-
Benchmarking AI-evolved cosmological structure formation
Authors:
Xiaofeng Dong,
Nesar Ramachandra,
Salman Habib,
Katrin Heitmann
Abstract:
The potential of deep learning-based image-to-image translations has recently attracted significant attention. One possible application of such a framework is as a fast, approximate alternative to cosmological simulations, which would be particularly useful in various contexts, including covariance studies, investigations of systematics, and cosmological parameter inference. To investigate differe…
▽ More
The potential of deep learning-based image-to-image translations has recently attracted significant attention. One possible application of such a framework is as a fast, approximate alternative to cosmological simulations, which would be particularly useful in various contexts, including covariance studies, investigations of systematics, and cosmological parameter inference. To investigate different aspects of learning-based cosmological mappings, we choose two approaches for generating suitable cosmological matter fields as datasets: a simple analytical prescription provided by the Zel'dovich approximation, and a numerical N-body method using the Particle-Mesh approach. The evolution of structure formation is modeled using U-Net, a widely employed convolutional image translation framework. Because of the lack of a controlled methodology, validation of these learned mappings requires multiple benchmarks beyond simple visual comparisons and summary statistics. A comprehensive list of metrics is considered, including higher-order correlation functions, conservation laws, topological indicators, and statistical independence of density fields. We find that the U-Net approach performs well only for some of these physical metrics, and accuracy is worse at increasingly smaller scales, where the dynamic range in density is large. By introducing a custom density-weighted loss function during training, we demonstrate a significant improvement in the U-Net results at smaller scales. This study provides an example of how a family of physically motivated benchmarks can, in turn, be used to fine-tune optimization schemes -- such as the density-weighted loss used here -- to significantly enhance the accuracy of scientific machine learning approaches by focusing attention on relevant features.
△ Less
Submitted 10 October, 2025; v1 submitted 8 October, 2025;
originally announced October 2025.
-
Cosmological Hydrodynamics at Exascale: A Trillion-Particle Leap in Capability
Authors:
Nicholas Frontiere,
J. D. Emberson,
Michael Buehlmann,
Esteban M. Rangel,
Salman Habib,
Katrin Heitmann,
Patricia Larsen,
Vitali Morozov,
Adrian Pope,
Claude-André Faucher-Giguère,
Antigoni Georgiadou,
Damien Lebrun-Grandié,
Andrey Prokopenko
Abstract:
Resolving the most fundamental questions in cosmology requires simulations that match the scale, fidelity, and physical complexity demanded by next-generation sky surveys. To achieve the realism needed for this critical scientific partnership, detailed gas dynamics, along with a host of astrophysical effects, must be treated self-consistently with gravity for end-to-end modeling of structure forma…
▽ More
Resolving the most fundamental questions in cosmology requires simulations that match the scale, fidelity, and physical complexity demanded by next-generation sky surveys. To achieve the realism needed for this critical scientific partnership, detailed gas dynamics, along with a host of astrophysical effects, must be treated self-consistently with gravity for end-to-end modeling of structure formation. As an important step on this roadmap, exascale computing enables simulations that span survey-scale volumes while incorporating key subgrid processes that shape complex cosmic structures. We present results from CRK-HACC, a cosmological hydrodynamics code built for the extreme scalability requirements set by modern cosmological surveys. Using separation-of-scale techniques, GPU-resident tree solvers, in situ analysis pipelines, and multi-tiered I/O, CRK-HACC executed Frontier-E: a four trillion particle full-sky simulation, over an order of magnitude larger than previous efforts. The run achieved 513.1 PFLOPs peak performance, processing 46.6 billion particles per second and writing more than 100 PB of data in just over one week of runtime.
△ Less
Submitted 3 October, 2025;
originally announced October 2025.
-
ASCR/HEP Exascale Requirements Review Report
Authors:
Salman Habib,
Robert Roser,
Richard Gerber,
Katie Antypas,
Katherine Riley,
Tim Williams,
Jack Wells,
Tjerk Straatsma,
A. Almgren,
J. Amundson,
S. Bailey,
D. Bard,
K. Bloom,
B. Bockelman,
A. Borgland,
J. Borrill,
R. Boughezal,
R. Brower,
B. Cowan,
H. Finkel,
N. Frontiere,
S. Fuess,
L. Ge,
N. Gnedin,
S. Gottlieb
, et al. (29 additional authors not shown)
Abstract:
This draft report summarizes and details the findings, results, and recommendations derived from the ASCR/HEP Exascale Requirements Review meeting held in June, 2015. The main conclusions are as follows. 1) Larger, more capable computing and data facilities are needed to support HEP science goals in all three frontiers: Energy, Intensity, and Cosmic. The expected scale of the demand at the 2025 ti…
▽ More
This draft report summarizes and details the findings, results, and recommendations derived from the ASCR/HEP Exascale Requirements Review meeting held in June, 2015. The main conclusions are as follows. 1) Larger, more capable computing and data facilities are needed to support HEP science goals in all three frontiers: Energy, Intensity, and Cosmic. The expected scale of the demand at the 2025 timescale is at least two orders of magnitude -- and in some cases greater -- than that available currently. 2) The growth rate of data produced by simulations is overwhelming the current ability, of both facilities and researchers, to store and analyze it. Additional resources and new techniques for data analysis are urgently needed. 3) Data rates and volumes from HEP experimental facilities are also straining the ability to store and analyze large and complex data volumes. Appropriately configured leadership-class facilities can play a transformational role in enabling scientific discovery from these datasets. 4) A close integration of HPC simulation and data analysis will aid greatly in interpreting results from HEP experiments. Such an integration will minimize data movement and facilitate interdependent workflows. 5) Long-range planning between HEP and ASCR will be required to meet HEP's research needs. To best use ASCR HPC resources the experimental HEP program needs a) an established long-term plan for access to ASCR computational and data resources, b) an ability to map workflows onto HPC resources, c) the ability for ASCR facilities to accommodate workflows run by collaborations that can have thousands of individual members, d) to transition codes to the next-generation HPC platforms that will be available at ASCR facilities, e) to build up and train a workforce capable of developing and using simulations and analysis to support HEP scientific research on next-generation systems.
△ Less
Submitted 31 March, 2016; v1 submitted 30 March, 2016;
originally announced March 2016.
-
The Universe at Extreme Scale: Multi-Petaflop Sky Simulation on the BG/Q
Authors:
Salman Habib,
Vitali Morozov,
Hal Finkel,
Adrian Pope,
Katrin Heitmann,
Kalyan Kumaran,
Tom Peterka,
Joe Insley,
David Daniel,
Patricia Fasel,
Nicholas Frontiere,
Zarija Lukic
Abstract:
Remarkable observational advances have established a compelling cross-validated model of the Universe. Yet, two key pillars of this model -- dark matter and dark energy -- remain mysterious. Sky surveys that map billions of galaxies to explore the `Dark Universe', demand a corresponding extreme-scale simulation capability; the HACC (Hybrid/Hardware Accelerated Cosmology Code) framework has been de…
▽ More
Remarkable observational advances have established a compelling cross-validated model of the Universe. Yet, two key pillars of this model -- dark matter and dark energy -- remain mysterious. Sky surveys that map billions of galaxies to explore the `Dark Universe', demand a corresponding extreme-scale simulation capability; the HACC (Hybrid/Hardware Accelerated Cosmology Code) framework has been designed to deliver this level of performance now, and into the future. With its novel algorithmic structure, HACC allows flexible tuning across diverse architectures, including accelerated and multi-core systems.
On the IBM BG/Q, HACC attains unprecedented scalable performance -- currently 13.94 PFlops at 69.2% of peak and 90% parallel efficiency on 1,572,864 cores with an equal number of MPI ranks, and a concurrency of 6.3 million. This level of performance was achieved at extreme problem sizes, including a benchmark run with more than 3.6 trillion particles, significantly larger than any cosmological simulation yet performed.
△ Less
Submitted 19 November, 2012;
originally announced November 2012.