Towards performance portability through locality-awareness for applications using one-sided communication primitives

TL;DR

This paper evaluates DART-MPI, a remote-memory-access model that simplifies locality-aware programming for one-sided communication, demonstrating its performance benefits over MPI-3 in multi-core supercomputing environments.

Contribution

The paper introduces and evaluates DART-MPI, a locality-aware, user-friendly remote-memory-access model that outperforms MPI-3 on multi-core systems, facilitating porting legacy applications.

Findings

DART-MPI outperforms MPI-3 in a heat diffusion simulation on Cray XC40.

DART-MPI simplifies locality-aware programming for one-sided communication.

The model effectively hides complexity and improves performance on multi-core architectures.

Abstract

MPI is the most widely used data transfer and communication model in High Performance Computing. The latest version of the standard, MPI-3, allows skilled programmers to exploit all hardware capabilities of the latest and future supercomputing systems. The revised asynchronous remote-memory-access model in combination with the shared-memory window extension, in particular, allow writing code that hides communication latencies and optimizes communication paths according to the locality of data origin and destination. The latter is particularly important for today's multi- and many-core systems. However, writing such efficient code is highly complex and error-prone. In this paper we evaluate a recent remote-memory-access model, namely DART-MPI. This model claims to hide the aforementioned complexities from the programmer, but deliver locality-aware remote-memory-access semantics which outperforms MPI-3 one-sided communication primitives on multi-core systems. Conceptually, the DART-MPI interface is simple; at the same time it takes care of the complexities of the underlying MPI-3 and system topology. This makes DART-MPI an interesting candidate for porting legacy applications. We evaluate these claims using a realistic scientific application, specifically a finite-difference stencil code which solves the heat diffusion equation, on a large-scale Cray XC40 installation.