Neon

While multi-GPU systems are effective at accelerating simulations, achieving the best performance and scalability has its challenges. Along with domain expertise, a strong knowledge of parallel programming is required. Neon is a new framework designed to make multi-GPU programming easier and more intuitive for non-GPU experts. Neon is based on a structured parallel model that primarily targets simulation on cartesian grids. Neon efficiently hides the complexity of managing a domain that is partitioned across multi-GPU and more.

Abstract

Neon: A Multi-GPU Programming Model for Grid-based Computations

Massimiliano Meneghin, Ahmed H. Mahmoud, Pradeep Kumar Jayaraman, Nigel J. W. Morris

IPDPS – IEEE International Parallel & Distributed Processing Symposium 2022

We present Neon, a new programming model for grid-based computation with an intuitive, easy-to-use interface that allows domain experts to take full advantage of single-node multi-GPU systems. Neon decouples data structure from computation and back end configurations, allowing the same user code to operate on a variety of data structures and devices. Neon relies on a set of hierarchical abstractions that allow the user to write their applications as if they were sequential applications, while the runtime handles distribution across multiple GPUs and performs optimizations such as overlapping computation and communication without user intervention. We evaluate our programming model on several applications: a Lattice Boltzmann fluid solver, a finite-difference Poisson solver and a finite-element linear elastic solver. We show that these applications can be implemented concisely and scale well with the number of GPUs—achieving more than 99% of ideal efficiency.