MPI Advance : Open-Source Message Passing Optimizations
Amanda Bienz, Derek Schafer, Anthony Skjellum

TL;DR
MPI Advance is an open-source library collection that enhances the performance of existing MPI implementations by providing optimized collectives, neighborhood collectives, partitioned communication, and GPU-aware communication, improving application efficiency.
Contribution
It introduces MPI Advance, a set of libraries that optimize the performance of any existing MPI implementation across various communication patterns.
Findings
Improved collective communication performance
Enhanced GPU-aware communication efficiency
Compatibility with multiple MPI implementations
Abstract
The large variety of production implementations of the message passing interface (MPI) each provide unique and varying underlying algorithms. Each emerging supercomputer supports one or a small number of system MPI installations, tuned for the given architecture. Performance varies with MPI version, but application programmers are typically unable to achieve optimal performance with local MPI installations and therefore rely on whichever implementation is provided as a system install. This paper presents MPI Advance, a collection of libraries that sit on top of MPI, optimizing the underlying performance of any existing MPI library. The libraries provide optimizations for collectives, neighborhood collectives, partitioned communication, and GPU-aware communication.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParallel Computing and Optimization Techniques · Distributed and Parallel Computing Systems · Advanced Data Storage Technologies
