Search NASA⌕ Search

SEARCH · Search NASA

Results for “partitioned algorithm”

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 289 records · Page 16

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (Distributed Parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve an optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively, the performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

Sattar, Naw Safrin↗

Scheduling and Performance of Asynchronous Tasks in Fortran 2018 with FEATS

Most parallel scientific programs contain compiler directives (pragmas) such as those from OpenMP (Hermanns in Parallel programming in Fortran 95 using openMP, 2002. School of Aeronautical Engineering, Universidad Politécnica de Madrid, España, 2011), explicit calls to runtime library procedures such as those implementing the Message Passing Interface (MPI) (in A message-passing interface standard version 4.0, 2021. https://www.mpi-forum.org/docs/mpi-4.0/mpi40-report.pdf), or compiler-specific language extensions such as those provided by CUDA (Ruetsch and Fatica in CUDA Fortran for scientists and engineers: best practices for efficient CUDA Fortran programming, Elsevier, 2013). By contrast, the recent Fortran standards empower developers to express parallel algorithms without directly referencing lower-level parallel programming models (Numrich in Parallel programming with co-arrays, CRC Press, 2018, and Curcic in Modern Fortran: building efficient parallel applications, Manning Publications, 2020). Fortran’s parallel features place the language within the Partitioned Global Address Space (PGAS) class of programming models. When writing programs that exploit data parallelism, application developers often find it straightforward to develop custom parallel algorithms. Problems involving complex, heterogeneous, staged calculations, however, pose much greater challenges. Such applications require careful coordination of tasks in a manner that respects dependencies prescribed by a directed acyclic graph. When rolling one’s own solution proves difficult, extending a customizable framework becomes attractive. Further, the paper presents the design, implementation, and use of the Framework for Extensible Asynchronous Task Scheduling (FEATS), which we believe to be the first task scheduling tool written in modern Fortran. We describe the benefits and compromises associated with choosing Fortran as the implementation language, and we propose ways in which future Fortran standards can best support the use case in this paper.

97 MATHEMATICS AND COMPUTING↗

A general ansatz for constructing quasi-diabatic states in electronically excited aggregated systems

We present a general method for analyzing the character of singly excited states in terms of charge transfer (CT) and locally excited (LE) configurations. The analysis is formulated for configuration interaction singles (CIS) singly excited wave functions of aggregate systems. It also approximately works for the second-order approximate coupled cluster singles and doubles and the second-order algebraic-diagrammatic construction methods [CC2 and ADC(2)]. The analysis method not only generates a weight of each character for an excited state, but also allows to define the related quasi-diabatic states and corresponding coupling matrix elements. In the character analysis approach, we divide the target system into domains and use a modified Pipek-Mezey algorithm to localize the canonical MOs on each domain, respectively. The CIS wavefunction is then transformed into the localized basis, which allows us to partition the wavefunction into LE configurations within domains and CT configuration between pairs of different domains. Quasi-diabatic states are then obtained by mixing excited states subject to the condition of maximizing the weight of one single LE or CT configuration (localization in configuration space). Different aims of such a procedure are discussed, either the construction of pure LE and CT states for analysis purposes (by including a large number of excited states) or the construction of effective models for dynamics calculations (by including a restricted number of excited states). Applications are given to LE/CT mixing in π-stacked systems, charge-recombination matrix elements in a hetero-dimer, and excitonic couplings in multi-chromophoric systems.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Filament capturing with the Multimaterial Moment-of-Fluid method

A novel method for capturing two-dimensional, thin, under-resolved material configurations, known as “filaments,” is presented in the context of interface reconstruction. This technique uses a partitioning procedure to detect disconnected regions of material in the advective preimage of a cell (indicative of a filament) and makes use of the existing functionality of the Multimaterial Moment-of-Fluid interface reconstruction method to accurately capture the under-resolved feature, while exactly conserving volume. An algorithm for Adaptive Mesh Refinement in the presence of filaments is developed so that refinement is introduced only near the tips of filaments and where the Moment-of-Fluid reconstruction error is still large. Comparison to the standard Moment-of-Fluid method is made. It is demonstrated that using filament capturing at a given resolution yields gains in accuracy comparable to introducing an additional level of mesh refinement at significantly lower cost.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

The unitary dependence theory for characterizing quantum circuits and states

Abstract Most existing quantum algorithms are discovered accidentally or adapted from classical algorithms, and there is the need for a systematic theory to understand and design quantum circuits. Here we develop a unitary dependence theory to characterize the behaviors of quantum circuits and states in terms of how quantum gates manipulate qubits and determine their measurement probabilities. Compared to the conventional entanglement description of quantum circuits and states, the unitary dependence picture offers more practical information on the measurement and manipulation of qubits, easier generalization to many-qubit systems, and better robustness upon partitioning of the system. The unitary dependence theory can be applied to systematically understand existing quantum circuits and design new quantum algorithms.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Self-organized topology of recurrence-based complex networks

With the rapid technological advancement, network is almost everywhere in our daily life. Network theory leads to a new way to investigate the dynamics of complex systems. As a result, many methods are proposed to construct a network from nonlinear time series, including the partition of state space, visibility graph, nearest neighbors, and recurrence approaches. However, most previous works focus on deriving the adjacency matrix to represent the complex network and extract new network-theoretic measures. Although the adjacency matrix provides connectivity information of nodes and edges, the network geometry can take variable forms. The research objective of this article is to develop a self-organizing approach to derive the steady geometric structure of a network from the adjacency matrix. We simulate the recurrence network as a physical system by treating the edges as springs and the nodes as electrically charged particles. Then, force-directed algorithms are developed to automatically organize the network geometry by minimizing the system energy. Further, a set of experiments were designed to investigate important factors (i.e., dynamical systems, network construction methods, force-model parameter, nonhomogeneous distribution) affecting this self-organizing process. Interestingly, experimental results show that the self-organized geometry recovers the attractor of a dynamical system that produced the adjacency matrix. This research addresses a question, i.e., “what is the self-organizing geometry of a recurrence network?” and provides a new way to reproduce the attractor or time series from the recurrence plot. As a result, novel network-theoretic measures (e.g., average path length and proximity ratio) can be achieved based on actual node-to-node distances in the self-organized network topology. The paper brings the physical models into the recurrence analysis and discloses the spatial geometry of recurrence networks.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Widespread underestimation of rain-induced soil carbon emissions from global drylands

Dryland carbon fluxes, particularly those driven by ecosystem respiration, are highly sensitive to water availability and rain pulses. However, the magnitude of rain-induced carbon emissions remains unclear globally. Here we quantify the impact of rain-pulse events on the carbon balance of global drylands and characterize their spatiotemporal controls. Using eddy-covariance observations of carbon, water and energy fluxes from 34 dryland sites worldwide, we produce an inventory of over 1,800 manually identified rain-induced CO2 pulse events. Based on this inventory, a machine learning algorithm is developed to automatically detect rain-induced CO2 pulse events. Our findings show that existing partitioning methods underestimate ecosystem respiration and photosynthesis by up to 30% during rain-pulse events, which annually contribute 16.9 ± 2.8% of ecosystem respiration and 9.6 ± 2.2% of net ecosystem productivity. We show that the carbon loss intensity correlates most strongly with annual productivity, aridity and soil pH. Finally, we identify a universal decay rate of rain-induced CO2 pulses and use it to bias-correct respiration estimates. Our research highlights the importance of rain-induced carbon emissions for the carbon balance of global drylands and suggests that ecosystem models may largely underrepresent the influence of rain pulses on the carbon cycle of drylands.

Nguyen, Ngoc B↗

True Load Balancing for Matricized Tensor Times Khatri-Rao Product

MTTKRP is the bottleneck operation in algorithms used to compute the CP tensor decomposition. For sparse tensors, utilizing the compressed sparse fibers (CSF) storage format and the CSF-oriented MTTKRP algorithms is important for both memory and computational efficiency on distributed-memory architectures. Existing intelligent tensor partitioning models assume the computational cost of MTTKRP to be proportional to the total number of nonzeros in the tensor. However, this is not the case for the CSF-oriented MTTKRP on distributed-memory architectures. We outline two deficiencies of nonzero-based intelligent partitioning models when CSF-oriented MTTKRP operations are performed locally: failure to encode processors' computational loads and increase in total computation due to fiber fragmentation. We focus on existing fine-grain hypergraph model and propose a novel vertex weighting scheme that enables this model encode correct computational loads of processors. We also propose to augment the fine-grain model by fiber nets for reducing the increase in total computational load via minimizing fiber fragmentation. In this way, the proposed model encodes minimizing the load of the bottleneck processor. In conclusion, parallel experiments with real-world sparse tensors on up to 1024 processors prove the validity of the outlined deficiencies and demonstrate the merit of our proposed improvements in terms of parallel runtimes.

97 MATHEMATICS AND COMPUTING↗

Zoltan2

Zoltan2 is a refactoring of the open-source Zoltan library that enables Zoltan users to take better advantage of current and emerging high performance computing architectures and software tools. Like Zoltan, Zoltan2 is a toolkit of combinatorial scientific computing algorithms that enable better performance of scientific codes via improved data locality and parallel scalability. Specifically Zoltan2 partitions data, colors graphs, and orders matrices. Zoltan2 is a software library written in template C++; it supports a wider range of data types and problem sizes than Zoltan. It will be available as part of Sandia's Trilinos framework of scientific computing packages.

Riesen, Lee Ann↗

A Low-Rank QTT-based Finite Element Method for Elasticity Problems

We present an efficient and robust numerical algorithm for solving the linear elasticity problem that combines the Quantized Tensor Train format and a domain partitioning strategy. This approach makes it possible to solve the linear elasticity problem on a computational domain that is more general than a square. By integrating Z-ordering and subdomain concatenation, our method substantially decreases memory usage and achieves a notable reduction in rank compared to established Finite Element implementations like the FEniCS platform. This efficiency is maintained while still guaranteeing exponential convergence with respect to the number of degrees of freedom. This performance gain, however, requires a fundamental rethinking of how core finite element operations are implemented. This includes changes to mesh discretization, node and degree of freedom ordering, stiffness matrix and internal nodal force assembly, and the execution of algebraic matrix-vector operations. In this work, we discuss all these aspects in detail and assess the method’s performance in the numerical approximation of three representative test cases.

97 MATHEMATICS AND COMPUTING↗

Graph-Based Representations and Applications to Process Simulation

Rapid and robust convergence of a process flowsheet is critical to enable large-scale simulations that address core scientific questions related to process design, optimization, and sustainability. However, due to the highly coupled and nonlinear nature of chemical processes, efficiently solving a flowsheet remains a challenge. In this work, we show that graph representations of the underlying physical phenomena in unit operations may help identify potential avenues to systematically reformulate the network of equations and enable more robust topology-based convergence of flowsheets. To this end, we developed graph abstractions of the governing equations of vapor-liquid and liquid-liquid equilibrium separation equipment. These graph abstractions consist of a mesh of interconnected variable nodes and equation nodes that are systematically generated through PhenomeNode, a new open-source library in Python developed in this study. We show that partitioning the graph into separate mass, energy, and equilibrium subgraphs can help decouple nonlinearities and guide decomposition algorithms. By employing the graph abstraction on an industrial separation process for separating glacial acetic acid from water, we implemented a new block decomposition scheme in BioSTEAM and demonstrated that this can accelerate convergence over a traditional sequential modular approach.

Distillation↗

Scaling to 150K cores: recent algorithm and performance engineering developments enabling XGC1 to run at scale

Particle-in-cell (PIC) methods have proven to be effective in discretizing the Vlasov-Maxwell system of equations describing the core of toroidal burning plasmas for many decades. Recent physical understanding of the importance of edge physics for stability and transport in tokamaks has lead to development of the fi rst fully toroidal edge PIC code - XGC1. The edge region poses special problems in meshing for PIC methods due to the lack of closed flux surfaces, which makes fi eld-line following meshes and coordinate systems problematic. We present a solution to this problem with a semi- field line following mesh method in a cylindrical coordinate system. Additionally, modern supercomputers require highly concurrent algorithms and implementations, with all levels of the memory hierarchy being effe ciently utilized to realize optimal code performance. This paper presents a mesh and particle partitioning method, suitable to our meshing strategy, for use on highly concurrent cache-based computing platforms.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Compact Graph Representations and Parallel Connectivity Algorithms for Massive Dynamic Network Analysis

Graph-theoretic abstractions are extensively used to analyze massive data sets. Temporal data streams from socioeconomic interactions, social networking web sites, communication traffic, and scientific computing can be intuitively modeled as graphs. We present the first study of novel high-performance combinatorial techniques for analyzing large-scale information networks, encapsulating dynamic interaction data in the order of billions of entities. We present new data structures to represent dynamic interaction networks, and discuss algorithms for processing parallel insertions and deletions of edges in small-world networks. With these new approaches, we achieve an average performance rate of 25 million structural updates per second and a parallel speedup of nearly28 on a 64-way Sun UltraSPARC T2 multicore processor, for insertions and deletions to a small-world network of 33.5 million vertices and 268 million edges. We also design parallel implementations of fundamental dynamic graph kernels related to connectivity and centrality queries. Our implementations are freely distributed as part of the open-source SNAP (Small-world Network Analysis and Partitioning) complex network analysis framework.

97 MATHEMATICS AND COMPUTING↗

Low-Cost Parallel Algorithms for 2:1 Octree Balance

The logical structure of a forest of octrees can be used to create scalable algorithms for parallel adaptive mesh refinement (AMR), which has recently been demonstrated for several petascale applications. Among various frequently used octree-based mesh operations, including refinement, coarsening, partitioning, and enumerating nodes, ensuring a 2:1 size balance between neighboring elements has historically been the most expensive in terms of CPU time and communication volume. The 2:1 balance operation is thus a primary target to optimize. One important component of a parallel balance algorithm is the ability to determine whether any two given octants have a consistent distance/size relation. Based on new logical concepts we propose fast algorithms for making this decision for all types of 2:1 balance conditions in 2D and 3D. Since we are able to achieve this without constructing any parent nodes in the tree that would otherwise need to be sorted and communicated, we can significantly reduce the required memory and communication volume. In addition, we propose a lightweight collective algorithm for reversing the asymmetric communication pattern induced by non-local octant interactions. We have implemented our improvements as part of the opensource “p4est” software. Benchmarking this code with both synthetic and simulation-driven adapted meshes we are able to demonstrate much reduced runtime and excellent weak and strong scalability. On our largest benchmark problem with 5.13 × 10 11 octants the new 2:1 balance algorithm executes in less than 8 seconds on 112,128 CPU cores of the Jaguar Cray XT5 supercomputer.

Computer Science↗

Accelerated finite element elastodynamic simulations using the GPU

An approach is developed to perform explicit time domain finite element simulations of elastodynamic problems on the graphical processing unit, using Nvidia's CUDA. Of critical importance for this problem is the arrangement of nodes in memory, allowing data to be loaded efficiently and minimising communication between the independently executed blocks of threads. The initial stage of memory arrangement is partitioning the mesh; both a well established ‘greedy’ partitioner and a new, more efficient ‘aligned’ partitioner are investigated. A method is then developed to efficiently arrange the memory within each partition. The software is applied to three models from the fields of non-destructive testing, vibrations and geophysics, demonstrating a memory bandwidth of very close to the card's maximum, reflecting the bandwidth-limited nature of the algorithm. Comparison with Abaqus, a widely used commercial CPU equivalent, validated the accuracy of the results and demonstrated a speed improvement of around two orders of magnitude. A software package, Pogo, incorporating these developments, is released open source, downloadable from (http://www.pogo-fea.com/) to benefit the community. -- Highlights: •A novel memory arrangement approach is discussed for finite elements on the GPU. •The mesh is partitioned then nodes are arranged efficiently within each partition. •Models from ultrasonics, vibrations and geophysics are run. •The code is significantly faster than an equivalent commercial CPU package. •Pogo, the new software package, is released open source.

58 GEOSCIENCES↗

The relationship between leaf area growth and biomass accumulation in Arabidopsis thaliana

Leaf area growth determines the light interception capacity of a crop and is often used as a surrogate for plant growth in high-throughput phenotyping systems. The relationship between leaf area growth and growth in terms of mass will depend on how carbon is partitioned among new leaf area, leaf mass, root mass, reproduction, and respiration. A model of leaf area growth in terms of photosynthetic rate and carbon partitioning to different plant organs was developed and tested with Arabidopsis thaliana L. Heynh. ecotype Columbia (Col-0) and a mutant line, gigantea-2 (gi-2), which develops very large rosettes. Data obtained from growth analysis and gas exchange measurements was used to train a genetic programming algorithm to parameterize and test the above model. The relationship between leaf area and plant biomass was found to be non-linear and variable depending on carbon partitioning. The model output was sensitive to the rate of photosynthesis but more sensitive to the amount of carbon partitioned to growing thicker leaves. The large rosette size of gi-2 relative to that of Col-0 resulted from relatively small differences in partitioning to new leaf area vs. leaf thickness.

carbon partitioning↗

Exact Enumeration of the Phase Space of an Ising Model of Ni2MnGa

Exact evaluations of partition functions are generally prohibitively expensive due to exponential growth of phase space with the number of degrees of freedom. For an Ising model with sites the number of possible states is requiring the use of better scaling methods such as importance sampling Monte-Carlo calculations for all but the smallest systems. Yet the ability to obtain exact solutions for as large as possible systems can provide important benchmark results and opportunities for unobscured insight into the underlying physicsofthesystem.HerewepresentanIsingmodelforthemagneticsublatticesoftheimportantmagneto-caloricmaterialNi MnGa and use an exact enumeration algorithm to calculate the number of states for each energy and sublattice magne- tizations and . This allows the efficient calculation of the partition function and derived thermodynamic quantities such as specific heat and susceptibility. Utilizing the jaguarpf system at Oak Ridge we are able to calculate for systems of up to48sites,whichprovidesimportantinsightintothemechanismforthelargemagnet-caloriceffectinNi MnGaaswellasanimportant benchmark for Monte-Carlo (esp. Wang-Landau method).

Eisenbach, Markus↗

Affinity of small-molecule solutes to hydrophobic, hydrophilic, and chemically patterned interfaces in aqueous solution

Significance Increasing global population, urbanization, and climate change pose tremendous constraints on water availability. While membrane processes offer attractive, energy-efficient options, transformative advances in membrane technology are needed to enable reuse of poor-quality waters from diverse sources. This work brings fundamental understanding of solute–surface interactions to membrane phenomena, including selectivity and fouling. Molecular simulations reveal limitations of traditional predictive measures of solute–surface partitioning, suggesting alternative thermodynamic signatures for solute binding that highlight the contextual nature of hydrophobicity. An inverse design algorithm provides a tool to pattern membrane nanoscale chemistry to optimize solute affinity and selectivity. This work demonstrates how simulations can inform practical materials design for sustainable water treatment and, more broadly, many technologies involving water-mediated solute–surface interactions.

36 MATERIALS SCIENCE↗