Redesigning GROMACS Halo Exchange: Improving Strong Scaling with GPU-initiated NVSHMEM

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Doijade, Mahesh, Alekseenko, Andrey, Brown, Ania, Gray, Alan, Páll, Szilárd
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909806781005824
author Doijade, Mahesh
Alekseenko, Andrey
Brown, Ania
Gray, Alan
Páll, Szilárd
author_facet Doijade, Mahesh
Alekseenko, Andrey
Brown, Ania
Gray, Alan
Páll, Szilárd
contents Improving time-to-solution in molecular dynamics simulations often requires strong scaling due to fixed-sized problems. GROMACS is highly latency-sensitive, with peak iteration rates in the sub-millisecond, making scalability on heterogeneous supercomputers challenging. MPI's CPU-centric nature introduces additional latencies on GPU-resident applications' critical path, hindering GPU utilization and scalability. To address these limitations, we present an NVSHMEM-based GPU kernel-initiated redesign of the GROMACS domain decomposition halo-exchange algorithm. Highly tuned GPU kernels fuse data packing and communication, leveraging hardware latency-hiding for fine-grained overlap. We employ kernel fusion across overlapped data forwarding communication phases and utilize the asynchronous copy engine over NVLink to optimize latency and bandwidth. Our GPU-resident formulation greatly increases communication-computation overlap, improving GROMACS strong scaling performance across NVLink by up to 1.5x (intra-node) and 2x (multi-node), and up to 1.3x multi-node over NVLink+InfiniBand. This demonstrates the profound benefits of GPU-initiated communication for strong-scaling a broad range of latency-sensitive applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21527
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Redesigning GROMACS Halo Exchange: Improving Strong Scaling with GPU-initiated NVSHMEM
Doijade, Mahesh
Alekseenko, Andrey
Brown, Ania
Gray, Alan
Páll, Szilárd
Distributed, Parallel, and Cluster Computing
Performance
Computational Physics
Improving time-to-solution in molecular dynamics simulations often requires strong scaling due to fixed-sized problems. GROMACS is highly latency-sensitive, with peak iteration rates in the sub-millisecond, making scalability on heterogeneous supercomputers challenging. MPI's CPU-centric nature introduces additional latencies on GPU-resident applications' critical path, hindering GPU utilization and scalability. To address these limitations, we present an NVSHMEM-based GPU kernel-initiated redesign of the GROMACS domain decomposition halo-exchange algorithm. Highly tuned GPU kernels fuse data packing and communication, leveraging hardware latency-hiding for fine-grained overlap. We employ kernel fusion across overlapped data forwarding communication phases and utilize the asynchronous copy engine over NVLink to optimize latency and bandwidth. Our GPU-resident formulation greatly increases communication-computation overlap, improving GROMACS strong scaling performance across NVLink by up to 1.5x (intra-node) and 2x (multi-node), and up to 1.3x multi-node over NVLink+InfiniBand. This demonstrates the profound benefits of GPU-initiated communication for strong-scaling a broad range of latency-sensitive applications.
title Redesigning GROMACS Halo Exchange: Improving Strong Scaling with GPU-initiated NVSHMEM
topic Distributed, Parallel, and Cluster Computing
Performance
Computational Physics
url https://arxiv.org/abs/2509.21527