OpenMP 5.0 Tasks in hpxMP -- A study of an OpenMP implementation within Task Based Runtime Systems

TL;DR

This paper explores implementing OpenMP 5.0 tasks within the hpxMP runtime, addressing challenges of integrating OpenMP with asynchronous task-based systems to improve performance and compatibility.

Contribution

It introduces task features of OpenMP 5.0 in hpxMP and optimizes parallel for execution, enhancing integration with task-based runtime systems.

Findings

hpxMP supports OpenMP 5.0 task features effectively

Optimizations improve parallel for performance

Comparative benchmarks show competitive results

Abstract

OpenMP has been the de facto standard for single node parallelism for more than a decade. Recently, asynchronous many-task runtime (AMT) systems have increased in popularity as a new programming paradigm for high performance computing applications. One of the major challenges of this new paradigm is the incompatibility of the OpenMP thread model and other AMTs. Highly optimized OpenMP-based libraries do not perform well when coupled with AMTs because the threading of both libraries will compete for resources. This paper is a follow-up paper on the fundamental implementation of hpxMP, an implementation of the OpenMP standard which utilizes the C++ standard library for Parallelism and Concurrency (HPX) to schedule and manage tasks. In this paper, we present the implementation of task features, e.g. taskgroup, task depend, and task_reduction, of the OpenMP 5.0 standard and optimization of the #pragma omp parallel for pragma. We use the daxpy benchmark, the Barcelona OpenMP Tasks Suite, Parallel research kernels, and OpenBLAS benchmarks to compare the different OpenMp implementations: hpxMP, llvm-OpenMP, and GOMP.