Simulating many-engine spacecraft: Exceeding 1 quadrillion degrees of freedom via information geometric regularization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wilfong, Benjamin, Radhakrishnan, Anand, Berre, Henry Le, Vickers, Daniel J., Prathi, Tanush, Tselepidis, Nikolaos, Dorschner, Benedikt, Budiardja, Reuben, Cornille, Brian, Abbott, Stephen, Schäfer, Florian, Bryngelson, Spencer H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914172977020928
author Wilfong, Benjamin
Radhakrishnan, Anand
Berre, Henry Le
Vickers, Daniel J.
Prathi, Tanush
Tselepidis, Nikolaos
Dorschner, Benedikt
Budiardja, Reuben
Cornille, Brian
Abbott, Stephen
Schäfer, Florian
Bryngelson, Spencer H.
author_facet Wilfong, Benjamin
Radhakrishnan, Anand
Berre, Henry Le
Vickers, Daniel J.
Prathi, Tanush
Tselepidis, Nikolaos
Dorschner, Benedikt
Budiardja, Reuben
Cornille, Brian
Abbott, Stephen
Schäfer, Florian
Bryngelson, Spencer H.
contents We present an optimized implementation of the recently proposed information geometric regularization (IGR) for unprecedented scale simulation of compressible fluid flows applied to multi-engine spacecraft boosters. We improve upon state-of-the-art computational fluid dynamics (CFD) techniques along computational cost, memory footprint, and energy-to-solution metrics. Unified memory on coupled CPU--GPU or APU platforms increases problem size with negligible overhead. Mixed half/single-precision storage and computation on well-conditioned numerics is used. We simulate flow at 200 trillion grid points and 1 quadrillion degrees of freedom, exceeding the current record by a factor of 20. A factor of 4 wall-time speedup is achieved over optimized baselines. Ideal weak scaling is seen on OLCF Frontier, LLNL El Capitan, and CSCS Alps using the full systems. Strong scaling is near ideal at extreme conditions, including 80% efficiency on CSCS Alps with an 8-node baseline and stretching to the full system.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07392
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Simulating many-engine spacecraft: Exceeding 1 quadrillion degrees of freedom via information geometric regularization
Wilfong, Benjamin
Radhakrishnan, Anand
Berre, Henry Le
Vickers, Daniel J.
Prathi, Tanush
Tselepidis, Nikolaos
Dorschner, Benedikt
Budiardja, Reuben
Cornille, Brian
Abbott, Stephen
Schäfer, Florian
Bryngelson, Spencer H.
Computational Physics
Computational Engineering, Finance, and Science
Fluid Dynamics
We present an optimized implementation of the recently proposed information geometric regularization (IGR) for unprecedented scale simulation of compressible fluid flows applied to multi-engine spacecraft boosters. We improve upon state-of-the-art computational fluid dynamics (CFD) techniques along computational cost, memory footprint, and energy-to-solution metrics. Unified memory on coupled CPU--GPU or APU platforms increases problem size with negligible overhead. Mixed half/single-precision storage and computation on well-conditioned numerics is used. We simulate flow at 200 trillion grid points and 1 quadrillion degrees of freedom, exceeding the current record by a factor of 20. A factor of 4 wall-time speedup is achieved over optimized baselines. Ideal weak scaling is seen on OLCF Frontier, LLNL El Capitan, and CSCS Alps using the full systems. Strong scaling is near ideal at extreme conditions, including 80% efficiency on CSCS Alps with an 8-node baseline and stretching to the full system.
title Simulating many-engine spacecraft: Exceeding 1 quadrillion degrees of freedom via information geometric regularization
topic Computational Physics
Computational Engineering, Finance, and Science
Fluid Dynamics
url https://arxiv.org/abs/2505.07392