Performance Evaluation of Python Parallel Programming Models: Charm4Py and mpi4py

TL;DR

This paper compares the performance of two Python parallel programming frameworks, Charm4Py and mpi4py, across CPU and GPU microbenchmarks and mini-apps to inform practitioners about their relative strengths.

Contribution

It provides the first detailed comparative performance analysis of Charm4Py and mpi4py for scientific computing applications.

Findings

Charm4Py and mpi4py show different performance profiles on CPU and GPU.

Performance differences depend on specific microbenchmarks and mini-apps.

Results guide practitioners in selecting suitable Python parallel frameworks.

Abstract

Python is rapidly becoming the lingua franca of machine learning and scientific computing. With the broad use of frameworks such as Numpy, SciPy, and TensorFlow, scientific computing and machine learning are seeing a productivity boost on systems without a requisite loss in performance. While high-performance libraries often provide adequate performance within a node, distributed computing is required to scale Python across nodes and make it genuinely competitive in large-scale high-performance computing. Many frameworks, such as Charm4Py, DaCe, Dask, Legate Numpy, mpi4py, and Ray, scale Python across nodes. However, little is known about these frameworks' relative strengths and weaknesses, leaving practitioners and scientists without enough information about which frameworks are suitable for their requirements. In this paper, we seek to narrow this knowledge gap by studying the relative performance of two such frameworks: Charm4Py and mpi4py. We perform a comparative performance analysis of Charm4Py and mpi4py using CPU and GPU-based microbenchmarks other representative mini-apps for scientific computing.