Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “parallel machines”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Spotlight: efficient automated global optimization in rietveld analysis of diffraction data

Performing reliable Rietveld analysis on tens or hundreds of powder diffraction datasets from parametric or time-resolved experiments often poses a bottleneck in extracting meaningful results from the data. While automated analysis of data has recently been demonstrated, high temperature annealing studies, during which phase transformations occur and lattice parameters may change due to repartitioning of elements, are prime examples where automation by a simple phase identification from a database of room temperature structures or automation by sequential refinements is likely to fail. To enable reliable, efficient, automated Rietveld analysis, we present a Python package named Spotlight , building on established Rietveld packages such as MAUD, GSAS , or GSAS-II , which extends the refinement of best fit parameters to a global optimization using an ensemble of optimizers leveraging hierarchical parallel execution on high-performance computing clusters. Spotlight further enables the efficient design of refinement plans through the iterative automated machine-learning of a surrogate for the refinement on which the global optimizations are performed until results from the surrogate converge to the response surface data. We demonstrate Spotlight with the analysis of uranium molybdenum and Ti–6Al–4V datasets, as well as in two open-source tutorials analyzing aluminium oxide and lead sulphate.

36 MATERIALS SCIENCE↗
DOE OSTI2024

PaRSEC: Scalability, flexibility, and hybrid architecture support for task-based applications in ECP

This paper highlights the most significant enhancements made to PaRSEC, a scalable task-based runtime system designed for hybrid machines, during the Exascale Computing Project (ECP). The enhancements focus on expanding the capabilities of PaRSEC to address the evolving landscape of parallel computing. Notable achievements include the integration of support for three major types of accelerators (NVIDIA, AMD, and Intel GPUs), the refinement and increased flexibility of the communication subsystem, and the introduction of new programming interfaces tailored for irregular applications. Additionally, the project resulted in the development of powerful debugging and performance analysis tools aimed at assisting users in understanding and optimizing their applications. We present a comprehensive demonstration of these advancements through a series of benchmarks and applications within ECP and beyond, thereby showcasing the enhanced capabilities of PaRSEC across the diverse architectures within the ECP, providing valuable insights into the runtime system’s adaptability and performance across varied computing environments.

Bouteiller, Aurelien↗
DOE OSTI2022

Machine Learning Assisted HPC Workload Trace Generation for Leadership Scale Storage Systems

Monitoring and analyzing a wide range of I/O activities in an HPC cluster is important in maintaining mission-critical performance in a large-scale, multi-user, parallel storage system. Center-wide I/O traces can provide high-level information and fine-grained activities per application or per user running in the system. Studying such large-scale traces can provide helpful insights into the system. It can be used to develop predictive methods for making predictive decisions, adjusting scheduling policies, or providing decisions for the design of next-generation systems. However, sharing real-world I/O traces to expedite such research efforts leaves a few concerns; i) the cost of sharing the large traces is expensive due to this large size, and ii) privacy concern is an issue.We address such issues by building an end-to-end machine learn- ing (ML) workflow that can generate I/O traces for large-scale HPC applications. We leverage ML based feature selection and gener- ative models for I/O trace generation. The generative models are trained on I/O traces collected by the darshan I/O characterization tool over a period of one year. We present a two-step generation process consisting of two deep-learning models, called the feature generator and the trace generator. The combination of two-step generative models provides robustness by reducing the bias of the model and accounting for the stochastic nature of the I/O traces across different runs of an application. We evaluate the performance of the generative models and show that the two-step model can generate time-series I/O traces with less than 20% root mean square error.

Paul, Arnab↗
DOE OSTI2022

Training data selection for accuracy and transferability of interatomic potentials

Abstract Advances in machine learning (ML) have enabled the development of interatomic potentials that promise the accuracy of first principles methods and the low-cost, parallel efficiency of empirical potentials. However, ML-based potentials struggle to achieve transferability, i.e., provide consistent accuracy across configurations that differ from those used during training. In order to realize the promise of ML-based potentials, systematic and scalable approaches to generate diverse training sets need to be developed. This work creates a diverse training set for tungsten in an automated manner using an entropy optimization approach. Subsequently, multiple polynomial and neural network potentials are trained on the entropy-optimized dataset. A corresponding set of potentials are trained on an expert-curated dataset for tungsten for comparison. The models trained to the entropy-optimized data exhibited superior transferability compared to the expert-curated models. Furthermore, the models trained to the expert-curated set exhibited a significant decrease in performance when evaluated on out-of-sample configurations.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Direct NeTS sampling of nuclear graphite $S(α, β, T)$ in Serpent

For advanced reactor applications, Neural Thermal Scattering (NeTS) modules were developed to predict the thermal scattering law (TSL or $S(α, β, T)$) of a nuclear graphite neutron moderator. NeTS are multi-layer, feedforward artificial neural networks, which act as universal function approximators designed for TSL datasets. In this case, a 4-layer neural network with 164 neurons per layer is trained using FLASSH evaluated data in PyTorch and serialized as a torchscript dictionary to predict $S(α, β, T)$ on-the-fly. Relative, absolute and maximum percent deviations of NeTS from File 7 data generated using the FLASSH code are on the order of 0.01%, 0.1% and 1%, respectively, with low inference latencies of 0.000172 s per $S(α, β, T)$ at a given temperature. Capturing the full dimensionality of possible inelastic neutron-lattice interactions, NeTS functionality is embedded in the Serpent Monte Carlo code, where $S(α, β, T)_{NeTS}$ sampling is conducted on-the-fly and compared to ACE look-up-tables for predicting TREAT criticality. k-eff differences between sampling algorithms of 6 pcm are observed and are within the order of Monte Carlo uncertainty. Compared to discrete and continuous-energy ACE files (30 MB and 131 MB per temperature), the NeTS format is on the order of 200–300 kB for a continuous-temperature, interpolation-free representation of $S(α, β, T)$ and cross sections. NeTS-in-Serpent runtimes comparable with ACE look-up tables are achieved by scaling NeTS for high performance computing architectures with hybrid OpenMP + MPI parallelization. This work validates a novel, self-contained reactor physics framework for predictive cross sections, and demonstrates a general methodology for embedding modern machine learning libraries within existing neutronic analysis frameworks.

Nuclear Criticality Safety Program (NCSP)↗
DOE OSTI2020

Predictive Inverse Model for Advective Heat Transfer in a Short–Circuited Fracture: Dimensional Analysis, Machine Learning, and Field Demonstration

Identifying fluid flow maldistribution in planar geometries is a well–established problem in subsurface science/engineering. Of particular importance to the thermal performance of enhanced (or “engineered”) geothermal systems is identifying the existence of nonuniform (i.e., heterogeneous) permeability and subsequently predicting advective heat transfer. Here, machine learning via a genetic algorithm (GA) identifies the spatial distribution of an unknown permeability field in a two–dimensional Hele–Shaw geometry (i.e., parallel plates). The inverse problem is solved by minimizing the L2 norm between simulated residence time distribution (RTD) and measurements of an inert tracer breakthrough curve (BTC) (C–Dot nanoparticle). Principal component analysis (PCA) of spatially correlated permeability fields enabled reduction of the parameter space by more than a factor of 10 and restricted the inverse search to reservoir–scale permeability variations. Thermal experiments and tracer tests conducted at the mesoscale Altona Field Laboratory (AFL) demonstrate that the method accurately predicts the effects of extreme flow channeling on heat transfer in a single bedding–plane rock fracture. However, this is only true when the permeability distributions provide adequate matches to both tracer RTD and frictional pressure loss. Without good agreement to frictional pressure loss, it is still possible to match a simulated RTD to measurements, but subsequent predictions of heat transfer are grossly inaccurate. Here, the results of this study suggest that it is possible to anticipate the thermal effects of flow maldistribution, but only if both simulated RTDs and frictional pressure loss between fluid inlets and outlets are in good agreement with measurements.

42 ENGINEERING↗
DOE OSTI2021

Observational Capabilities to Capture Water Cycle Event Dynamics and Impacts in the Age of AI

This whitepaper is responsive to focal area (1) Data acquisition and assimilation enabled by machine learning (ML), Artificial Intelligence (AI), and advanced methods. Here we describe how Earth observations specific to water cycle disturbances can be collected in parallel with and integrated into future model development, and make use of the latest technologies other than AI/ ML such as 5G/satellite, edge computing, big data technologies, and cloud computing.

58 GEOSCIENCES↗
DOE OSTI2024

Performance on HPC Platforms Is Possible Without C++

Computing at large scales has become extremely challenging due to increasing heterogeneity in both hardware and software. More and more scientific workflows must tackle a range of scales and use machine learning and AI intertwined with more traditional numerical modeling methods, placing more demands on computational platforms. These constraints indicate a need to fundamentally rethink the way computational science is done and the tools that are needed to enable these complex workflows. The current set of C++-based solutions may not suffice, and relying exclusively upon C++ may not be the best option, especially because several newer languages and boutique solutions offer more robust design features to tackle the challenges of heterogeneity. In June 2023, we held a mini symposium that explored the use of newer languages and heterogeneity solutions that are not tied to C++ and that offer options beyond template metaprogramming and Parallel. For for performance and portability. In conclusion, we describe some of the presentations and discussion from the mini symposium in this article.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

COMPOFF: A Compiler Cost model using Machine Learning to predict the Cost of OpenMP Offloading

The HPC industry is inexorably moving towards an era of extremely heterogeneous architectures, with more devices configured on any given HPC platform and potentially more kinds of devices, some of them highly specialized. Writing a separate code suitable for each target system for a given HPC application is not practical. The better solution is to use directive-based parallel programming models such as OpenMP. OpenMP provides a number of options for offloading a piece of code to devices like GPUs. To select the best option from such options during compilation, most modern compilers use analytical models to estimate the cost of executing the original code and the different offloading code variants. Building such an analytical model for compilers is a difficult task that necessitates a lot of effort on the part of a compiler engineer. Recently, machine learning techniques have been successfully applied to build cost models for a variety of compiler optimization problems. In this paper, we present COMPOFF, a cost model which uses the multi-layer perceptrons to statically estimates the Cost of OpenMP OFFloading. We used six different transformations on a parallel code of Wilson Dslash Operator to support GPU offloading, and we predicted their cost of execution on different GPUs using COMPOFF during compile time. Our results show that this model can predict offloading costs with a root mean squared error in prediction of less than 0.5 seconds. Our preliminary findings indicate that this work will make it much easier and faster for scientists and compiler developers to port legacy HPC applications that use OpenMP to new heterogeneous computing environment.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Stress intensity factor models using mechanics-guided decomposition and symbolic regression

The finite element method can be used to compute accurate stress intensity factors (SIFs) for cracks with complex geometries and boundary conditions. In contrast, handbook solutions act as surrogate SIF models that provide significantly faster evaluation times. However, the development of conventional surrogate SIF models relies on manual development based on low-order parameterizations. This limits surrogate model accuracy and generalizability. Here, in this paper, we develop a framework for the automated development of mechanics-guided handbook SIF solutions by using interpretable machine learning via genetic programming for symbolic regression (GPSR). Formalizing the mechanics-based approach of Raju and Newman, SIF training data is decomposed into multiple subsets. This decomposition enables parallel GPSR model development of subfunctions, each of which accounts for specific geometrical corrections with respect to a known analytical model. Using this mechanics-based approach with GPSR allows for equations to be learned with improved accuracy and reduced complexity relative to the Raju Newman equations while maintaining the inherent interpretability of mathematical expressions. In this paper, we present equations that match the complexity of the Raju Newman equations while having reduced error, as well as equations with similar errors and reduced complexity.

42 ENGINEERING↗
DOE OSTI2025

Automated and highly parallelized Bayesian optimization scheme for direct drive fusion experiments on OMEGA

Finding the optimal implosion design on existing experimental facilities for inertial confinement fusion requires an exhaustive search of the vast design parameter space. This is infeasible both with experiments and with simulations. Consequently, a large fraction of the experimentally realizable design space remains unexplored, and new design schemes are challenging to optimize in a reasonable time frame. On the OMEGA laser facility, predictive machine learning models have been developed to accurately forecast the result of an experiment using only inexpensive simulations and the large dataset of prior experimental data. However, the full design space remains vast enough to be unassailable with simple optimization techniques. Here we develop an automated and optimally parallel Bayesian optimization algorithm that can entirely optimize the target and pulse shape of a direct-drive ICF implosion under a given design paradigm. We use this algorithm to find a markedly improved design for the performance implosions on OMEGA that is predicted to hydroequivalently scale to ignition at 2.15 MJ.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

System Modeling and Robust Stability Region Analysis for Multi-inverters Based on VSG

As the number of inverter-interfaced distributed generators (IIDGs) increases, the decrease in the inertia of the microgrid affects the stability of microgrid voltage and current. The virtual synchronous generator (VSG) control method simulates the output characteristics of the synchronous machine to improve the inertia and damping of the microgrid. However, low-frequency oscillations can occur in systems with multi-VSGs connected in parallel, primarily when operating in island mode. Therefore, this article develops the small-signal state-space model for multi-inverters based on VSG and analyses the robust stability region (RSR) of the control parameters. Firstly, an extensible small-signal state-space model is established and simplified in the dq axis, which is a necessary preprocessing for the subsequent stability analysis. Secondly, the guardian map method based on bialternate product operation is constructed, and the RSR is established through translation mapping and rotation mapping. Therefore, the solution of RSR is transformed into the problem of identifying the Hurwitz matrix. Finally, the simulations and experiments verify that the calculated region can ensure stable operation during startup and meet the requirement to suppress low-frequency oscillations. In conclusion, the method of solving RSR proposed in this paper provides a basis for selecting controller parameters in practical engineering.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Progress Report of Alloy 709 Performance in Liquid Sodium

With improved high-temperature properties, Alloy 709 shows great potential for advanced reactor applications. To understand the effects of sodium on A709, small tensile specimens were machined from two commercial heats and subject to sodium exposure in two forced convection loops operated by Argonne. Thermal aging experiments were also conducted in parallel to isolate any sodium-specific effects. An increasing trend in yield strength and a decrease trend in ultimate tensile strength can be seen with the increasing exposure time, suggesting microstructural changes at these temperatures. Nonetheless, the thermally aged and sodium exposed samples behaved similarly, implying no sodium-specific effect at these temperatures. In contrast, 316H SS exposed to sodium at 650°C showed a strong sodium effect. The different responses of A709 and 316H SS to sodium exposure is of interest and requires additional effort to understand. The cold traps of the sodium loop were replaced early in FY23. During a maintenance operation, an unexpected sodium leak incident occurred at one of the sodium loops, triggering an emergency response. An investigation into the incident revealed that the leak happened at a VCR fitting on the recently replaced cold trap. The metal gasket of the leaked VCR fitting was not compressed sufficiently. A dimensional mismatch between the new component and old piping configuration was responsible for a significant misalignment. A new cold trap with improved design is in production. The new design provides additional flexibility and an access point for post-installation helium leak check and for venting of trapped gas. These design features will make the system more error-tolerant and the installation quality verifiable. A thermodynamic analysis was performed to understand the carburization-decarburization behavior of A709 in sodium environment. The equilibrium carbon activity in the alloy was evaluated with M 23 C 6 , TiC, and NbC. The carburization-decarburization boundary was calculated with different methods developed previously. The results suggests that A709 will be carburized in SMT-1 and SMT-2, and can be decarburized in low-carbon-activity environments such as EBR-II at temperatures above 620-650°C. Nonetheless, A709 should be less likely to be decarburized than 316H SS when exposed to the same low-carbon-activity environment.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

GPU-enabled extreme-scale turbulence simulations: Fourier pseudo-spectral algorithms at the exascale using OpenMP offloading

Fourier pseudo-spectral methods for nonlinear partial differential equations are of wide interest in many areas of advanced computational science, including direct numerical simulation of three-dimensional (3-D) turbulence governed by the Navier-Stokes equations in fluid dynamics. This paper presents a new capability for simulating turbulence at a new record resolution up to 35 trillion grid points, on the world's first exascale computer, Frontier, comprising AMD MI250x GPUs with HPE's Slingshot interconnect and operated by the US Department of Energy's Oak Ridge Leadership Computing Facility (OLCF). Key programming strategies designed to take maximum advantage of the machine architecture involve performing almost all computations on the GPU which has the same memory capacity as the CPU, performing all-to-all communication among sets of parallel processes directly on the GPU, and targeting GPUs efficiently using OpenMP offloading for intensive number-crunching including 1-D Fast Fourier Transforms (FFT) performed using AMD ROCm library calls. With 99% of computing power on Frontier being on the GPU, leaving the CPU idle leads to a net performance gain via avoiding the overhead of data movement between host and device except when needed for some I/O purposes. Memory footprint including the size of communication buffers for MPI_ALLTOALL is managed carefully to maximize the largest problem size possible for a given node count. Detailed performance data including separate contributions from different categories of operations to the elapsed wall time per step are reported for five grid resolutions, from 2048 3 on a single node to 32768 3 on 4096 or 8192 nodes out of 9408 on the system. Both 1D and 2D domain decompositions which divide a 3D periodic domain into slabs and pencils respectively are implemented. The present code suite (labeled by the acronym GESTS, GPUs for Extreme Scale Turbulence Simulations) achieves a figure of merit (in grid points per second) exceeding goals set in the Center for Accelerated Application Readiness (CAAR) program for Frontier. The performance attained is highly favorable in both weak scaling and strong scaling, with notable departures only for 2048 3 where communication is entirely intra-node, and for 32768 3 , where a challenge due to small message sizes does arise. Communication performance is addressed further using a lightweight test code that performs all-to-all communication in a manner matching the full turbulence simulation code. Performance at large problem sizes is affected by both small message size due to high node counts as well as dragonfly network topology features on the machine, but is consistent with official expectations of sustained performance on Frontier. Overall, although not perfect, the scalability achieved at the extreme problem size of 32768 3 (and up to 8192 nodes — which corresponds to hardware rated at just under 1 exaflop/sec of theoretical peak computational performance) is arguably better than the scalability observed using prior state-of-the-art algorithms on Frontier's predecessor machine (Summit) at OLCF. New science results for the study of intermittency in turbulence enabled by this code and its extensions are to be reported separately in the near future.

3D fast Fourier transform↗
DOE OSTI2020

Initial Implementation Of Machine Learning System for SRF Cavity Fault Classification at CEBAF

The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Laboratory is high power CW electron accelerator. It uses a mixture of two types of SRF modules, older, lower energy C20/C50 modules and newer higher energy C100 modules, arrayed in two anti-parallel linear accelerators. Accurately classifying the type of cavity faults is essential to maintaining and improving accelerator performance. Each C100 cryomodule contains eight 7-cell cavities. When a cavity fault occurs within a cryomodule, all eight cavities generate 17 waveforms each containing 8192 points. This data is exported from EPICS and saved for review. Analysis of these waveforms is time intensive and requires subject matter expertise (SME). SMEs examine the data from each event and label it according to one of several known cavity fault types. Multiple machine learning models have been developed on this labeled dataset with sufficient performance to warrant the creation of a limited machine learning software system for use by accelerator operations staff. This paper discusses the transition from model development to implementation of a prototype system.

Carpenter, A.↗
DOE OSTI2022

Computer Science Research Needs for Parallel Discrete Event Simulation (PDES)

Historically, scientific computing efforts have demonstrated the clear need for, and effective use of, supercomputing with traditional time-stepped simulations. Nevertheless, there are several areas in the mission spaces of the U.S. Department of Energy and other agencies waiting to tap advanced computing research using a different, discrete event style of modeling, simulation, and analysis. These span a wide spectrum of applications including energy grid resilience, urban planning and policy, transportation science, building technologies, emergency response and planning, environmental impact analysis, computational epidemiology, Internet communications, cyber security, and cyber-physical systems, to name only a few. Even within traditional scientific applications, the role of discrete event modes of execution is increasing in the form of new event-based mathematical solvers such as quantized state integration methods and discrete-continuous hybrid system solvers. Co-design of advanced supercomputing hardware systems is another area that exploits discrete event simulation at its core for effective analyses. Complex systems, entity behaviors and interconnections play a significant role in all these applications, which are mapped to large-scale models with discrete event formulations. To make advancements in all the aforementioned scientific areas, many technical aspects need to be more thoroughly studied and deeply understood in parallel discrete event simulation (PDES). The unique dynamics inherent in a discrete event modeling approach, by their very nature, intersect and influence the entire stack of the computing system, including (a) the unique nature of the instruction sets exercised in PDES workloads without a predominance of high-precision floating point operations, (b) virtual time-constrained multi-threaded execution of many logical processes per processor, (c) extremely variable and difficult to predict network traffic characteristics, (d) interfaces and inter-dependencies with machine learning and artificial intelligence codes at higher software layers, and (e) highly challenging load balancing needs, especially in effectively accounting for accelerated/extremely heterogeneous computing in current and future high-performance computing systems. Efficient and accurate parallel execution of PDES workloads is also dominated by challenges in dealing with their asynchronous concurrency fundamentally present at the model level. Conservative synchronization, optimistic/speculative synchronization, and their hybrid schemes open new questions in fundamental computer science with respect to reversibility of computation and prediction (lookahead) of behaviors inherent within model codes. On the implementation front, there are relatively few scalable, general-purpose parallel discrete event simulators in the world, and even fewer have been studied on emerging hardware platforms. To enable scientific advances using PDES, the research needs in computer science must also be pursued and met in the intersection of the algorithmic and hardware-aware aspects of scalable PDES engines. This report is aimed at capturing a computer science-oriented view of this important area of research in PDES, presenting a sample of important applications with their inherent discrete event technology elements. Needs are outlined in core areas of parallel discrete event research as well as cross-cutting directions in computer science research that positively impact scientific advancements across several important application areas. A selection of priority research opportunities in advanced computing for PDES is identified to serve as reference for key research topics and their order of importance for scientific advancements.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

ppdx : Automated modeling of protein–protein interaction descriptors for use with machine learning

This paper describes ppdx, a python workflow tool that combines protein sequence alignment, homology modeling, and structural refinement, to compute a broad array of descriptors for characterizing protein–protein interactions. The descriptors can be used to predict various properties of interest, such as protein–protein binding affinities, or inhibitory concentrations (IC 50 ), using approaches that range from simple regression to more complex machine learning models. The software is highly modular. It supports different protocols for generating structures, and 95 descriptors can be currently computed. More protocols and descriptors can be easily added. The implementation is highly parallel and can fully exploit the available cores in a single workstation, or multiple nodes on a supercomputer, allowing many systems to be analyzed simultaneously. As an illustrative application, ppdx is used to parametrize a model that predicts the IC 50 of a set of antigens and a class of antibodies directed to the influenza hemagglutinin stalk.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Scalable training of trustworthy and energy-efficient predictive graph foundation models for atomistic materials modeling: a case study with HydraGNN

We present our work on developing and training scalable, trustworthy, and energy-efficient predictive graph foundation models (GFMs) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) computations in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define nearest-neighbor convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFMs training to tens of thousands of GPUs on datasets consisting of hundreds of millions of graphs. Our GFMs use multitask learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as energy and atomic forces. Using over 154 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two state-of-the-art US Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge Leadership Computing Facility. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2000 GPUs on Perlmutter and 16,000 GPUs on Frontier.

97 MATHEMATICS AND COMPUTING↗