Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel cluster”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing

The next generation HPC and data centers are likely to be reconfigurable and data-centric due to the trend of hardware specialization and the emergence of data-driven applications. In this work, we propose ARENA – an asynchronous reconfigurable accelerator ring architecture as a potential scenario on how the future HPC and data centers will be like. Despite using the coarse-grained reconfigurable arrays (CGRAs) as the substrate platform, our key contribution is not only the CGRA-cluster design itself, but also the ensemble of a new architecture and programming model that enables asynchronous tasking across a cluster of reconfigurable nodes, so as to bring specialized computation to the data rather than the reverse. We presume distributed data storage without asserting any prior knowledge on the data distribution. Hardware specialization occurs at runtime when a task finds the majority of data it requires are available at the present node. In other words, we dynamically generate specialized CGRA accelerators where the data reside. The asynchronous tasking for bringing computation to data is achieved by circulating the task token, which describes the dataflow graphs to be executed for a task, among the CGRA cluster connected by a fast ring network. Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement (53.9 percent). Compared with contemporary compute-centric parallel models, ARENA can bring on average 4.37× speedup. The synthesized CGRAs and their task-dispatchers only occupy 2.93mm 2 chip area under 45nm process technology and can run at 800MHz with on average 759.8mW power consumption. ARENA also supports the concurrent execution of multi-applications, offering ideal architectural support for future high-performance parallel computing and data analytics systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Reducing Communication in Graph Neural Network Training

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which have lower arithmetic intensity and thus higher communication costs compared to dense matrices, making GNNs harder to scale to high concurrencies than convolutional or fully-connected neural networks. Here, we introduce a family of parallel algorithms for training GNNs and show that they can asymptotically reduce communication compared to previous parallel GNN training methods. We implement these algorithms, which are based on 1D, 1. 5D, 2D, and 3D sparse-dense matrix multiplication, using torch.distributed on GPU-equipped clusters. Our algorithms optimize communication across the full GNN training pipeline. We train GNNs on over a hundred GPUs on multiple datasets, including a protein network with over a billion edges.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

ArborX 2.0

ArborX library tackles a problem of efficiently finding geometric objects that are close in space. Variations of this problem, such as finding the nearest neighbors of a point, or finding all objects within a certain distance, are inherent components of applications in many fields. The data may be large so that solving the problem efficiently may require significant computational resources, such as multiple processors or accelerators such as general purpose GPUs. ArborX' main advantage in its ability to solve large problems efficiently utilizing a combination of distributed and on-node parallelism. ArborX can be run efficiently on a wide variety of hardware, including GPUs from different vendors, which distinguishes it from other available libraries which typically choose only few of these. The other advantage is that it supports both types of user problems: spatial problems (useful for intersections and finding objects within certain distance), and nearest neighbor problems. ArborX also supports flexible interface in its interaction with a user. Particularly, it allows a user to call user's own function on a positive match, a functionality not rarely available in other libraries. ArborX implements construction and traversal algorithms using efficient tree structures, such as bounding volume hierarchy (BVH). At its core, ArborX uses linear BVH for its low construction cost and sufficient quality. ArborX implements both spatial and nearest-neighbor traversal algorithms. ArborX also provides several clustering algorithms (minimum spanning tree, DBSCAN, HDBSCAN*), interpolation using minimum least squares and ray tracing. ArborX is written using C++, and is parallelized using the message passing interface (MPI) for the distributed communication, and the Kokkos library for on-node parallelism. This approach allows ArborX to be run on a wide variety of hardware, from common laptops and desktops to supercomputers while using the same codebase.

Prokopenko, Andrey [Oak Ridge National Laboratory ↗
DOE OSTI2019

Introducing Nonstructural Ligands to Zirconia-like Metal–Organic Framework Nodes To Tune the Activity of Node-Supported Nickel Catalysts for Ethylene Hydrogenation [Introducing Nonstructural Ligands to Zirconia-like MOF Nodes To Tune the Activity of Node-Supported Nickel Catalysts for Ethylene Hydrogenation]

Previous work has shown that introduction of hexafluoroacetylacetone (Facac) units as nonstructural ligands for the zirconia-like nodes of the eight-connected metal-organic framework (MOF), NU-1000, greatly alters the selectivity of node-supported oxy-nickel clusters for ethylene dimerization vs oligomerization. Here we i explore a related concept: tuning of support/catalyst interactions, and therefore, catalyst activity, via parallel installation of organic modifiers on the support itself. As modifiers we focused on para-substituted benzoates (R-BA – ; R = -NH 2 , -OCH 3 , -CH 3 , -H, -F, and -NO 2 ) where the substituents were chosen to present similar steric demand, but varying electron-donating or electron-withdrawing properties. R-benzoate-engendered shifts in the node-based aqua O-H stretching frequency for NU-1000, as measured by DRIFTS (diffuse-reflectance infrared Fourier-transform spectroscopy), together with systematic shifts in Ni 2p peak energies, as measured by X-ray photoelectron spectroscopy, show that the electronic properties of the support can be modulated. The vibrational and electronic peak shifts correlate with the putative electron-withdrawing vs electron-donating strength of the para-substituted benzoate modifiers. Subsequent installation of node-supported, oxy-Ni(II) clusters for ethylene hydrogenation yield a compelling correlation between log (catalyst turnover frequency) and the electron donating or withdrawing character of the substituent of the benzoate units. Single crystal X-ray diffraction measurements reveal that each organic modifier makes use of only one of two available carboxylate oxygens to accomplish grafting. The remaining oxygen atom is, in principle, well positioned to coordinate directly to an installed Ni(II) ion. We postulate that the unanticipated direct coordination of the catalyst by the node-modifier (rather than indirect modifier-based tuning of support(node)/catalyst electronic interactions) is the primary source of the observed systematic tuning of hydrogenation activity. Here we suggest, however, that regardless of mechanism for communication with active-sites of MOF-supported catalysts, intentional elaboration of nodes via grafted, nonstructural organic species could prove to be a valuable general strategy for fine-tuning supported-catalyst activity and/or selectivity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

On the Efficient Evaluation of the Exchange Correlation Potential on Graphics Processing Unit Clusters

The predominance of Kohn–Sham density functional theory (KS-DFT) for the theoretical treatment of large experimentally relevant systems in molecular chemistry and materials science relies primarily on the existence of efficient software implementations which are capable of leveraging the latest advances in modern high-performance computing (HPC). With recent trends in HPC leading toward increasing reliance on heterogeneous accelerator-based architectures such as graphics processing units (GPU), existing code bases must embrace these architectural advances to maintain the high levels of performance that have come to be expected for these methods. In this work, we purpose a three-level parallelism scheme for the distributed numerical integration of the exchange-correlation (XC) potential in the Gaussian basis set discretization of the Kohn–Sham equations on large computing clusters consisting of multiple GPUs per compute node. In addition, we purpose and demonstrate the efficacy of the use of batched kernels, including batched level-3 BLAS operations, in achieving high levels of performance on the GPU. We demonstrate the performance and scalability of the implementation of the purposed method in the NWChemEx software package by comparing to the existing scalable CPU XC integration in NWChem.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A network approach for multiscale catchment classification using traits

Abstract. The classification of river catchments into groups with similar biophysical characteristics is useful to understand and predict their hydrological behavior. The increasing availability of remote sensing and other large-scale geospatial datasets has enabled the use of advanced data-driven approaches to classify catchments using traits such as topography, geology, climate, land cover, land use, and human influence. Unsupervised clustering algorithms based on the Euclidean distance are commonly used for trait-based classification but are not suitable for highly dimensional data. In this study we present a new network-based method for multi-scale catchment classification, which can be applied to large datasets and used to determine the traits associated with different catchment groups. In this framework, two networks are analyzed in parallel: the first being where the nodes are traits and the second being where the nodes are catchments. In both cases, edges represent pairwise similarity, and a network cluster detection algorithm is used for the classification. The trait network is used to investigate redundancy in the trait data and to condense this information into a small number of interpretable categories. The catchments network is used to classify the catchments into clusters and to identify representative catchments for the different groups using the degree centrality metric. We apply this method to classify 9067 river catchments across the contiguous United States at both regional and continental scales using 274 non-categorical traits. At the continental scale, we identify 25 interpretable trait categories and 34 catchment clusters of sizes greater than 50. We find that catchments with similar trait categories are typically located in the same region, with different spatial patterns emerging among clusters dominated by natural and anthropogenic traits. We also find that the catchment clusters exhibit distinct hydrological behavior based on an analysis of streamflow indices. This network approach provides several advantages over traditional means of classification, including better separation of clusters, the use of alternate similarity metrics that are more suitable for highly dimensional data, and reducing redundancy in the trait information. The paired catchment–trait networks enable analysis of hydrological behavior using the dominant trait categories for each catchment cluster. The approach can be used at multiple spatial scales since the network topologies adjust automatically to reflect the trait patterns at the scale of investigation. Finally, the representative catchments identified as hub nodes in the network can be used to guide transferable observational and modeling strategies. The method is broadly applicable beyond hydrology for classification of other complex systems that utilize different types of trait datasets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Scalable All-pairs Shortest Paths for Huge Graphs on Multi-GPU Clusters

We present an optimized Floyd-Warshall (Floyd-Warshall) algorithm that computes the All-pairs shortest path (APSP) for GPU accelerated clusters. The Floyd-Warshall algorithm due to its structural similarities to matrix-multiplication is well suited for highly parallel GPU architectures. To achieve high parallel efficiency, we address two key algorithmic challenges: reducing high communication overhead and addressing limited GPU memory. To reduce high communication costs, we redesign the parallel (a) to expose more parallelism, (b) aggressively overlap communication and computation with pipelined and asynchronous scheduling of operations, and (c) tailored MPI-collective. To cope with limited GPU memory, we employ an offload model, where the data resides on the host and is transferred to GPU on-demand. The proposed optimizations are supported with detailed performance models for tuning. Our optimized parallel Floyd-Warshall implementation is up to 5x faster than a strong baseline and achieves 8.1 PetaFLOPS/sec on 256~nodes of the Summit supercomputer at Oak Ridge National Laboratory. This performance represents 70% of the theoretical peak and 80% parallel efficiency. The offload algorithm can handle 2.5x larger graphs with a 20% increase in overall running time.

Sao, Piyush↗
DOE OSTI2020

Unidirectional growth of graphene nano-islands from carbon cluster seeds on Ge(1 1 0)

The anisotropic twofold symmetry of Ge(1 1 0) makes it a unique substrate for the growth of single-crystalline graphene. However, the underlying mechanism during the initial stage of growth of graphene on Ge(1 1 0) surface is not well understood. Here, we use in-situ cryogenic scanning tunneling microscopy (STM) and spectroscopy (STS), to study the initial growth properties of graphene synthesized on Ge(1 1 0) surface with ethylene precursor gases. The STM results reveal that the unidirectional growth of the graphene nanoribbons (GNRs) initiates from carbon cluster seeds on terraces during the early stage of the growth. The orientations of the GNRs show the same directions which are nearly parallel to the direction of the Ge(1 1 0) surface. This orientation is the same as that of the wafer-scale graphene grown on Ge(1 1 0). Subsequent growth, transformed the GNRs to graphene nanoislands (GNIs), which eventually coalesced to form single crystalline monolayer graphene. STS measurements demonstrated that the GNRs have small bandgaps induced by the confinement effect of graphene. Furthermore, this study provides an in-depth understanding of the growth mechanism of graphene on Ge(1 1 0) surface in various synthesis conditions.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Parallel performance of algebraic multigrid domain decomposition

Algebraic multigrid (AMG) is a widely used scalable solver and preconditioner for large-scale linear systems resulting from the discretization of a wide class of elliptic PDEs. While AMG has optimal computational complexity, the cost of communication has become a significant bottleneck that limits its scalability as processor counts continue to grow on modern machines. This article examines the design, implementation, and parallel performance of a novel algorithm, algebraic multigrid domain decomposition (AMG-DD), designed specifically to limit communication. The goal of AMG-DD is to provide a low-communication alternative to standard AMG V-cycles by trading some additional computational overhead for a significant reduction in communication cost. Numerical results show that AMG-DD achieves superior accuracy per communication cost compared with AMG, and speedup over AMG is demonstrated on a large GPU cluster.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Local Distortions and Metal–Semiconductor–Metal Transition in Quasi-One-Dimensional Nanowire Compounds AV 3 Q 3 O δ (A = K, Rb, Cs and Q = Se, Te)

Metal cluster compounds have garnered renewed interest in the search for novel superconductors and topological semimetals owing to structural instabilities of metal-cluster geometries and broken symmetries. Here we synthesized needle-like crystals of the V-cluster-based quasi-one-dimensional (Q1D) materials AV 3 Q 3 O δ (A = K, Rb, Cs, Q= Se, Te) which can also be viewed as being composed of parallel nanowires. We examine how changes in their average and local structure control their electronic properties. All compounds crystallize in the TIFe 3 Te 3 -type structure (P6 3 /m space group) with infinite (V 3 )Q 3 ) - double-walled columnar chains separated by A + cations. Our single-crystal and synchrotron powder diffraction studies indicate oxygen atoms partially occupy the center site of the V 6 octahedral metal cluster cages in KV 3 Te 3 O 0.33 , RbV 3 Te 3 O 0.32 , and CsV 3 Te 3 O 0.35 , whereas KV 3 Se 3 is structurally oxygen-free. Our synchrotron X-ray pair distribution function (PDF) analyses indicate that the oxygen-free V 6 cluster octahedra in KV 3 Se 3 are highly distorted perpendicular to the chain direction even at room temperature, reducing the symmetry of the average structure from hexagonal P6 3 /m to monoclinic P2 1 /m. Our theoretical calculation supports this P2 1 /m distortion and suggests the structure further distorts to P2 1 or P2 1 /c at lower temperatures. In contrast, the oxygen-centered V-cluster in KV 3 Te 3 O 0.33 exhibits a V-3-triangle-trimerization along the chain direction. This feature is discernible from the local PDF and is consistent with lattice dynamical calculations based on density functional theory. Resistivity measurements indicate that KV 3 Se 3 exhibits metallic behavior, whereas a dramatic metal-semiconductor-metal transition emerges in KV 3 Te 3 O 6.33 , RbV 3 Te 3 O 0.32 , and CsV 3 Te 3 O 0.35 because of oxygen disorder and changes in local structure captured from our electronic structure analyses of the Fermi surface. Our investigation of the AV 3 Q 3 O 6 family demonstrates the importance of understanding local changes in structure driven by electronic instabilities, which can guide the search for new quantum materials in other low-dimensional cluster-compound materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

EJFAT: Towards Intelligent Compute Destination Load Balancing

To handle increased data flow, Jefferson Lab (JLab) is partnering with ESnet for development of an AI/ML directed compute work Load Balancer (LB) of UDP streamed data. The LB is FPGA based featuring dynamically configurable, low latency and high throughput destination address switching. The LB provides integration of edge and core computing to support JLab experimental programs, the Electron-Ion Collider, as well as data centers of the future. In the ESnet/JLab FPGA Accelerated Transport (EJFAT) initiative, the function of the LB Data Plane (DP) is to redirect data streams to selectable (but unknown to sender) destination hosts based on current worload and within that host to destination ports as a function of sub- stream id. This effects hierarchical scaling, first across compute machines for processing over a series of events and second, across ports so different data source sub-streams may be assigned to different processors for further parallelization. The LB Control Plane (CP) programs the DP using compute farm telemetry to direct and balance workloads across a compute cluster as the operating conditions require. While Proportional/Integrative/Derivative (PID) controllers are often seen in similar applications, here we investigate the feasibility of a Reinforcement Learning (RL) based schedule manager running in the CP to provide dynamic updates to the DP scheduling policy.

Lawrence, David↗
DOE OSTI2025

Unraveling the Determinant Mechanisms in Flow-Mediated Crystal Growth and Phase Behaviors

To uncover the critical mechanisms responsible for mesoscopic level development during flow-mediated crystal growth, we develop a semi-two-way hydrodynamic coupled structural phase-field crystal formalism (HXPFC-s2). The new formalism, inspired by previous attempts at coupling hydrodynamic and phase-field crystal (PFC) equations, allows for studying mesoscopic flow-mediated crystallization at diffusive timescales pertinent to industrial applications. Unlike previous efforts, the devised coupling to the structural PFC (XPFC) equations allows generalization to more complex crystal structures through explicit parameterization of the direct correlation function (DCF). Utilizing the HXPFC-s2 formalism, we seek to uncover the determinant physical mechanisms in crystallization under simple shear flows by comparing temperature-driven crystallization to flow-mediated crystallization under varying flow-strengths. Parallels and deviations of under-cooling and flow-strength effects on crystal growth are drawn using the crystal cluster-size and system ordering time evolutions. In doing so, we identify scaling behaviors with a Peclet-like number, Pe∼, a critical Peclet-like number, Pe∼*, and flow-field-crystal plane-dependent interactions. Our findings may be relevant for controlling crystal growth and phase behaviors in flow applications.

Willis, L. Connor (ORCID:0009000961321848)↗
DOE OSTI2024

The Effective Fragment Molecular Orbital Method: Achieving High Scalability and Accuracy for Large Systems

The effective fragment molecular orbital (EFMO) method has been developed to predict the total energy of a very large molecular system accurately (with respect to the underlying quantum mechanical method) and efficiently by taking advantage of the locality of strong chemical interactions and employing a two-level hierarchical parallelism. The accuracy of the EFMO method is partly attributed to the accurate and robust intermolecular interaction prediction between distant fragments, in particular, the many-body polarization and dispersion effects, which require the generation of static and dynamic polarizability tensors by solving the coupled perturbed Hartree–Fock (CPHF) and time-dependent HF (TDHF) equations, respectively. Solving the CPHF and TDHF equations is the main EFMO computational bottleneck due to the inefficient (serial) and I/O-intensive implementation of the CPHF and TDHF solvers. In this work, the efficiency and scalability of the EFMO method are significantly improved with a new CPU memory-based implementation for solving the CPHF and TDHF equations that are parallelized by either message passing interface (MPI) or hybrid MPI/OpenMP. Here, the accuracy of the EFMO method is demonstrated for both covalently bonded systems and noncovalently bound molecular clusters by systematically examining the effects of basis sets and a key distance-related cutoff parameter, R cut . R cut determines whether a fragment pair (dimer) is treated by the chosen ab initio method or calculated using the effective fragment potential (EFP) method (separated dimers). Decreasing the value of Rcut increases the number of separated (EFP) dimers, thereby decreasing the computational effort. It is demonstrated that excellent accuracy (<1 kcal/mol error per fragment) can be achieved when using a sufficiently large basis set with diffuse functions coupled with a small R cut value. With the new parallel implementation, the total EFMO wall time is substantially reduced, especially with a high number of MPI ranks. Given a sufficient workload, nearly ideal strong scaling is achieved for the CPHF and TDHF parts of the calculation. For the first time, EFMO calculations with the inclusion of long-range polarization and dispersion interactions on a hydrated mesoporous silica nanoparticle with explicit water solvent molecules (more than 15k atoms) are achieved on a massively parallel supercomputer using nearly 1000 physical nodes. In addition, EFMO calculations on the carbinolamine formation step of an amine-catalyzed aldol reaction at the nanoscale with explicit solvent effects are presented.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2019

GMRT 610 MHz observations of galaxy clusters in the ACT equatorial sample

Abstract We present Giant Metrewave Radio Telescope (GMRT) 610 MHz observations of 14 Atacama Cosmology Telescope (ACT) clusters, including new data for nine. The sample includes 73 per cent of ACT equatorial clusters with M500 > 5 × 1014 M⊙. We detect diffuse emission in three of these (27$^{+20}_{-14}$ per cent): we detect a radio minihalo in ACT-CL J0022.2–0036 at z = 0.8, making it the highest redshift minihalo known; we detect potential radio relic emission in ACT-CL J0014.9–0057 (z = 0.533); and we confirm the presence of a radio halo in low-mass cluster ACT-CL J0256.5+0006, with flux density S610 = 6.3 ± 0.4 mJy. We also detect residual diffuse emission in ACT-CL J0045.9–0152 (z = 0.545), which we cannot conclusively classify. For systems lacking diffuse radio emission, we determine radio halo upper limits in two ways and find via survival analysis that these limits do not significantly affect radio power scaling relations. Several clusters with no diffuse emission detection are known or suspected mergers, based on archival X-ray and/or optical measures; given the limited sensitivity of our observations, deeper observations of these disturbed systems are required in order to rule out the presence of diffuse emission consistent with known scaling relations. In parallel with our diffuse emission results, we present catalogues of individual radio sources, including a few interesting extended sources. Our study represents the first step towards probing the occurrence of diffuse emission in high-redshift (z ≳ 0.5) clusters, and serves as a pilot for statistical studies of larger cluster samples with the new radio telescopes available in the pre-SKA era.

Knowles, Kenda↗
DOE OSTI2025

Characterization of DESI fiber assignment incompleteness effect on 2-point clustering and mitigation methods for DR1 analysis

We present an in-depth analysis of the fiber assignment incompleteness in the Dark Energy Spectroscopic Instrument (DESI) Data Release 1 (DR1). This incompleteness is caused by the restricted mobility of the robotic fiber positioner in the DESI focal plane, which limits the number of galaxies that can be observed at the same time, especially at small angular separations. As a result, the observed clustering amplitude is suppressed in a scale-dependent manner, which, if not addressed, can severely impact the inference of cosmological parameters. We discuss the methods adopted for simulating fiber assignment on mocks and data. In particular, we introduce the fast fiber assignment (FFA) emulator, which was employed to obtain the power spectrum covariance adopted for the DR1 full-shape analysis. We present the mitigation techniques, organised in two classes: measurement stage and model stage. We then use high fidelity mocks as a reference to quantify both the accuracy of the FFA emulator and the effectiveness of the different measurement-stage mitigation techniques. This complements the studies conducted in a parallel paper for the model-stage techniques, namely the θ-cut approach. We find that pairwise inverse probability (PIP) weights with angular upweighting recover the “true” clustering in all the cases considered, in both Fourier and configuration space. Notably, we present the first ever power spectrum measurement with PIP weights from real data.

cosmological simulations↗
DOE OSTI2025

HARD: A performance portable radiation hydrodynamics code based on FleCSI framework

Hydrodynamics And Radiation Diffusion (HARD) is an open-source application for high-performance simulations of compressible hydrodynamics with radiation-diffusion coupling. Built on the FleCSI (Bergen et al., 2021 [1]) (Flexible Computational Science Infrastructure) framework, HARD expresses its computational units as tasks whose execution can be orchestrated by multiple back-end runtimes, including Legion (Bauer et al., 2012 [2]), MPI (Forum, 1994 [3]), and HPX (Kaiser et al., 2020 [4]). Node-level parallelism is handled through Kokkos (Edwards et al., 2014 [5]), providing a single-source, portable code base that runs efficiently on laptops, small homogeneous clusters, and the largest heterogeneous supercomputers currently available. To ensure scientific reliability, HARD includes a regression test suite that automatically reproduces canonical verification problems such as the Sod and LeBlanc shock tubes, and the Sedov blast wave, comparing numerical solutions against known analytical results. The project is distributed under an OSI-approved license, hosted on GitHub, and accompanied by reproducible build scripts and continuous integration workflows. This combination of performance portability, verification infrastructure, and community-focused development makes HARD a sustainable platform for advancing radiation hydrodynamics research across multiple domains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Two-Stage Gauss-Seidel Preconditioners and Smoothers for Krylov Solvers on a GPU Cluster: Preprint

Gauss-Seidel (GS) relaxation is often employed as a preconditioner for a Krylov solver or as a smoother for Algebraic Multigrid (AMG). However, the requisite sparse triangular solve is difficult to parallelize on many-core architectures such as graphics processing units (GPUs). In the present study, the performance of the sequential GS relaxation based on a triangular solve is compared with two-stage variants, replacing the direct triangular solve with a fixed number of inner Jacobi-Richardson (JR) iterations. When a small number of inner iterations is sufficient to maintain the Krylov convergence rate, the two-stage GS (GS2) often outperforms the sequential algorithm on many-core architectures. The GS2 algorithm is also compared with JR. When they perform the same number of ops for SpMV (e.g. three JR sweeps compared to two GS sweeps with one inner JR sweep), the GS2 iterations, and the Krylov solver preconditioned with GS2, may converge faster than the JR iterations. Moreover, for some problems (e.g. elasticity), it was found that JR may diverge with a damping factor of one, whereas two-stage GS may improve the convergence with more inner iterations. Finally, to study the performance of the two-stage smoother and preconditioner for a practical problem, these were applied to incompressible uid ow simulations on GPUs.

algebraic multigrid↗
DOE OSTI2022

MPLBM-UT: Multiphase LBM library for permeable media analysis

MPLBM-UT is a specialized lattice-Boltzmann library that makes running single- and two-phase flow simulations in porous media accessible to everyone. We provide a suite of tools to pre-process computational domains for simulation, to set up custom boundary conditions, to run simulations, to post-process simulation outputs, and to visualize simulation results and data. All of these tools are easily accessible to users through the mplbm_utils Python package included in and automatically installed with MPLBM-UT. The high-performance, highly parallel library Palabos is used as the solver backend. MPLBM-UT is easily deployed in a variety of systems, from laptops to supercomputer clusters. MPLBM-UT also features multiple examples and benchmark templates that allow for fast prototyping of different porous media problems. We also provide an interface for reading in different file types and downloading domains from the Digital Rocks Portal to perform simulations.

97 MATHEMATICS AND COMPUTING↗