SEARCH · Search NASA

Results for “Parallel Architectures”

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.

SourceResearch connectionFrom yearThrough year

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

At least 1,693 records · Page 94

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Impact of Emerging Computing Architectures and Opportunities for Process Systems Engineering Applications

Moore’s “law” was the observation that the number of transistors in an integrated circuit doubled approximately every two years. This trend has distinctly failed to hold in recent years. The death of Moore’s law has left researchers and practitioners in the computational sciences searching for technologies to provide the speedups formerly supported by Moore’s law. Previously overlooked chip architectures and other computing technologies are now receiving more development resources. Critically, these technologies are gaining more mature software support, opening their adoption by researchers in algorithms and applications. In this article, we review some of these computing technologies, their relationship with various algorithms and applications, and their potential benefits (or pitfalls). We close with recommendations for future work by the process systems engineering community specifically.

Emerging hardware↗

DOE OSTI2020

Successes and Opportunities for Discovery of Metal Oxide Photoanodes for Solar Fuels Generators

We report that the importance of metal oxide photoanodes in solar fuels technology has garnered concerted efforts in photoanode discovery in recent decades, which complement parallel efforts in development of analytical techniques and optimization strategies using standard photoanodes such as TiO 2 , Fe 2 O 3 and BiVO 4 . Theoretical guidance of high-throughput experiments has been particularly effective in dramatically increasing the portfolio of metal oxide photoanodes, motivating a new era of photoanode development where the characterization and optimization techniques developed on traditional materials are applied to nascent photoanodes that exhibit visible light photoresponse. The compendium of metal oxide photoanodes presented in the present work can also serve as the basis for further technique development, with a primary goal to establish workflows for discovery of materials that perform better against the critical criteria of operational stability, visible light photoresponse, and photovoltage suitable for tandem absorber architectures.

14 SOLAR ENERGY↗

DOE OSTI2026

Intern Poster Session 08/13: Autonomous Nuclear Robotics: Applications in nuclear waste inspection and hot cell experiments

The nuclear industry is experiencing renewed interest in autonomous robotics, yet most deployed systems remain teleoperated with limited autonomy. This work presents two contributions toward fully autonomous nuclear robotic systems: autonomous waste inspection at the Hanford Site and an autonomous hot cell laboratory framework. Inspections of Hanford's underground waste storage tanks are performed manually at significant cost and personnel exposure. We developed a reinforcement-learning (RL) training pipeline for a custom-built inspection arm. In parallel, we are designing an autonomous laboratory framework for post-irradiation examination in hot cells at the Specimen Preparation Laboratory (SPL) that integrates computer vision, task and motion planning, hardware execution, and operator-in-the-loop control. These systems demonstrate a path toward safer, more efficient nuclear operations by reducing human exposure while maintaining rigorous human oversight at critical decision points.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2025

Wide-Bandgap Semiconductor Amplifiers for Fusion Plasma Heating and Control

This paper discusses power electronics developed under the ARPA-E GAMOW program to support nuclear fusion power production. The goal of this project was to develop and assess the potential for wide-bandgap (WBG) semiconductor devices in power electronics to enable high-efficiency and high-voltage solid-state systems for fusion plasma generation, heating, and control. The power electronics use an architecture in which multiple high-power boards can be combined to produce megawatt-level power, where using multiple boards provides high reliability. Two main areas of power electronics boards are developed in this project for fusion plasma heating and control applications: (1) pulse generation and control and (2) radiofrequency generation. The first area is for boards capable of driving high-voltage millisecond pulses at high duty cycles. The envisioned application of these pulses is in plasma control of magnetohydrodynamic instabilities, plasma position, and edge-localized modes. Pulse-width modulation allows for the implementation of a wide variety of linear and nonlinear control systems. The boards developed for this project could actuate control coils based on digital input signals and can be parallelized to provide megawatts of output power. The design of the pulse generator is a low-side load switch. A load switch was designed and constructed that utilized 2-kV-rated field-effect transistor (FET)-based cascodes developed by Qorvo under this project to perform initial testing of these cascodes. The second area is being implemented using class E amplifiers with WBG devices and a reactance steering network to handle inductive or capacitive plasma loads. Applications include ion cyclotron resonance heating (ICRH) and high-harmonic fast-wave (HHFW) heating. A class E reactance steering network is demonstrated in modeling and experiment with a resistive-inductive load that models an inductively-coupled plasma. Power combining of boards with class E reactance steering networks is also simulated and demonstrated experimentally, to enable scaling up to high power. Modeling of high-power-density cooling and remaining useful life is conducted to enable reliable, effectively cooled high-power electronics for fusion applications.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2024

LibERI—A portable and performant multi-GPU accelerated library for electron repulsion integrals via OpenMP offloading and standard language parallelism

A portable and performant graphics processing unit (GPU)-accelerated library for electron repulsion integral (ERI) evaluation, named LibERI, has been developed and implemented via directive-based (e.g., OpenMP and OpenACC) and standard language parallelism (e.g., Fortran DO CONCURRENT). Offloaded ERIs consist of integrals over low and high contraction s, p, and d functions using the rotated-axis and Rys quadrature methods. GPU codes are factorized based on previous developments with two layers of integral screening and quartet presorting. In this work, the density screening is moved to the GPU to enhance the computational efficacy for large molecular systems. Here, the L-shells in the Pople basis set are also separated into pure S and P shells to increase the ERI homogeneity and reduce atomic operations and the memory footprint. LibERI is compatible with any quantum chemistry drivers supporting the MolSSI Driver Interface. Benchmark calculations of LibERI interfaced with the GAMESS software package were carried out on various GPU architectures and molecular systems. The results show that the LibERI performance is comparable to other state-of-the-art GPU-accelerated codes (e.g., TeraChem and GMSHPC) and, in some cases, outperforms conventionally developed ERI CUDA kernels (e.g., QUICK) while fully maintaining portability.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

NASA NTRS1993

Optimal cube-connected cube multiprocessors

Many CFD (computational fluid dynamics) and other scientific applications can be partitioned into subproblems. However, in general the partitioned subproblems are very large. They demand high performance computing power themselves, and the solutions of the subproblems have to be combined at each time step. The cube-connect cube (CCCube) architecture is studied. The CCCube architecture is an extended hypercube structure with each node represented as a cube. It requires fewer physical links between nodes than the hypercube, and provides the same communication support as the hypercube does on many applications. The reduced physical links can be used to enhance the bandwidth of the remaining links and, therefore, enhance the overall performance. The concept and the method to obtain optimal CCCubes, which are the CCCubes with a minimum number of links under a given total number of nodes, are proposed. The superiority of optimal CCCubes over standard hypercubes was also shown in terms of the link usage in the embedding of a binomial tree. A useful computation structure based on a semi-binomial tree for divide-and-conquer type of parallel algorithms was identified. It was shown that this structure can be implemented in optimal CCCubes without performance degradation compared with regular hypercubes. The result presented should provide a useful approach to design of scientific parallel computers.

Sun, Xian-He↗

NASA NTRSDate not supplied

Powder Bed Fusion Laser Beam Metals Additive Manufacturing: Process Monitoring Approaches for Qualification and Certification

The use of in-situ process monitoring is of interest to lower the cost of inspection for the qualification of powder bed fusion laser beam metal (PBF-LB/M) additively manufactured (AM) parts. Precise monitoring of the PBF-LB/M AM build process constitutes a multi-scale and multi-discipline task. There are several significant challenges to the in-situ approach: the synchronization of sensor signals to process steps; the physical interpretation and classification of sensor signals; managing very large datasets; and comparing the inputs with the observed monitoring signals. At NASA Langley Research Center, a configurable architecture additive testbed has been developed to monitor the build process with synchronized sensors. The philosophy and method adopted for the synchronization of the cameras with laser power and position throughout a complex PBF-LB/M AM build will be described. The synchronized in-situ monitoring signals are compared with ex-situ nondestructive inspection, x-ray computed tomography (XCT). Such comparisons permit a better understanding of how the sequential process actions of LPBF-AM can affect build quality. The multi-scale and complex process of printing additively manufactured (AM) parts can have unexpected, but predictable, build conditions that result in material microstructure variability. This presentation will describe an additive manufacturing model-based process metric (AM-PM) computational method that is a fully parallel reduced order modeling approach developed to evaluate the evolution of AM processes. This method couples the known sequence of the AM process with a physically informed nearest neighbors’ calculation to map the conditions of a part-scale build. The result is a map of the build that is derived directly from build files or in-situ process monitoring sensors. The methodology of the approach will be described and mapped to the porosity observed from XCT for a complex PBF-LB/M build. Such comparative results develop understanding of how the sequential process actions can affect the PBF-LB/M AM build quality and microstructure variability.

Laser Powder Bed Fusion↗

DOE OSTI2019

Parallel beamlet dose calculation via beamlet contexts in a distributed multi‐GPU framework

Purpose Dose calculation is one of the most computationally intensive, yet essential tasks in the treatment planning process. With the recent interest in automatic beam orientation and arc trajectory optimization techniques, there is a great need for more efficient model‐based dose calculation algorithms that can accommodate hundreds to thousands of beam candidates at once. Foundational work has shown the translation of dose calculation algorithms to graphical processing units ( GPU s), lending to remarkable gains in processing efficiency. But these methods provide parallelization of dose for only a single beamlet, serializing the calculation of multiple beamlets and under‐utilizing the potential of modern GPU s. In this paper, the authors propose a framework enabling parallel computation of many beamlet doses using a novel beamlet context transformation and further embed this approach in a scalable network of multi‐ GPU computational nodes. Methods The proposed context‐based transformation separates beamlet‐local density and TERMA into distinct beamlet contexts that independently provide sufficient data for beamlet dose calculation. Beamlet contexts are arranged in a composite context array with dosimetric isolation, and the context array is subjected to a GPU collapsed‐cone convolution superposition procedure, producing the set of beamlet‐specific dose distributions in a single pass. Dose from each context is converted to a sparse representation for efficient storage and retrieval during treatment plan optimization. The context radius is a new parameter permitting flexibility between the speed and fidelity of the dose calculation process. A distributed manager‐worker architecture is constructed around the context‐based GPU dose calculation approach supporting an arbitrary number of worker nodes and resident GPU s. Phantom experiments were executed to verify the accuracy of the context‐based approach compared to Monte Carlo and a reference CPU ‐ CCCS implementation for single beamlets and broad beams composed by addition of beamlets. Dose for representative 4 π beam sets was calculated in lung and prostate cases to compare its efficiency with that of an existing beamlet‐sequential GPU ‐ CCCS implementation. Code profiling was also performed to evaluate the scalability of the framework across many networked GPU s. Results The dosimetric accuracy of the context‐based method displays <1.35% and 2.35% average error from the existing serialized CPU ‐ CCCS algorithm and Monte Carlo simulation for beamlet‐specific PDD s in water and slab phantoms, respectively. The context‐based method demonstrates substantial speedup of up to two orders of magnitude over the beamlet‐sequential GPU ‐ CCCS method in the tested configurations. The context‐based framework demonstrates near linear scaling in the number of distributed compute nodes and GPU s employed, indicating that it is flexible enough to meet the performance requirements of most users by simply increasing the hardware utilization. Conclusions The context‐based approach demonstrates a new expectation of performance for beamlet‐based dose calculation methods. This approach has been successful in accelerating the dose calculation process for very large‐scale treatment planning problems ‐ such as automatic 4 π IMRT beam orientation and VMAT arc trajectory selection, with hundreds of thousands of beamlets ‐ in clinically feasible timeframes. The flexibility of this framework makes it as a strong candidate for use in a variety of other very large‐scale treatment planning tasks and clinical workflows.

Neph, Ryan↗

DOE OSTI2021

Implementing a neural network interatomic model with performance portability for emerging exascale architectures

The two main thrusts of computational science are increasingly accurate predictions and faster calculations; to this end, the zeitgeist in molecular dynamics (MD) simulations is pursuing machine learned and data driven interatomic models, e.g. neural network potentials, and novel hardware architectures, e.g. GPUs. Current implementations of neural network potentials are orders of magnitude slower than traditional interatomic models and while looming exascale computing offers the ability to run large, accurate simulations with these models, achieving portable performance for MD with new and varied exascale hardware requires rethinking traditional algorithms, using novel data structures, and library solutions. We re-implement a neural network interatomic model in CabanaMD, an MD proxy application, built on libraries developed for performance portability. Our implementation shows significantly improved thread scaling in this complex kernel as compared to a current LAMMPS implementation, across both strong and weak scaling. Our single-source solution enables simulations up to 20 million atoms on a single CPU node and 4 million atoms with improved performance on a single GPU. Furthermore, we also explore parallelism and data layout choices (using flexible data structures called AoSoAs) and their effect on performance, seeing up to ~50% and ~5% improvements in performance on a GPU by choosing the right level of parallelism and data layout respectively.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Confinement and Processing Can Alter the Morphology and Periodicity of Bottlebrush Block Copolymers in Thin Films

Bottlebrush block copolymers (BBCPs) are intriguing architectural variations on linear BCPs with highly tunable structure. Confinement can have a significant impact on polymer assembly, giving rise to changes in morphology, assembly kinetics, and properties like the glass transition. Given that confinement leads to significant changes in the persistence length of bottlebrush homopolymers, it is reasonable to expect that BBCPs will see significant changes in their structure and periodicity relative to the bulk morphology. Understanding how confinement influences assembly will be important for designing BBCPs for thin film applications including membranes, integrated photonic structures, and potentially BCP lithography. In this work, in order to study the effects of confinement on BBCP conformation and morphology, a blade coating was used to prepare films with continuous variation in film thickness. Unlike thin films of linear BCPs, islands/holes were not observed, and instead mixtures of parallel and perpendicular morphologies emerge after annealing. The lamellar periodicity ($L_0$) of the morphologies is found to be thickness dependent, increasing $L_0$ with decreasing film thickness for blade coated films. Films coated out of tetrahydrofuran (THF) resulted in a single well-defined lamellar periodicity, verified through atomic force microscopy (AFM) and grazing incidence small-angle X-ray scattering (GISAXS), which increases dramatically from the bulk value (30.6 nm) and continues to increase as the film thickness decreases. The largest observed $L_0$ was 65.5 nm, and this closely approaches the estimated upper limit of 67 nm corresponding to a fully extended backbone in a bilayer arrangement. Films coated out of propylene glycol methyl ether acetate (PGMEA) resulted in a mixture of perpendicular lamellae and a smaller, likely cylindrical morphology. The lamellar portion of the film shows the same thickness dependence as the lamellae observed in the THF coated films. The scaling of the lamellar $L_0$ with respect to film thickness follows predictions for confined semiflexible polymers with weak excluded volume interactions and can be related to models for confinement of DNA. Spin coated films shows the same reduction in periodicity, although at very different film thicknesses. This result suggests that the material has shallow free-energy barriers to transitioning between different $L_0$ and morphologies, a property that could be taken advantage of for patterning diverse structures with a single material.

36 MATERIALS SCIENCE↗

NASA NTRS2001

Cell-wall architecture and lignin composition of wheat developed in a microgravity environment

The microgravity environment encountered during space-flight has long been considered to affect plant growth and developmental processes, including cell wall biopolymer composition and content. As a prelude to studying how microgravity is perceived - and acted upon - by plants, it was first instructive to investigate what gross effects on plant growth and development occurred in microgravity. Thus, wheat seedlings were exposed to microgravity on board the space shuttle Discovery (STS-51) for a 10 day duration, and these specimens were compared with their counterparts grown on Earth under the same conditions (e.g. controls). First, the primary roots of the wheat that developed under both microgravity and 1 g on Earth were examined to assess the role of gravity on cellulose microfibril (CMF) organization and secondary wall thickening patterns. Using a quick freeze/deep etch technique, this revealed that the cell wall CMFs of the space-grown wheat maintained the same organization as their 1 g-grown counterparts. That is, in all instances, CMFs were randomly interwoven with each other in the outermost layers (farthest removed from the plasma membrane), and parallel to each other within the individual strata immediately adjacent to the plasma membranes. The CMF angle in the innermost stratum relative to the immediately adjacent stratum was ca 80 degrees in both the space and Earth-grown plants. Second, all plants grown in microgravity had roots that grew downwards into the agar; they did not display "wandering" and upward growth as previously reported by others. Third, the space-grown wheat also developed normal protoxylem and metaxylem vessel elements with secondary thickening patterns ranging from spiral to regular pit to reticulate thickenings. Fourthly, both the space- and Earth-grown plants were essentially of the same size and height, and their lignin analyses revealed no substantial differences in their amounts and composition regardless of the gravitational field experienced, i.e. for the purposes of this study, all plants were essentially identical. These results suggest that the microgravity environment itself at best only slightly affected either cell wall biopolymer synthesis or the deposition of CMFs, in contrast to previous assertions.

manned↗

DOE OSTI2025

Substituent and Heteroatom Effects on π–π Interactions: Evidence That Parallel-Displaced π-Stacking is Not Driven by Quadrupolar Electrostatics

Stacking interactions are a recurring motif in supramolecular chemistry and biochemistry, where a persistent theme is a preference for parallel-displaced aromatic rings rather than face-to-face π-stacking. This is usually explained in terms of quadrupole–quadrupole interactions between the arene moieties but that interpretation is inconsistent with accurate calculations, which reveal that the quadrupolar picture is qualitatively wrong. At typical π-stacking distances, quadrupolar electrostatics may differ in sign from an exact calculation based on charge densities of the interacting arenes. We apply symmetry-adapted perturbation theory to dimers composed of substituted benzene and various aromatic heterocycles, which display a wide range of electrostatic interactions, and we investigate the interplay of Pauli repulsion, dispersion, and electrostatics as it pertains to parallel-displaced π-stacking. Profiles of energy components along cofacial slip-stacking coordinates support a prominent role for the “van der Waals model” (dispersion in competition with Pauli repulsion), even for polar monomers where electrostatic interactions are significant. While electrostatic interactions are necessary to explain the optimal face-to-face π-stacking distance and to account for the relative orientation of one polar arene with respect to another, we find no evidence to support continued invocation of quadrupolar electrostatics as a basis for π-stacking. Our results suggest that a driving force for offset-stacking exists even in the absence of electrostatic interactions. Consequently, tuning electrostatics via functionalization does not guarantee that slip-stacking can be avoided. This has implications for rational design of soft materials and other supramolecular architectures.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2026

The high level trigger and express data production at STAR

To meet the demands of the Beam Energy Scan phase-II (BES-II) program, the STAR experiment at the Relativistic Heavy Ion Collider (RHIC) developed a dual real-time framework consisting of a High Level Trigger (HLT) and an Express Data Production system (xProduction). The HLT operates online within the Data Acquisition (DAQ) chain on a dedicated multi-core CPU cluster with the option to offload compute-intensive kernels to Xeon Phi coprocessors. It uses parallelized algorithms, such as the Cellular Automaton (CA) Track Finder, to perform rapid tracking, vertexing, and event filtering. This allows it to select events of interest in real time and provide immediate feedback on detector and beam conditions. In contrast, the xProduction workflow runs concurrently and independently of the DAQ loop. It applies near offline-quality calibration and reconstruction within hours of data collection. The xProduction input is the express data stream, whose content can be enriched by HLT trigger/priority selections under DAQ/HLT resource constraints, and it uses the STAR calibration/conditions framework, incorporating online calibration/QA information when available. This enables early preliminary physics analysis, including the reconstruction of rare signals, such as hyperons and hypernuclei. It also provides collaboration-wide access to analysis-ready datasets. Together, the HLT and xProduction systems form a complementary architecture: the HLT performs online event selection while the xProduction chain delivers high-quality results within a short amount of time. This integrated framework has enabled the prompt reconstruction of the $^5_Λ$ He hypernucleus with high statistical significance and the efficient processing of hundreds of millions of heavy-ion collision events. In conclusion, its demonstrated scalability and robustness establish a model for future high-luminosity experiments requiring both online event filtering and rapid access to analysis-quality data.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2021

A High Performance Sparse Tensor Algebra Compiler in MLIR

Sparse tensor algebra is widely used in many applications, including scientific computing, machine learning, and data analytics. The performance of sparse tensor algebra kernels strongly depends on the intrinsic characteristics of the input tensors, hence many storage formats are designed for tensors to achieve optimal performance for particular applications/architectures, which makes it challenging to implement and optimize every tensor operation of interest on a given architecture. We propose a tensor algebra domain-specific language (DSL) and compiler framework to automatically generate kernels for mixed sparse-dense tensor algebra operations. The proposed DSL provides high-level programming abstractions that resemble the familiar Einstein notation to represent tensor algebra operations. The compiler introduces a new Sparse Tensor Algebra dialect built on top of LLVM's extensible MLIR compiler infrastructure for efficient code generation while covering a wide range of tensor storage formats. Our compiler also leverages input-dependent code optimization to enhance data locality for better performance. Our results show that the performance of automatically generated kernels outperforms the state-of-the-art sparse tensor algebra compiler, with up to 20.92x, 6.39x, and 13.9x performance improvement over state-of-the-art tensor algebra compilers, for parallel SpMV, SpMM, and TTM, respectively.

Tian, Ruiqin↗

NASA NTRSDate not supplied

Feasibility Study of Distributed Decision-Making on the Edge for Urban Air Mobility

The Concept of Operations for Urban Air Mobility (UAM) put forward by FAA, NASA, and several industry stakeholders acknowledges the diversity and complexity in UAM operations and, thereby, envisions a federated architecture for UAM management. In this architecture, the decision-making is distributed to a set of service providers who collectively manage the shared airspace usage by different stakeholders. This notionally brings autonomy closer to the UAM businesses and encourages to explore the feasibility of decision making on the very edge, which is the topic of the presented research. This paper reports research conducted on the hypothesis based on which the residual compute capability onboard smart unmanned aerial systems (UASs) is utilized to build situational awareness and resolve conflicts by passive and active coordination among multiple UASs, thereby implementing a layer of distributed autonomy in UAM. Key features of the edge-computing approach involve inter-UAS information exchange, independent assessment of own flight and environmental conditions, and estimation of other UASs’ flight preferences, incorporating machine learning techniques in the last two. Parallel computing on portable graphics processing unit (GPU) enables the machine learning workflow on the edge. A custom-built 3D simulator is used to evaluate the efficacy of the distributed decision-making on the edge. Each edge node, representing a smart UAS, connects to the simulator from a remote location and independently controls the behavior of the corresponding virtual asset in the simulator, analogous to participants in an online multi-player game. The presented edge-computing-based distributed decision-making framework is envisioned to pave the way for collective mobility of autonomous air vehicles in the future shared airspace, while allowing the inclusion of the business preferences of the UAS operators within allowed regulatory limits.

Edge computing↗

NASA NTRSDate not supplied

Feasibility Study of Distributed Decision-Making on the Edge for Urban Air Mobility

Edge computing↗

DOE OSTI2025

Introduction: Neuromorphic Materials

The explosive growth in data collection and the need to process it efficiently, as well as the desire to automate increasingly complex tasks in transportation, medical care, manufacturing, security and many other fields have motivated a growing interest in neuromorphic computing. Unlike the binary, transistorbased ON/OFF logic gates and separate logic and memory functionalities employed in digital computing, neuromorphic computing is inspired by animal brains that use interconnected synapses and neurons to perform processing, storage and transmission of information at the same location, while only consuming ~20 W or less of power. Motivated by the brain’s efficiency, adaptability, self-learning and resiliency qualities, neuromorphic computing can be broadly defined as an approach to processing and storing information using hardware and algorithms inspired by models of biological neural systems. Present research in neuromorphic computing encompasses approaches that vary significantly in their degree of neuro-inspiration, from systems that only incorporate features such as asynchronous, event-driven operation or use crossbar arrays of non-volatile memory (NVM) elements to accelerate deep neural networks (DNNs), to designs that embrace the extreme parallelism, sparsity, reconfigurability, adaptability, complexity and stochasticity observed in nervous systems. The term ‘neuromorphic’ computing is often credited to Carver Mead, who in the 1980s investigated Si-based analog electronics to replicate functions of the animal retina. Earlier important advances in this field include the work of Frank Rosenblatt, who proposed the concept of the perceptron, Bernard Widrow, who used this concept to build one of the first analog neural networks, the Adaline and many other researchers (see ref. 6 for an historical perspective on neuromorphic computing). With the recent increase in the use of artificial intelligence and large language models, and rising concerns over the associated energy costs, interest in neuromorphic hardware has expanded rapidly. According to some estimates, driven largely by the drastic growth in the training use of artificial intelligence (AI) models using the current computing architectures, the energy cost of computing is projected to reach the energy supply worldwide by 2045. Furthermore, while this is not a realistic outcome, it means that, if more efficient computing technologies are not developed -- soon -- the world will soon become one where demand for energy and market constraints limit the continued increase of societal access to AI and cloud services from data centers. Data centers used for training and use of these models consume hundreds of terawatt hours of electricity, already past 4% of the US electricity demand.

Circuits↗

DOE OSTI2025

Lustre Unveiled: Evolution, Design, Advancements, and Current Trends

The Lustre filesystem serves as a vital element in high-performance parallel storage, meeting the rising demands of scientific, research, and enterprise environments. Widely deployed across HPC environments, ranging from small-scale applications in AI/ML, to domains like oil and gas, drug discovery, and meteorology, and manufacturing, Lustre addresses the universal challenge of efficiently accessing vast and ever-increasing volumes of data. Lustre is the filesystem of choice on six out of the top 10 fastest supercomputers in the world today, over 65% of the top 100, and also for over 60% of the top 500. Despite its widespread popularity, there is a lack of a complete and up-to-date reference, covering Lustre’s evolution, design, and various advancements made over the years. In this journal, we aim to fill this gap by providing a comprehensive journey of Lustre, including its history with significant contributions to HPC, detailed architecture and design elements, exploration of advancements added through its evolution, and future directions. Additionally, we present a comparison of Lustre with other prominent storage technologies of the era. To illustrate the current state of Lustre, we analyze several filesystem trends, including utilization, performance, and usage patterns on Orion, the Lustre filesystem on the first exascale supercomputer Frontier. We hope that this journal serves as a comprehensive educational reference for the current and future generations interested in HPC filesystem storage aspects.

97 MATHEMATICS AND COMPUTING↗