Accelerating communication for parallel programming models on GPU systems

Jaemin Choi, Zane Fink, Sam White, Nitin Bhat, David F. Richards, Laxmikant V. Kale

Research output: Contribution to journalArticlepeer-review


As an increasing number of leadership-class systems embrace GPU accelerators in the race towards exascale, efficient communication of GPU data is becoming one of the most critical components of high-performance computing. For developers of parallel programming models, implementing support for GPU-aware communication using native APIs for GPUs such as CUDA can be a daunting task as it requires considerable effort with little guarantee of performance. In this work, we demonstrate the capability of the Unified Communication X (UCX) framework to compose a GPU-aware communication layer that serves multiple parallel programming models of the Charm++ ecosystem: Charm++, Adaptive MPI (AMPI), and Charm4py. We demonstrate the performance impact of our designs with microbenchmarks adapted from the OSU benchmark suite, obtaining improvements in latency of up to 10.1x in Charm++, 11.7x in AMPI, and 17.4x in Charm4py. We also observe increases in bandwidth of up to 10.1x in Charm++, 10x in AMPI, and 10.5x in Charm4py. We show the potential impact of our designs on real-world applications by evaluating a proxy application for the Jacobi iterative method, improving the communication performance by up to 12.4x in Charm++, 12.8x in AMPI, and 19.7x in Charm4py.

Original languageEnglish (US)
Article number102969
JournalParallel Computing
StatePublished - Oct 2022


  • AMPI
  • CUDA-aware MPI
  • Charm++
  • Charm4py
  • GPU-aware communication
  • Python
  • UCX

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computer Networks and Communications
  • Computer Graphics and Computer-Aided Design
  • Artificial Intelligence


Dive into the research topics of 'Accelerating communication for parallel programming models on GPU systems'. Together they form a unique fingerprint.

Cite this