English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As an increasing number of leadership-class systems embrace GPU acceleratorsin the race towards exascale, efficient communication of GPU data is becomingone of the most critical components of high-performance computing. Fordevelopers of parallel programming models, implementing support for GPU-awarecommunication using native APIs for GPUs such as CUDA can be a daunting task asit requires considerable effort with little guarantee of performance. In thiswork, we demonstrate the capability of the Unified Communication X (UCX)framework to compose a GPU-aware communication layer that serves multipleparallel programming models of the Charm++ ecosystem: Charm++, Adaptive MPI(AMPI), and Charm4py. We demonstrate the performance impact of our designs withmicrobenchmarks adapted from the OSU benchmark suite, obtaining improvements inlatency of up to 10.1x in Charm++, 11.7x in AMPI, and 17.4x in Charm4py. Wealso observe increases in bandwidth of up to 10.1x in Charm++, 10x in AMPI, and10.5x in Charm4py. We show the potential impact of our designs on real-worldapplications by evaluating a proxy application for the Jacobi iterative method,improving the communication performance by up to 12.4x in Charm++, 12.8x inAMPI, and 19.7x in Charm4py.

Accelerating Communication for Parallel Programming Models on GPU Systems