SEARCH · Engineering Papers

Results for “parallel computer architecture”

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.

1,075 records · Page 60

All sources NASA NTRS DOE OSTI

NASA NTRS2020

Mars Ascent Vehicle Solid Propulsion Configuration

As part of a Mars Sample Return (MSR) campaign, two Mars Ascent Vehicle (MAV) configurations have been designed in parallel. Each ascent vehicle configuration has a different propulsion system, which ultimately leads to two unique vehicle designs. As part of a Preliminary Architecture Assessment (PAA), these vehicle designs were developed to the same level of maturity in order to inform the selection of one of the vehicles as the point of departure design for the campaign. The selection will be made in November 2019. Although the initial MSR architecture called for a hybrid-based propulsion MAV featuring solid wax fuel with liquid oxidizer, a configuration using more traditional solid propulsion was developed as an additional risk mitigation option. Though lacking in the single stage to orbit (SSTO) and throttle flexibility of a hybrid configuration, a solid configuration vehicle allows a simpler design with significantly longer flight heritage and higher Technology Readiness Level (TRL). This paper describes the design of the solid propulsion configuration. An additional paper will be published describing the design of the hybrid propulsion configuration. The solid propulsion configuration MAV was developed in 2019 by NASA Marshall Space Flight Center (MSFC) in association with NASA Jet Propulsion Laboratory (JPL). It features two stages with a modified STAR-17 motor for the second stage and a traditional electromechanical actuator Thrust Vector Controller (TVC). The vehicle was designed to deliver approximately 0.47kg of Martian geological samples to a circular orbit at Mars of 343km at a 25° inclination. Although solid motor designs in general are at a relatively high TRL, the integrated vehicle subsystems that operate in conjunction with these propulsion elements do not typically operate in a Martian environment, which in this application can get as cold as -40°C. The PAA advanced the maturity of these subsystems by performing detailed design and analysis on the vehicle with respect to structures and mechanisms, Guidance/Navigation/Control (GNC) systems, avionics, Reaction Control System (RCS), TVC, thermal environments, and advanced Computational Fluid Dynamics (CFD). This paper will summarize the results of these studies.

Yaghoubi, Darius↗

NASA NTRS2020

Mars Ascent Vehicle Solid Propulsion Configuration

Yaghoubi, Darius↗

NASA NTRS2009

Cooperative Three-Robot System for Traversing Steep Slopes

Teamed Robots for Exploration and Science in Steep Areas (TRESSA) is a system of three autonomous mobile robots that cooperate with each other to enable scientific exploration of steep terrain (slope angles up to 90 ). Originally intended for use in exploring steep slopes on Mars that are not accessible to lone wheeled robots (Mars Exploration Rovers), TRESSA and systems like TRESSA could also be used on Earth for performing rescues on steep slopes and for exploring steep slopes that are too remote or too dangerous to be explored by humans. TRESSA is modeled on safe human climbing of steep slopes, two key features of which are teamwork and safety tethers. Two of the autonomous robots, denoted Anchorbots, remain at the top of a slope; the third robot, denoted the Cliffbot, traverses the slope. The Cliffbot drives over the cliff edge supported by tethers, which are payed out from the Anchorbots (see figure). The Anchorbots autonomously control the tension in the tethers to counter the gravitational force on the Cliffbot. The tethers are payed out and reeled in as needed, keeping the body of the Cliffbot oriented approximately parallel to the local terrain surface and preventing wheel slip by controlling the speed of descent or ascent, thereby enabling the Cliffbot to drive freely up, down, or across the slope. Due to the interactive nature of the three-robot system, the robots must be very tightly coupled. To provide for this tight coupling, the TRESSA software architecture is built on a combination of (1) the multi-robot layered behavior-coordination architecture reported in "An Architecture for Controlling Multiple Robots" (NPO-30345), NASA Tech Briefs, Vol. 28, No. 10 (October 2004), page 65, and (2) the real-time control architecture reported in "Robot Electronics Architecture" (NPO-41784), NASA Tech Briefs, Vol. 32, No. 1 (January 2008), page 28. The combination architecture makes it possible to keep the three robots synchronized and coordinated, to use data from all three robots for decision- making at each step, and to control the physical connections among the robots. In addition, TRESSA (as in prior systems that have utilized this architecture) , incorporates a capability for deterministic response to unanticipated situations from yet another architecture reported in Control Architecture for Robotic Agent Command and Sensing (NPO-43635), NASA Tech Briefs, Vol. 32, No. 10 (October 2008), page 40. Tether tension control is a major consideration in the design and operation of TRESSA. Tension is measured by force sensors connected to each tether at the Cliffbot. The direction of the tension (both azimuth and elevation) is also measured. The tension controller combines a controller to counter gravitational force and an optional velocity controller that anticipates the motion of the Cliffbot. The gravity controller estimates the slope angle from the inclination of the tethers. This angle and the weight of the Cliffbot determine the total tension needed to counteract the weight of the Cliffbot. The total needed tension is broken into components for each Anchorbot. The difference between this needed tension and the tension measured at the Cliffbot constitutes an error signal that is provided to the gravity controller. The velocity controller computes the tether speed needed to produce the desired motion of the Cliffbot. Another major consideration in the design and operation of TRESSA is detection of faults. Each robot in the TRESSA system monitors its own performance and the performance of its teammates in order to detect any system faults and prevent unsafe conditions. At startup, communication links are tested and if any robot is not communicating, the system refuses to execute any motion commands. Prior to motion, the Anchorbots attempt to set tensions in the tethers at optimal levels for counteracting the weight of the Cliffbot; if either Anchorbot fails to reach its optimal tension level within a specified time, it sends message to the other robots and the commanded motion is not executed. If any mechanical error (e.g., stalling of a motor) is detected, the affected robot sends a message triggering stoppage of the current motion. Lastly, messages are passed among the robots at each time step (10 Hz) to share sensor information during operations. If messages from any robot cease for more than an allowable time interval, the other robots detect the communication loss and initiate stoppage.

Stroupe, Ashley↗

DOE OSTI2026

User Manual - HydraGNN v5.0: Distributed Implementation of Multi-Tasking Graph Neural Networks

This document serves as the user manual for HydraGNN v5.0, a scalable graph neural network (GNN) architecture for simultaneous prediction of multiple target properties using multi-task learning (MTL). This version of HydraGNN has been developed primarily to support the development, training, and deployment of predictive graph-based deep learning (DL) models for atomistic materials modeling. HydraGNN is templated over 13 message-passing policies, including invariant models (GIN, PNA, PNAPlus, GAT, MFC, CGCNN, SAGE, SchNet, DimeNet) and equivariant models (EGNN, PNAEq, PAINN, MACE), and supports distributed training via distributed data parallelism (DDP), DeepSpeed, and Fully Sharded Data Parallelism (FSDP) on leadership-class supercomputers. Although HydraGNN can be applied to problems beyond atomistic materials modeling, its current use is confined to homogeneous graphs. Additional capabilities include machine-learned interatomic potentials with energy-conserving forces, General, Powerful, and Scalable Graph Transformer (GraphGPS) global attention, periodic boundary conditions, hyperparameter optimization, mixed-precision training, and uncertainty quantification.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

LLMs for Mfg.—On the State of Large Language Models and Applications to Manufacturing

Additive Manufacturing (AM), referred to as 3D printing, has emerged as a key pillar of Industry 4.0 enabling layer-by-layer fabrication of intricate geometries from CAD models. In parallel, Large Language Models (LLMs), deep learning models for natural language generation trained on vast text corpora, have demonstrated unprecedented capabilities in understanding and generating human-like text. The convergence of these trends opens new opportunities at the intersection of AM and AI/ML, where LLMs can assist engineers and researchers in design, manufacture planning, and knowledge discovery. Recent academic work has begun to explore LLM applications in AM and adjacent fields, such as material science, mechanical engineering, and design for additive manufacturing. This exploration ranges from intelligent process planning to domain-specific knowledge retrieval. This survey provides a comprehensive review of current developments, focusing on peer-reviewed literature contributions that apply, adapt, and advance LLMs in general and domain-specific domains. We analyze state-of-the-art (SOTA) techniques, such as fine-tuning foundational models for specific domains, retrieval-augmented generation (RAG) pipelines, knowledge graph integration, and delve into the architectures and evaluation methods employed. The goal of this survey is to inform researchers and practitioners of the current capabilities and limitations of LLMs in general and in domain-specific applications, and to outline how these models are being tailored to meet the requirements of these applications.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Distributed out-of-memory NMF on CPU/GPU architectures

We propose an efficient distributed out-of-memory implementation of the non-negative matrix factorization (NMF) algorithm for heterogeneous high-performance-computing systems. The proposed implementation is based on prior work on NMFk, which can perform automatic model selection and extract latent variables and patterns from data. In this work, we extend NMFk by adding support for dense and sparse matrix operation on multi-node, multi-GPU systems. The resulting algorithm is optimized for out-of-memory problems where the memory required to factorize a given matrix is greater than the available GPU memory. Memory complexity is reduced by batching/tiling strategies, and sparse and dense matrix operations are significantly accelerated with GPU cores (or tensor cores when available). Input/output latency associated with batch copies between host and device is hidden using CUDA streams to overlap data transfers and compute asynchronously, and latency associated with collective communications (both intra-node and inter-node) is reduced using optimized NVIDIA Collective Communication Library (NCCL) based communicators. Benchmark results show significant improvement, from 32X to 76x speedup, with the new implementation using GPUs over the CPU-based NMFk. Good weak scaling was demonstrated on up to 4096 multi-GPU cluster nodes with approximately 25,000 GPUs when decomposing a dense 340 Terabyte-size matrix and an 11 Exabyte-size sparse matrix of density 10 -6 .

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2000

Web Exploration Tools for a Fast Federated Optical Survey Database

We implemented several new web-based tools to improve the efficiency and versatility of access to the APS Catalog of the POSS I (Palomar Observatory-National Geographic Sky Survey) and its associated image database. The most important addition was a federated database system to link the APS Catalog and image database into one Internet-accessible database. With the FDBS, the queries and transactions on the integrated database are performed as if it were a single database. We installed Myriad the FDBS developed by Professor Jaideep Srivastava and members of his group in the University of Minnesota Computer Science Department. It is the first system to provide schema integration, query processing and optimization, and transaction management capabilities in a single framework. The attached figure illustrates the Myriad architecture. The FDBS permits horizontal access to the data, not just vertical. For example, for the APS, queries can be made not only by sky position, but also by any parameter present in either of the databases. APS users will be able to produce an image of all the blue galaxies and stellar sources for comparison with x-ray source error ellipses from AXAF (X Ray Astrophysics Facility) (Chandra) for example. The FDBS is now available as a beta release with the appropriate query forms at our web site. While much of our time was occupied with adapting Myriad to the APS environment, we also made major changes in Star Base, our DBMS for the Catalog, at the web interface to improve its efficiency for issuing and processing queries. Star Base is now three times faster for large queries. Improvements were also made at the web end of the image database for faster access; although work still needs to be done to the image database itself for more efficient return with the FDBS. During the past few years, we made several improvements to the database pipeline that creates the individual plate databases queries by StarBase. The changes include improved positions especially for galaxies, using a new median centroider and integrated magnitudes for galaxies with an improved density-to-intensity calibration with a "sky" background subtraction. In the original version of StarBase the object classification fainter than 19.5-20.0 mag., was an extrapolation of the networks trained on brighter objects. We have used a new catalog of galaxies at the NGP to train a neural network on objects fainter than 20th mag. This improved classification is used in the new version of StarBase. We have also added a FITS table option for the returned data from queries on the object catalog. The APS image database includes images in both colors so we have added a tool for querying the image database in both colors simultaneously. The images can be displayed in parallel or blinked for comparison.

Humphreys, Roberta M.↗

NASA NTRS2020

Mars Ascent Vehicle Hybrid Propulsion Configuration

As part of a Mars Sample Return (MSR) campaign, two Mars Ascent Vehicle (MAV) configurations have been designed in parallel. Each ascent vehicle configuration has a different propulsion system which ultimately leads to two unique vehicle designs. As part of a Preliminary Architecture Assessment (PAA), these vehicle designs were developed to the same level of maturity in order to inform the selection of one of the vehicles as the point of departure design for the campaign. The selection will be made in November 2019. The initial MSR architecture called for a hybrid-based propulsion MAV. This type of propulsion system calls for a solid wax motor that would utilize liquid MON-25 as an oxidizer. Hybrid rocket propulsion allows for more flexibility than traditional solid or liquid propulsion options, and typically benefits from the advantages of both. A hybrid motor can be throttled and shut down easily, and avoids significant risk in manufacturing and handling. On a theoretical level, hybrid motors perform at a higher specific impulse (Isp) than solid motors. The primary disadvantage of hybrid motors comes from additional complexity and significantly less flight heritage and low Technology Readiness Level (TRL). This paper describes the design of the hybrid propulsion configuration. An additional paper will be published describing the design of the solid propulsion configuration1. The hybrid propulsion configuration MAV was developed in 2019 by NASA Marshall Space Flight Center (MSFC) in association with NASA Jet Propulsion Laboratory (JPL). It features a Single Stage to Orbit (SSTO) design with an SP7A solid wax fuel and MON-25 liquid oxidizer. The liquid portion of the vehicle allows for a Liquid Injection Thrust Vector Controller (LITVC) as well as hypergolic propellant additives for ignition. The vehicle was designed to deliver approximately 0.31kg of Martian geological samples to a circular orbit at Mars of 343km at a 25o inclination. Although hybrid propulsion in general has been used on launch vehicles in the past, the integrated vehicle subsystems that operate in conjunction with these propulsion elements do not typically operate in a Martian environment, which in this application can get as cold as -40oC. The PAA advanced the maturity of these subsystems by performing detailed design and analysis on the vehicle with respect to structures and mechanisms, Guidance/Navigation/Control (GNC) systems, avionics, Reaction Control System (RCS), LITVC, thermal environments, and advanced Computational Fluid Dynamics (CFD). This paper will summarize the results of these studies.

Yaghoubi, Darius↗

DOE OSTI2026

HydraGNN_Predictive_GFM_2026 - Ensemble of predictive graph foundation models for atomistic materials modeling

This release contains data and parameters of HydraGNN-based graph foundation models trained as a result of the work published in the pre-print "Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data" by M. Lupo Pasini et al. (https://arxiv.org/abs/2604.15380). We jointly train on 16 open first-principles datasets (544+ million structures covering 85+ elements) using a multi-task architecture with per-dataset heads and a scalable ADIOS2/DDStore data pipeline. On Frontier, we execute six large-scale DeepHyper hyperparameter optimization campaigns in FP64 and promote the top-performing message-passing models to sustained 2,048-node training, yielding a PaiNN-based lead model. The version of HydraGNN used to generate the outputs provided in this release is HydraGNN v5.0 (https://github.com/ORNL/HydraGNN/releases/tag/v5.0) The list of datasets used for the training of the graph foundation model is the following: 1) Alexandria [1] 2) ANI1x [2] 3) MPTrj [3] 4) Open Catalyst 2020 (OC20) [4] 5) Open Catalyst 2022 (OC22) [5] 6) Open Catalyst 2025 (OC25) [6] 7) Open Direct ir Capture 2023 (ODAC23) [7] 8) Open Materials 2024 (OMat24) [8] 9) Open Molecules 2025 (OMol25) [9] 10) OMol25-neutral (subset of OMol25 that contains only molecules with zero total charge) 11) OMol25-non-neutral (subset of OMol25 that contains only molecules with non-zero total charge) 12) Open Polymers 2026 (OPoly2026) [10] 13) Nabla2DFT [11] 14) QCML [12] 15) QM7X [reference 13] 16) transition1x [14] Dataset references: [1] J. Schmidt et al., “A dataset of 175k stable and metastable materials calculated with the PBEsol and SCAN functionals,” Scientific Data, vol. 9, p. 64, 2022. [2] J. S. Smith et al., “The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules,” Scientific Data, vol. 7, p. 134, 2020. [Online]. Available: https: //www.nature.com/articles/s41597-020-0473-z [3] A. Jain et al., “Commentary: The Materials Project: A materials genome approach to accelerating materials innovation,” APL Materials, vol. 1, no. 1, p. 011002, 07 2013. [Online]. Available: https://doi.org/10.1063/1.4812323 [4] L. Chanussot et al., “Open catalyst 2020 (oc20) dataset and community challenges,” ACS Catalysis, vol. 11, no. 10, pp. 6059–6072, 2021. [Online]. Available: https://doi.org/10.1021/acscatal.0c04525 [5] K. Tran et al., “Open catalyst 2022 (oc22) dataset and challenges for oxidation electrocatalysts,” ACS Catalysis, vol. 13, no. 5, pp. 3066–3084, 2023. [Online]. Available: https://doi.org/10.1021/acscatal.2c05426 [6] S. J. Sahoo et al., “The open catalyst 2025 (oc25) dataset and models for solid-liquid interfaces,” arXiv preprint arXiv:2509.17862, 2025. [Online]. Available: https://arxiv.org/abs/2509.17862 [7] A. Sriram et al., “The open DAC 2023 dataset and challenges for sorbent discovery in direct air capture,” ACS Central Science, vol. 10, no. 5, pp. 923–941, 2024. [8] L. Barroso-Luque et al., “Open materials 2024 (omat24) inorganic materials dataset and models,” 2024. [Online]. Available: https://arxiv.org/abs/2410.12771 [9] D. S. Levine et al., “The open molecules 2025 (OMol25) dataset, evaluations, and models,” 2025. [Online]. Available: https://arxiv.org/abs/2505.08762 [10] D. S. Levine et al., The open polymers 2026 (OPoly26) dataset and evaluations,” arXiv preprint arXiv:2512.23117, 2025. [Online]. Available: https://arxiv.org/abs/2512.23117 [11] K. Khrabrov et al., “Nabla2dft: A universal quantum chemistry dataset of drug-like molecules and a benchmark for neural network potentials,” in NeurIPS 2024 Datasets and Benchmarks Track, 2024. [Online]. Available: https://openreview.net/forum?id=ElUrNM9U8c [12] S. Ganscha et al., “The QCML dataset, quantum chemistry reference data from 33.5M DFT and 14.7B semi-empirical calculations,” Scientific Data, vol. 12, p. 406, 2025. [13] J. Hoja et al., “QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules,” Scientific Data, vol. 8, p. 43, 2021. [Online]. Available: https://www.nature.com/articles/s41597-021-00812-2 [14] M. Schreiner et al., “Transition1x - a dataset for building generalizable reactive machine learning potentials,” Scientific Data, vol. 9, p. 779, 2022. The folder "datasets_ADIOS2_format" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "datasets_ADIOS2_format" directory contains 2 sub-directories, one for the version "v1" of the datasets and one for the version "v2" of the datasets. The version "v1" of the datasets provides values of the total energy as they are extracted from the original data as it was released by the respective institutions. The version "v2" of the datasets provides values of the energy that have been realigned. The realignment was performed by training a linear regression model that predicts the total energy as a function of the chemical composition of the atomistic structure, and then subtract such prediction from the original value of the total energy. Both folders "v1" and "v2" contain 16 sub-directories, each corresponding to an ADIOS2-formatted dataset The folder "DeepHyper-results" contains the configurational files and model's parameters for all the 186 HPO trials that were successfully completed by the scalable hyperparameter optimization (HPO) runs on Frontier. The content of the folder "DeepHyper-results" I structured as follows: 1) task-list.txt: list of mpnn name, jobid, and deephyper task id 2) gfm_${MPNN}_${JOBID}_0.${TASKID}: run directory with checkpoint files 3) gfm_${MPNN}: deephyper summary directory (*.csv) for each specific MPNN type 4) deephyper-experiment-${JOBID}: output and error logs for each job The file "deephyper-sorted.csv" contains the details of each HydraGNN model built and tested by HPO, obtained by merging the (*.csv) filed from each HPO run executed. Out of all the HPO trials, we selected 10 to continue the training of the respective HydraGNN models. Due to limited computational budget available in the LRN070 allocation we could not complete the training till convergence for all these 10 selected models. The folder "models" contains multiple sub-folders, one per each HydraGNN model trained. Each model sub-folder contains the parameters of each HydraGNN model, with multiple checkpoint-restarts. The list of sub-folders are as follows: 1) multidataset_hpo-BEST1-fp64 2) multidataset_hpo-BEST2-fp64 3) multidataset_hpo-BEST3-fp64 4) multidataset_hpo-BEST4-fp64 5) multidataset_hpo-BEST5-fp64 6) multidataset_hpo-BEST6-fp64 7) multidataset_hpo-BEST7-fp64 8) multidataset_hpo-BEST8-fp64 9) multidataset_hpo-BEST9-fp64 10) multidataset_hpo-BEST10-fp64 Within each one of these folders, additional auxiliary log files are provided with descriptions about how the training proceeded. The lead PaiNN-model is contained inside "multidataset_hpo-BEST6-fp64". The file "mlp_branch_weights" contains the parameters of the multi-layer perceptron (MLP) used to reconcile the predictions of the 16 output decoding heads of the HydragNN architectures. The MLP takes in input the chemical composition of the atomistic structure and predicts averaging weights to linearly mix the predictions of each output decoding head toward consolidating them into a single one. The folder "1.1billion-structure-inference" contains 1.1 billion atomistic structures randomly generated. Each structures is associated with energy and forces predicted with the lead-PaiNN model combined with the MLP model for reconciliation of the multi-branch predictions generated by the 16 output decoding heads. The folder "1.1billion-structure-inference" contains 9,300 (*.tar.gz) subdirectories, one per Frontier compute node used to execute the inference at exascale. Once uncompressed, each (*.tar.gz) subdirectory contains an ADIOS2 (*.bp) file container, where each atomistic structure is stored as a PyTorch-Geometric Data object. The file "export_dataset_environment_variables.sh" contains the environment variables that need to be set before running the HydraGNN code to reproduce the results provided in this dataset release. The code that can be used to load the ADIOS2 files, load HydraGNN models, and run inference is available at: https://github.com/ORNL/HydraGNN/releases/tag/v5.0

36 MATERIALS SCIENCE↗

DOE OSTI2025

Hybrid PDES Simulation of HPC Networks Using Zombie Packets

Although high-fidelity network simulations have proven to be reliable and cost-effective tools to peer into architectural questions for high-performance computing (HPC) networks, they incur a high resource cost. The time spent in simulating a single millisecond of network traffic in the highest detail can take hours, even for static, well-behaved traffic patterns such as uniform random. Surrogate models offer a significant reduction in runtime, yet they cannot serve as complete replacements and should only be used when appropriate. Thus, there is a need for hybrid modeling, where high-fidelity simulation and surrogates run side-by-side. Here, we present a surrogate model for HPC networks in which: packets bypass the network, while the network state is left untouched, i.e., suspended. To bypass the network, we use historical data to estimate the arrival time at which every packet should be scheduled at; to suspend the network, all in-flight packets are scheduled to arrive at their destinations, and are kept in the system to awaken as zombies when switching back to high-fidelity. Speedup for a hybrid model is relative to the proportion of surrogate to high-fidelity. This light-weight surrogate obtained up to 76× speedup. Keeping the zombies in the network showed an increase in the accuracy of the high-fidelity simulation on restart when compared to restarting the network from an empty state.

HPC networks↗

DOE OSTI2025

Track reconstruction as a service for collider physics

Optimizing charged-particle track reconstruction algorithms is crucial for efficient event reconstruction in Large Hadron Collider (LHC) experiments due to their significant computational demands. Existing track reconstruction algorithms have been adapted to run on massively parallel coprocessors, such as graphics processing units (GPUs), to reduce processing time. Nevertheless, challenges remain in fully harnessing the computational capacity of coprocessors in a scalable and non-disruptive manner. This paper proposes an inference-as-a-service approach for particle tracking in high energy physics experiments. To evaluate the efficacy of this approach, two distinct tracking algorithms are tested: Patatrack, a rule-based algorithm, and Exa.TrkX, a machine learning-based algorithm. The as-a-service implementations show enhanced GPU utilization and can process requests from multiple CPU cores concurrently without increasing per-request latency. The impact of data transfer is minimal and insignificant compared to running on local coprocessors. This approach greatly improves the computational efficiency of charged particle tracking, providing a solution to the computing challenges anticipated in the High-Luminosity LHC era.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

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↗

DOE OSTI2021

Scalable Pattern Matching in Metadata Graphs via Constraint Checking

Pattern matching is a fundamental tool for answering complex graph queries. Unfortunately, existing solutions have limited capabilities: They do not scale to process large graphs and/or support only a restricted set of search templates or usage scenarios. Moreover, the algorithms at the core of the existing techniques are not suitable for today’s graph processing infrastructures relying on horizontal scalability and shared-nothing clusters, as most of these algorithms are inherently sequential and difficult to parallelize. In this article we present an algorithmic pipeline that bases pattern matching on constraint checking. The key intuition is that each vertex and edge participating in a match has to meet a set of constraints implicitly specified by the search template. These constraints can be verified independently and typically are less expensive to compute than searching the full template. The pipeline we propose generates these constraints and iterates over them to eliminate all the vertices and edges that do not participate in any match, thus reducing the background graph to a subgraph that is the union of all template matches—the complete set of all vertices and edges that participate in at least one match. Additional analysis can be performed on this annotated, reduced graph, such as full match enumeration, match counting, or computing vertex/edge centrality. Furthermore, a vertex-centric formulation for constraint checking algorithms exists, and this makes it possible to harness existing high-performance, vertex-centric graph processing frameworks. This technique (i) enables highly scalable pattern matching in metadata (labeled) graphs; (ii) supports arbitrary patterns with 100% precision; (iii) enables tradeoffs between precision and time-to-solution, while always selects all vertices and edges that participate in matches, thus offering 100% recall; and (iv) supports a set of popular data analytics scenarios. We implement our approach on top of HavoqGT, an open-source asynchronous graph processing framework, and demonstrate its advantages through strong and weak scaling experiments on massive scale real-world (up to 257 billion edges) and synthetic (up to 4.4 trillion edges) labeled graphs, respectively, and at scales (1,024 nodes / 36,864 cores), orders of magnitude larger than used in the past for similar problems. This article serves two purposes: First, it synthesises the knowledge accumulated during a long-term project. Second, it presents new system features, usage scenarios, optimizations, and comparisons with related work that strengthen the confidence that pattern matching based on iterative pruning via constraint checking is an effective and scalable approach in practice. The new contributions include the following: (i) We demonstrate the ability of the constraint checking approach to efficiently support two additional search scenarios that often emerge in practice, interactive incremental search and exploratory search. (ii) We empirically compare our solution with two additional state-of-the-art systems, Arabsque and TriAD. (iii) We show the ability of our solution to accommodate a more diverse range of datasets with varying properties, e.g., scale, skewness, label distribution, and match frequency. (iv) We introduce or extend a number of system features (e.g., work aggregation, load balancing, and the ability to cap the generated traffic) and design optimizations and demonstrate their advantages with respect to improving performance and scalability. (v) We present bottleneck analysis and insights into artifacts that influence performance. (vi) We present a theoretical complexity argument that motivates the performance gains we observe.

97 MATHEMATICS AND COMPUTING↗