Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Computational graph”

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 613 records · Page 34
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Machine-learning-aided cognitive reconfiguration for flexible-bandwidth HPC and data center networks [Invited]

This paper proposes a machine-learning (ML)-aided cognitive approach for effective bandwidth reconfiguration in optically interconnected datacenter/high-performance computing (HPC) systems. The proposed approach relies on a Hyper-X-like architecture augmented with flexible-bandwidth photonic interconnections at large scales using a hierarchical intra/inter-POD photonic switching layout. We first formulate the problem of the connectivity graph and routing scheme optimization as a mixed-integer linear programming model. A two-phase heuristic algorithm and a joint optimization approach are devised to solve the problem with low time complexity. Then, we propose an ML-based end-to-end performance estimator design to assist the network control plane with intelligent decision making for bandwidth reconfiguration. Numerical simulations using traffic distribution profiles extracted from HPC applications traces as well as random traffic matrices verify the accuracy performance of the ML design estimator ( < <#comment/> 9 % <#comment/> error) and demonstrate up to 5 × <#comment/> throughput gain from the proposed approach compared with the baseline Hyper-X network using fixed all-to-all intra/inter-portable data center interconnects.

Chen, Xiaoliang (ORCID:0000000278056237)↗
DOE OSTI2023

HBMax: Optimizing Memory Efficiency for Parallel Influence Maximization on Multicore Architectures

The goal of influence maximization is to select k most-influential vertices or seeds in a network, where influence is defined by a given diffusion process. The problem has a number of important applications such as viral marketing, information spread, and epidemic control. Although computing optimal seed set is NP-Hard, due to the submodular nature of the problem efficient approximation algorithms exist. However, even state-of-the-art parallel implementations are limited by a sampling step that incurs large memory footprints. This in turn limits the problem size reach and approximation quality. In this work, we study the memory footprint of the sampling process collecting reverse reachability information in the IMM algorithm over large real-world social networks. We present an adaptive and memory-efficient optimization approach for a state-of-the-art multi-threaded parallel influence maximization algorithm. Our approach,HuffMax, uses a portion of the reverse reachable (RR) sets collected by the algorithm to learn the characteristics of the graph. Then, it compresses the intermediate reverse reachability information with Huffman coding, and queries directly on the compressed data to preserve the memory savings obtained through compression. We also propose an efficient sampling strategy based on the distribution of RR sets, which can further reduce the computation time for typical social networks with long-tail distributions. Considering a NUMA architecture, we scale up our solution on 128-core CPUs and reduce the memory footprint by up to 45.7% with negligible time overhead (or even faster) and without perceivable loss of accuracy.

Chen, Xinyu↗
DOE OSTI2024

Scaling whole-chip QAOA for higher-order ising spin glass models on heavy-hex graphs

Abstract We show that the quantum approximate optimization algorithm (QAOA) for higher-order, random coefficient, heavy-hex compatible spin glass Ising models has strong parameter concentration across problem sizes from 16 up to 127 qubits for p = 1 up to p = 5, which allows for computationally efficient parameter transfer of QAOA angles. Matrix product state (MPS) simulation is used to compute noise-free QAOA performance. Hardware-compatible short-depth QAOA circuits are executed on ensembles of 100 higher-order Ising models on noisy IBM quantum superconducting processors with 16, 27, and 127 qubits using QAOA angles learned from a single 16-qubit instance using the JuliQAOA tool. We show that the best quantum processors find lower energy solutions up to p = 2 or p = 3, and find mean energies that are about a factor of two off from the noise-free distribution. We show that p = 1 QAOA energy landscapes remain very similar as the problem size increases using NISQ hardware gridsearches with up to a 414 qubit processor.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

LatticeAnalytics: Strut-Level Visualization and Inspection of Additively Manufactured Lattice Structures

Additive manufacturing (AM) is revolutionizing the production of custom components with complex internal geometries, essential for high-performance applications in diverse fields such as medicine and defense. These AM parts optimize strength while minimizing weight by utilizing internal lattice structures consisting of large quantities of small interconnected struts. However, the complexity of these structures, combined with the challenges of using X-ray Computed Tomography (XCT) data, makes validation of part reliability difficult. This ultimately inhibits the development of novel parts for our collaborating material scientists. Here, we introduce LatticeAnalytics, a novel framework specifically designed for visual inspection of defects in these lattice structures. Our framework offers an end-to-end solution that includes the data management of XCT scans, enables remote access for geographically dispersed teams through a web-based dashboard, and incorporates novel visualizations. Our analysis is facilitated by a coarse alignment between the lattice’s nominal model, a spatial graph, and the XCT data. We employ a simple VR-based approach for fast and rough alignment, followed by an offline registration and identification of the struts. With the nodes and struts aligned and identified in the volume, our framework allows querying of subvolumes containing a single strut at multiple resolutions. This avoids computation over the entire lattice and also allow for easy parallelization of down-stream computations, such as strut-specific metrics. To depict a fast overview of the strut quality, we introduce two innovative visual encodings, crucial for our collaborators’ research in creating novel AM parts: the Contour View and the Roughness Map, which depict critical geometrical and surface features of individual struts in standardized two 2D views. We evaluated the integrated system through expert interviews. The feedback confirms the framework’s practicality and its effectiveness in enhancing current inspection workflows. It solves major bottlenecks for our collaborators, ultimately helping them create novel parts with advanced properties.

Miao, Haichao [Lawrence Livermore National Laborat↗
DOE OSTI2024

Efficient Parallelization of Irregular Applications on GPU Architectures

With the enlarging computation capacity of general Graphics Processing Units (GPUs), leveraging GPUs to accelerate parallel applications has become a critical topic in academia and industry. However, a wide range of irregular applications with the computation-/memory-intensive nature cannot easily achieve high GPU utilization. The challenges mainly involve the following aspects: first, data dependence leads to coarse-grained kernel and inefficient parallelism; second, heavy GPU memory usage may cause frequent memory evictions and extra overhead of I/O; third, specific computation patterns produce memory redundancies; last, workload balance and data reusability conjunctly benefit the overall performance, but there may exist a dynamic trade-off between them. Targeting these challenges, this dissertation proposes multiple optimizations to accelerate two real-world applications: many-body correlation functions to simulate nuclear physics in a large-scale scientific system; the other is the eALS-based matrix factorization recommendation system. To accelerate the calculations of many-body correlation functions, this dissertation presents three frameworks in GPU memory management and multi-GPU scheduling. Firstly, an optimized systematic GPU memory management framework, MemHC, utilizes a series of new memory reduction designs in GPU memory allocation, CPU/GPU communications, and GPU memory oversubscription. Secondly, an enhanced multi-GPU scheduling framework, MICCO, particularly by taking both data dimension (e.g., data reuse and data eviction) and computation dimension into account. MICCO designs a heuristic scheduling algorithm and a machine learning-based regression model to generate the optimal settings of a proposed new concept to manage the trade-off. Thirdly, a locality-aware multi-GPU scheduling framework. This scheduler leverages pipeline batch generation with a looking-ahead strategy by building local dependency graphs for memory transfer reduction and better data reuse, achieving up to 79.92% memory cost reduction and 1.67x speedup. To parallelize the eALS-based recommendation system, this dissertation proposes an efficient CPU/GPU heterogeneous recommendation system, HEALS. HEALS employs newly designed architecture-adaptive data formats to achieve load balance and good data locality on CPU and GPU. To mitigate the data dependence, HEALS presents a CPU/GPU collaboration model for both task parallelism and data parallelism with multiple kernel computation optimizations. In summary, this dissertation efficiently accelerates two typical irregular applications on GPUs by building four frameworks, including CPU/GPU collaboration, GPU memory management, and multi-GPU scheduling.

Wang, Qihan↗
DOE OSTI2022

Efficient and universal characterization of atomic structures through a topological graph order parameter

Abstract A graph-based order parameter, based on the topology of the graph itself, is introduced for the characterization of atomistic structures. The order parameter is universal to any material/chemical system and is transferable to all structural geometries. Four sets of data are used to validate both the generalizability and accuracy of the algorithm: (1) liquid lithium configurations spanning up to 300 GPa, (2) condensed phases of carbon along with nanotubes and buckyballs at ambient and high temperature, (3) a diverse set of aluminum configurations including surfaces, compressed and expanded lattices, point defects, grain boundaries, liquids, nanoparticles, all at nonzero temperatures, and (4) eleven niobium oxide crystal phases generated with ab initio molecular dynamics. We compare our proposed method to existing, state-of-the-art methods for the cases of aluminum and niobium oxide. Our order parameter uniquely classifies every configuration and outperforms all studied existing methods, opening the door for its use in a multitude of complex application spaces that can require fine structure-level characterization of atomistic graphs.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Improved Line Outage Detection in Transmission Systems with Few PMUs

Unlike transmission systems, distribution systems historically lack enough measurements, making their real-time monitoring almost impossible. Recent deployment of diverse types of devices such as phasor measurement units (PMUs), smart meters, solar inverters and weather information sensors opens up new ways of monitoring these systems, with the assistance of customized machine learning (ML) applications. The paper describes a grid-model-informed machine learning (ML) tool which integrates heterogeneous data streams and creates synchronous measurement snapshots to be used by a hybrid robust state estimator (SE) which provides not only accurate state estimates but also real-time feedback for ML model refinement. Improved monitoring performance due to the use of developed computational framework is experimentally observed by simulated scenarios on an electric utility’s distribution system.

Distribution systems, graph learning, machine lear↗
DOE OSTI2021

A Kinetic Monte Carlo Approach for Simulating Cascading Transmission Line Failure

In this work, cascading transmission line failures are studied through a dynamical model of the power system operating under fixed conditions. The power grid is modeled as a stochastic dynamical system where first-principles electromechanical dynamics are excited by small Gaussian disturbances in demand and generation around a specified operating point. In this context, a single line failure is interpreted in a large deviation context as a first escape event across a surface in phase space defined by line security constraints. The resulting system of stochastic differential equations admits a transverse decomposition of the drift, which leads to considerable simplification in evaluating the quasipotential (rate function) and, consequently, computation of exit rates. Tractable expressions for the rate of transmission line failure in a restricted network are derived from large deviation theory arguments and validated against numerical simulations. Extensions to realistic settings are considered, and individual line failure models are aggregated into a Markov model of cascading failure inspired by chemical kinetics. Cascades are generated by traversing a graph composed of weighted edges representing transitions to degraded network topologies. Numerical results indicate that the Markov model can produce cascades with qualitative power-law properties similar to those observed in empirical cascades.

Kinetic Monte Carlo, rare events, Cascading Failur↗
DOE OSTI2020

Equations of State in Computational Physics: What, Why, and How

Summary: 1. Equations of state furnish thermodynamic properties of a material. 2. Usually involve P, p (or V), and T, or P, r, and E 3. Necessary ingredient to solve compressible flow problems. 4. Varieties: i. Analytical expressions (ideal gas, Grüneisen) – fast, convenient for verification and test problems ii. Graphs and charts – good for hand calculations iii. Tables and databases – generally most accurate, require interpolation i. Steam tables ii. NIST database iii. SESAME EOS Library 5. Constructed by using semi-empirical models from Statistical Mechanics and fitting to available data

36 MATERIALS SCIENCE↗
DOE OSTI2025

Comparing three generations of D-Wave quantum annealers for minor embedded combinatorial optimization problems

Abstract Quantum annealing (QA) is a novel type of analog computation that aims to use quantum mechanical fluctuations to search for optimal solutions of Ising problems. QA in the transverse Ising model, implemented on D-Wave quantum processing units, are available as cloud computing resources. In this study we report concise benchmarks across three generations of D-Wave quantum annealers, consisting of four different devices, for the NP-hard discrete combinatorial optimization problems unweighted maximum clique and unweighted maximum cut on random graphs. The Ising, or equivalently quadratic unconstrained binary optimization, formulation of these problems do not require auxiliary variables for order reduction, and their overall structure and weights are not highly variable, which makes these problems simple test cases to understand the sampling capability of current D-Wave quantum annealers. All-to-all minor embeddings of size 52, with relatively uniform chain lengths, are used for a direct comparison across the Chimera, Pegasus, and Zephyr device topologies. A grid-search over annealing times and the minor embedding chain strengths is performed in order to determine the level of reasonable performance for each device and problem type. Experiment metrics that are reported are approximation ratios for non-broken chain samples, chain break proportions, and time-to-solution for the maximum clique problem instances. How fairly the quantum annealers sample optimal maximum cliques, for instances which contain multiple maximum cliques, is quantified using entropy of the measured ground state distributions. The newest generation of quantum annealing hardware, which has a Zephyr hardware connectivity, performed the best overall with respect to approximation ratios and chain break frequencies.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Parallelization techniques for quantum simulation of fermionic systems

Mapping fermionic operators to qubit operators is an essential step for simulating fermionic systems on a quantum computer. We investigate how the choice of such a mapping interacts with the underlying qubit connectivity of the quantum processor to enable (or impede) parallelization of the resulting Hamiltonian-simulation algorithm. It is shown that this problem can be mapped to a path coloring problem on a graph constructed from the particular choice of encoding fermions onto qubits and the fermionic interactions onto paths. The basic version of this problem is called the weak coloring problem. Taking into account the fine-grained details of the mapping yields what is called the strong coloring problem, which leads to improved parallelization performance. A variety of illustrative analytical and numerical examples are presented to demonstrate the amount of improvement for both weak and strong coloring-based parallelizations. Our results are particularly important for implementation on near-term quantum processors where minimizing circuit depth is necessary for algorithmic feasibility.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Large-scale experimental validation of thermochemical water-splitting oxides discovered by defect graph neural networks

Thermochemical water-splitting (TCH) based on 2-step thermal redox cycles in metal oxides is a promising approach to generating H 2 , but state-of-the-art (SOTA) CeO 2 has several practical limitations, which has motivated continued materials discovery efforts in this field. Here, in this study, we improve upon a SOTA defect graph neural network (dGNN) surrogate model's oxygen vacancy predictions and combine them with materials project phase diagrams to down-select and discover structurally diverse, experimentally known metal oxides whose TCH performance was previously unknown. Amongst twelve candidates selected based on our high-throughput screening and down-selection criteria, we achieved ∼80% accuracy in identifying materials with stable redox cycling and hydrogen production in stagnation flow reactor water-splitting experiments. Closer to 100% accuracy can be achieved if higher-accuracy, hybrid DFT-predicted vacancy formation energies were computed and used in lieu of the most uncertain dGNN-based screening predictions, as they correct false positives to true negatives. Notably, two discovered candidates, Sr 3 PrMn 2 O 8 and Ba 2 Fe 2 O 5 , display hydrogen yields greater than CeO 2 under specific redox conditions. In conclusion, these results demonstrate our ability to computationally predict and experimentally validate promising candidate TCH materials that have the potential to compete with CeO 2 .

08 HYDROGEN↗
DOE OSTI2024

Graph network heterogeneity predicts interplant wake losses

Wind plants generate large-scale wakes, which can affect the performance of neighboring installations. Such wakes are challenging to estimate due to the inherent complexity in modeling wake interactions between large quantities of turbines at various distances. Weighted directed graph networks can inform complex models by linking turbine pairs into chains of upstream and downstream neighbors for a given wind direction. A novel interpretation of the graph network adjacency matrix is proposed where each element of the matrix represents the cumulative impact of upstream turbines on an individual. In this study, wake losses were estimated with an engineering wake model across a range of inflow conditions for nine parametric variations of a system containing two neighboring wind plants. The parametric nature of the study isolates turbine spacing within the plant, separation distance between plants, and wind direction as the main drivers of wake losses. Spatial heterogeneity is computed from the weighted average adjacency matrix of each plant arrangement. The proposed method is orders of magnitude faster than wake modeling and does not require detailed turbine information or atmospheric conditions. Furthermore, the weighted average adjacency matrix provides insight on the spatial organization of wake losses at various scales. Plant heterogeneity is correlated with wake losses within and among plants. Framing wind plant wake interaction in terms of graph network spatial heterogeneity provides an efficient approach for predicting wake losses within and among neighboring wind plants with applications to other complex systems where wake interactions are key factor.

17 WIND ENERGY↗
DOE OSTI2022

graphenv: a Python library for reinforcement learning on graph search spaces

Many important and challenging problems in combinatorial optimization (CO) can be expressed as graph search problems, in which graph vertices represent full or partial solutions and edges represent decisions that connect them. Graph structure not only introduces strong relational inductive biases for learning (Battaglia et al., 2018) - in this context, by providing a way to explicitly model the value of transitioning (along edges) between one search state (vertex) and the next - but lends itself to problems both with and without clearly defined algebraic structure. For example, classic CO problems on graphs such as the Traveling Salesman Problem (TSP) can be expressed as either pure graph search or integer programs. Other problems, however, such as molecular optimization, do no have concise algebraic formulations and yet are readily implemented as a graph search (V. et al., 2022; Zhou et al., 2019). Such "model-free" problems constitute a large fraction of modern reinforcement learning (RL) research owing to the fact that it is often much easier to write a forward simulation that expresses all of the state transitions and rewards, than to write down the precise mathematical expression of the full optimization problem. In the case of molecular optimization, for example, one can use domain knowledge alongside existing software libraries to model the effect of adding a single bond or atom to an existing but incomplete molecule, and let the RL algorithm build a model of how good a given decision is by "experiencing" the simulated environment many times through. In contrast, a model-based mathematical formulation that fully expresses all the chemical and physical constraints is intractable. In recent years, RL has emerged as an effective paradigm for optimizing searches over graphs and led to state-of-the-art heuristics for games like Go and chess, as well as for classical CO problems such as the TSP. This combination of graph search and RL, while powerful, requires non-trivial software to execute, especially when combining advanced state representations such as Graph Neural Networks (GNN) with scalable RL algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

AMORE-Isoprene v1.0: a new reduced mechanism for gas-phase isoprene oxidation

Abstract. Gas-phase oxidation of isoprene by ozone (O3) and the hydroxyl (OH) and nitrate (NO3) radicals significantly impacts tropospheric oxidant levels and secondary organic aerosol formation. The most comprehensive and up-to-date chemical mechanism for isoprene oxidation consists of several hundred species and over 800 reactions. Therefore, the computational expense of including the entire mechanism in large-scale atmospheric chemical transport models is usually prohibitive, and most models employ reduced isoprene mechanisms ranging in size from ∼ 10 to ∼ 200 species. We have developed a new reduced isoprene oxidation mechanism using a directed-graph path-based automated model reduction approach, with minimal manual adjustment of the output mechanism. The approach takes as inputs a full isoprene oxidation mechanism, the environmental parameter space, and a list of priority species which are protected from elimination during the reduction process. Our reduced mechanism, AMORE-Isoprene (where AMORE stands for Automated Model Reduction), consists of 12 species which are unique to the isoprene mechanism as well as 22 reactions. We demonstrate its performance in a box model in comparison with experimental data from the literature and other current isoprene oxidation mechanisms. AMORE-Isoprene's performance with respect to predicting the time evolution of isoprene oxidation products, including isoprene epoxydiols (IEPOX) and formaldehyde, is favorable compared with other similarly sized mechanisms. When AMORE-Isoprene is included in the Community Regional Atmospheric Chemistry Multiphase Mechanism 1.0 (CRACMM1AMORE) in the Community Multiscale Air Quality Model (CMAQ, v5.3.3), O3 and formaldehyde agreement with Environmental Protection Agency (EPA) Air Quality System observations is improved. O3 bias is reduced by 3.4 ppb under daytime conditions for O3 concentrations over 50 ppb. Formaldehyde bias is reduced by 0.26 ppb on average for all formaldehyde measurements compared with the base CRACMM1. There was no significant change in computation time between CRACMM1AMORE and the base CRACMM. AMORE-Isoprene shows a 35 % improvement in agreement between simulated IEPOX concentrations and chamber data over the base CRACMM1 mechanism when compared in the Framework for 0-D Atmospheric Modeling (F0AM) box model framework. This work demonstrates a new highly reduced isoprene mechanism and shows the potential value of automated model reduction for complex reaction systems.

58 GEOSCIENCES↗