Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Parallel Computing”

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 1,747 records · Page 97
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Rigorous justification for the space–split sensitivity algorithm to compute linear response in Anosov systems

Ruelle gave a formula for linear response of transitive Anosov diffeomorphisms. Recently, practically computable realizations of Ruelle's formula have emerged that potentially enable sensitivity analysis of certain high-dimensional chaotic numerical simulations encountered in the applied sciences. In this paper, we provide full mathematical justification for the convergence of one such efficient computation, the space–split sensitivity, or S3, algorithm. In S3, Ruelle's formula is computed as a sum of two terms obtained by decomposing the perturbation vector field into a coboundary and a remainder that is parallel to the unstable direction. Such a decomposition results in a splitting of Ruelle's formula that is amenable to efficient computation. Here, we prove the existence of the S3 decomposition and the convergence of the computations of both resulting components of Ruelle's formula.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2017

A multi-platform evaluation of the randomized CX low-rank matrix factorization in Spark

We investigate the performance and scalability of the randomized CX low-rank matrix factorization and demonstrate its applicability through the analysis of a 1TB mass spectrometry imaging (MSI) dataset, using Apache Spark on an Amazon EC2 cluster, a Cray XC40 system, and an experimental Cray cluster. We implemented this factorization both as a parallelized C implementation with hand-tuned optimizations and in Scala using the Apache Spark high-level cluster computing framework. We obtained consistent performance across the three platforms: using Spark we were able to process the 1TB size dataset in under 30 minutes with 960 cores on all systems, with the fastest times obtained on the experimental Cray cluster. In comparison, the C implementation was 21X faster on the Amazon EC2 system, due to careful cache optimizations, bandwidth-friendly access of matrices and vector computation using SIMD units. We report these results and their implications on the hardware and software issues arising in supporting data-centric workloads in parallel and distributed environments.

Gittens, Alex↗
DOE OSTI2017

Hierarchical calibration and validation for modeling bench-scale solvent-based carbon capture. Part 1: Non-reactive physical mass transfer across the wetted wall column

A hierarchical model calibration and validation are proposed here for quantifying the confidence level of mass transfer prediction using a computational fluid dynamics (CFD) model, where the solvent-based carbon dioxide (CO 2 ) capture is simulated and the predicted results are compared to the corresponding bench-scale experimental data. Two unit problems with an increasing level of complexity are proposed to break down the complex physical/chemical processes of solvent-based CO 2 capture into relatively simpler problems to separate the effects of physical transport and chemical reaction. This paper focuses on the calibration and validation of the first unit problem, i.e., the CO 2 mass transfer across a falling ethanolamine (MEA) film in the absence of chemical reaction. This problem is investigated both experimentally and numerically using non-reactive nitrous oxide (N 2 O) as a surrogate for CO 2 . To capture motion of the gas-liquid interface, a volume of fluid method is employed with a one-fluid formulation to compute the mass transfer between the two phases. Parallel bench-scale experiments are designed and conducted to validate and calibrate the CFD models using a general Bayesian calibration approach. Two important transport parameters, Henry's constant and gas diffusivity, are calibrated to produce the posterior distributions, which will be used as input for the second unit problem to address the chemical absorption of CO 2 across the MEA falling film, where both mass transfer and chemical reaction are involved. Finally, mass transfer coefficients predicted by CFD are also compared with those predicted by the traditional/empirical correlations under both steady and wavy falling film conditions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Evaluating asynchronous Schwarz solvers on GPUs

With the commencement of the exascale computing era, we realize that the majority of the leadership supercomputers are heterogeneous and massively parallel. Even a single node can contain multiple co-processors such as GPUs and multiple CPU cores. For example, ORNL’s Summit accumulates six NVIDIA Tesla V100 GPUs and 42 IBM Power9 cores on each node. Synchronizing across compute resources of multiple nodes can be prohibitively expensive. Hence, it is necessary to develop and study asynchronous algorithms that circumvent this issue of bulk-synchronous computing. In this study, we examine the asynchronous version of the abstract Restricted Additive Schwarz method as a solver. We do not explicitly synchronize, but allow the communication between the sub-domains to be completely asynchronous, thereby removing the bulk synchronous nature of the algorithm. We accomplish this by using the one-sided Remote Memory Access (RMA) functions of the MPI standard. We study the benefits of using such an asynchronous solver over its synchronous counterpart. We also study the communication patterns governed by the partitioning and the overlap between the sub-domains on the global solver. Finally, we show that this concept can render attractive performance benefits over the synchronous counterparts even for a well-balanced problem.

Nayak, Pratik↗
DOE OSTI2025

Introduction: Neuromorphic Materials

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

Circuits↗
DOE OSTI2015

Parallel performance optimizations on unstructured mesh-based simulations

This paper addresses two key parallelization challenges the unstructured mesh-based ocean modeling code, MPAS-Ocean, which uses a mesh based on Voronoi tessellations: (1) load imbalance across processes, and (2) unstructured data access patterns, that inhibit intra- and inter-node performance. Our work analyzes the load imbalance due to naive partitioning of the mesh, and develops methods to generate mesh partitioning with better load balance and reduced communication. Furthermore, we present methods that minimize both inter- and intranode data movement and maximize data reuse. Our techniques include predictive ordering of data elements for higher cache efficiency, as well as communication reduction approaches. We present detailed performance data when running on thousands of cores using the Cray XC30 supercomputer and show that our optimization strategies can exceed the original performance by over 2×. Additionally, many of these solutions can be broadly applied to a wide variety of unstructured grid-based computations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Method and apparatus for offloading compute resources to a flash co-processing appliance

Solid-State Drive (SSD) burst buffer nodes are interposed into a parallel supercomputing cluster to enable fast burst checkpoint of cluster memory to or from nearby interconnected solid-state storage with asynchronous migration between the burst buffer nodes and slower more distant disk storage. The SSD nodes also perform tasks offloaded from the compute nodes or associated with the checkpoint data. For example, the data for the next job is preloaded in the SSD node and very fast uploaded to the respective compute node just before the next job starts. During a job, the SSD nodes perform fast visualization and statistical analysis upon the checkpoint data. The SSD nodes can also perform data reduction and encryption of the checkpoint data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Scale-up Unlearnable Examples Learning with High-performance Computing

Recent advancements in AI models, like ChatGPT, are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on online platforms, there is a risk that medical imaging data may be repurposed for future AI training without explicit consent, spotlighting critical privacy and intellectual property concerns around healthcare data usage. Addressing these privacy challenges, a novel approach known as Unlearnable Examples (UEs) has been introduced, aiming to make data unlearnable to deep learning models. A prominent method within this area, called Unlearnable Clustering (UC), has shown improved UE performance with larger batch sizes but was previously limited by computational resources (e.g., a single workstation). To push the boundaries of UE performance with theoretically unlimited resources, we scaled up UC learning across various datasets using Distributed Data Parallel (DDP) training on the Summit supercomputer. Our goal was to examine UE efficacy at high-performance computing (HPC) levels to prevent unauthorized learning and enhance data security, particularly exploring the impact of batch size on UE’s unlearnability. Utilizing the robust computational capabilities of the Summit, extensive experiments were conducted on diverse datasets such as Pets, MedMNist, Flowers, and Flowers102. Our findings reveal that both overly large and overly small batch sizes can lead to performance instability and affect accuracy. However, the relationship between batch size and unlearnability varied across datasets, highlighting the necessity for tailored batch size strategies to achieve optimal data protection. The use of Summit’s high-performance GPUs, along with the efficiency of the DDP framework, facilitated rapid updates of model parameters and consistent training across nodes. Our results underscore the critical role of selecting appropriate batch sizes based on the specific characteristics of each dataset to prevent learning and ensure data security in deep learning applications. The source code is publicly available at https: // github. com/ hrlblab/ UE_ HPC .

Zhu, Yanfan [Vanderbilt University, Nashville, TN,↗
DOE OSTI2017

Extreme-Scale De Novo Genome Assembly

De novo whole genome assembly reconstructs genomic sequence from short, overlapping, and potentially erroneous DNA segments and is one of the most important computations in modern genomics. This work presents HipMER, a high-quality end-to-end de novo assembler designed for extreme scale analysis, via efficient parallelization of the Meraculous code. Genome assembly software has many components, each of which stresses different components of a computer system. This chapter explains the computational challenges involved in each step of the HipMer pipeline, the key distributed data structures, and communication costs in detail. We present performance results of assembling the human genome and the large hexaploid wheat genome on large supercomputers up to tens of thousands of cores.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2015

Dynamic Non-Hierarchical File Systems for Exascale Storage

This constitutes the final report for “Dynamic Non-Hierarchical File Systems for Exascale Storage”. The ultimate goal of this project was to improve data management in scientific computing and high-end computing (HEC) applications, and to achieve this goal we proposed: to develop the first, HEC-targeted, file system featuring rich metadata and provenance collection, extreme scalability, and future storage hardware integration as core design goals, and to evaluate and develop a flexible non-hierarchical file system interface suitable for providing more powerful and intuitive data management interfaces to HEC and scientific computing users. Data management is swiftly becoming a serious problem in the scientific community – while copious amounts of data are good for obtaining results, finding the right data is often daunting and sometimes impossible. Scientists participating in a Department of Energy workshop noted that most of their time was spent “...finding, processing, organizing, and moving data and it’s going to get much worse”. Scientists should not be forced to become data mining experts in order to retrieve the data they want, nor should they be expected to remember the naming convention they used several years ago for a set of experiments they now wish to revisit. Ideally, locating the data you need would be as easy as browsing the web. Unfortunately, existing data management approaches are usually based on hierarchical naming, a 40 year-old technology designed to manage thousands of files, not exabytes of data. Today’s systems do not take advantage of the rich array of metadata that current high-end computing (HEC) file systems can gather, including content-based metadata and provenance1 information. As a result, current metadata search approaches are typically ad hoc and often work by providing a parallel management system to the “main” file system, as is done in Linux (the locate utility), personal computers, and enterprise search appliances. These search applications are often optimized for a single file system, making it difficult to move files and their metadata between file systems. Users have tried to solve this problem in several ways, including the use of separate databases to index file properties, the encoding of file properties into file names, and separately gathering and managing provenance data, but none of these approaches has worked well, either due to limited usefulness or scalability, or both. Our research addressed several key issues: High-performance, real-time metadata harvesting: extracting important attributes from files dynamically and immediately updating indexes used to improve search; Transparent, automatic, and secure provenance capture: recording the data inputs and processing steps used in the production of each file in the system; Scalable indexing: indexes that are optimized for integration with the file system; Dynamic file system structure: our approach provides dynamic directories similar to those in semantic file systems, but these are the native organization rather than a feature grafted onto a conventional system. In addition to these goals, our research effort will include evaluating the impact of new storage technologies on the file system design and performance. In particular, the indexing and metadata harvesting functions can potentially benefit from the performance improvements promised by new storage class memories.

42 ENGINEERING↗
DOE OSTI2020

Controlling Cation-Cation Interactions in Uranyl Coordination Dimers by Varying the Length of the Dicarboxylate Linker

The chemistry of linear uranyl(V/VI) dioxo cations, [O yl –U–O yl ] +/2+ , is dominated by coordination of uranium in the equatorial plane. Effects of this constraint were evaluated by experiment and theory for gas-phase mixed-valence U V/VI coordination dimers in which uranyl moieties are linked by alkyl dicarboxylates, [(UO 2 + )(UO 2 2+ )(OOC-(CH 2 ) n-2 -COO 2– ) 2 ] – (n = 3–12). Faster O 2 -addition to dimers with short linkers n = 3 and 4, vs. n ≥ 5, suggests a structural difference. Computed structures with the shortest linkers have bridging dicarboxylates and nearly parallel, non-interacting uranyls. Longer linkers, n = 5–7, accommodate uranyl orientations with distinct U V –U VI end-on cation-cation interactions (CCIs), whereby Lewis base O yl from U V coordinates to the acid U VI , denoted as U V O yl ···U VI . The dimer structure for n = 8 has a U V –U VI side-on diamond-shape CCI, with U V O yl ···U VI and U VI O yl ···U V interactions. Addition of O 2 to the n = 4 and 5 dimers yields [(UO22+)2(OOC-(CH2)n-2-COO2–)2(O2–)]–, with U V oxidized to U VI and O 2 reduced to O 2 – . Whereas O 2 can associate to and oxidize the exposed U V center for dimers with n = 3 and 4, the more crowded U V site in the CCI structures inhibits O 2 addition. Finally, the results demonstrate rational structural control of uranyl-uranyl bonding and reactivity in small coordination complexes.

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

A scalable compressible volume of fluid solver using a stratified flow model

Here, in this paper, a Volume of Fluid method which uses a Stratified Flow model for flux calculation is proposed to solve a compressible multiphase flow in a way that has high parallel efficiency. The solver is part of an open-source computing tool to study fuel entrainment and combustion in the application of paraffin-based hybrid rocket motors. This paper focuses on the compressible Volume of Fluid solver for the liquid and gaseous phases in this environment. This solver uses perfect gas and stiffened gas models for equation of state, with the ability to easily add other models as desired. Additionally a comparison of a Riemann solver versus an AUSM+up scheme is conducted, showing improvement with the later in the solution of multiphase flows. This solver successfully reproduces shock tube cases with the expected accuracy, as well as simulating two-dimensional shear and gravity-driven flows. Results also show that the code is able to utilize a Stratified Flow model to evaluate shear flow without the need for interface reconstruction or gradient calculations. Finally, it is shown that the solver has near-ideal scaling under strong scaling tests as well as good performance in static scaling, giving improved performance over current options and implying future advancement of high-performance computing efficiency for multiphase flow solvers.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Distance-dependent dielectric constant at the calcite/electrolyte interface: Implication for surface complexation modeling

Hypothesis: The electrical double layer formed at the mineral/electrolyte interface is often modeled using mean-field approaches based on a continuum description of the solvent whose dielectric constant is assumed to decrease monotonically with decreasing distance to the surface. In contrast, molecular simulations show that the solvent polarizability oscillates near the surface similar to the water density profile - as shown previously, for example, by Bonthuis et al. (D.J. Bonthuis, S. Gekle, R.R. Netz, Dielectric Profile of Interfacial Water and its Effect on Double-Layer Capacitance, Phys Rev Lett 107(16) (2011) 166102). Here, we showed that molecular and mesoscale pictures agree by spatially averaging the dielectric constant obtained from molecular dynamics simulations over the distances relevant to the mean-field representation. In addition, the values of capacitances used to describe the electrical double layer in Surface Complexation Models (SCMs) of the mineral/electrolyte interface can be estimated using molecularly informed spatially averaged dielectric constants and positions of hydration layers. Experiments: First, we used molecular dynamics simulations to model the calcite 101¯4/electrolyte interface. Next, by using atomistic trajectories, we calculated the distance-dependent static dielectric constant and water density in the direction normal to the. Finally, we applied spatial compartmentalization consistent with the model of parallel-plate capacitors connected in series to estimate SCM capacitances. Findings: Computationally expensive simulations are required to determine the dielectric constant profile of interfacial water near the mineral surface. On the other hand, water density profiles are readily assessable from much shorter simulation trajectories. Our simulations confirmed that dielectric and water density oscillations at the interface are correlated. Here, we parametrized linear regression models to estimate the dielectric constant directly from the local water density. This is a significant computational shortcut compared to slowly converging calculations relying on total dipole moment fluctuations. The amplitude of the interfacial dielectric constant oscillation can exceed the dielectric constant of the bulk water, suggesting an ice-like frozen state, but only if there are no electrolyte ions. The interfacial accumulation of electrolyte ions causes a decrease in the dielectric constant due to the reduction of water density and re-orientation of water dipoles in ion hydration shells. Finally, we show how to use the computed dielectric properties to estimate SCM's capacitances.

58 GEOSCIENCES↗
DOE OSTI2023

Accelerating the density-functional tight-binding method using graphical processing units

Acceleration of the density-functional tight-binding (DFTB) method on single and multiple graphical processing units (GPUs) was accomplished using the MAGMA linear algebra library. Herein two major computational bottlenecks of DFTB ground-state calculations were addressed in our implementation: the Hamiltonian matrix diagonalization and the density matrix construction. The code was implemented and benchmarked on two different computer systems: (1) the SUMMIT IBM Power9 supercomputer at the Oak Ridge National Laboratory Leadership Computing Facility with 1–6 NVIDIA Volta V100 GPUs per computer node and (2) an in-house Intel Xeon computer with 1–2 NVIDIA Tesla P100 GPUs. The performance and parallel scalability were measured for three molecular models of 1-, 2-, and 3-dimensional chemical systems, represented by carbon nanotubes, covalent organic frameworks, and water clusters.

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

Phase-field model for diffusion-induced grain boundary migration: An application to battery electrodes

Diffusion-induced grain boundary migration is a phenomenon in which a grain boundary moves in response to the driving forces generated by diffusing solute species. For example, diffusing solute species change the atomic volume in the host material, either by filling a vacancy with a misfitting solute atom or by expanding host lattices through interstitial diffusion. These volume changes are inhomogeneous and are stored as elastic energy in the material that drives grain boundaries. In this paper, we introduce our previously developed Cahn-Hilliard–phase-field-crystal model (CH-PFC) as a computational tool to investigate diffusion-induced grain boundary migration in crystalline materials. This multiscale phase-field model couples the composition field of a diffusing species with the crystallographic texture of a host material. We apply the CH-PFC model to battery electrodes and investigate whether interstitial solute diffusion induces grain growth in FePO 4 /LiFePO 4 electrodes. To this end, we compute grain growth in 60 FePO 4 electrodes by conducting two parallel trials: In the first trial, we cycle the electrode and calculate diffusion-induced grain growth. In the second trial, we do not cycle the electrode and calculate curvature-driven grain growth. We find a statistically significant grain growth in the cycled electrodes and negligible grain growth in the noncycled electrodes. Altogether, we show that the CH-PFC model not only predicts electrode microstructures as a function of the Li composition, but also predicts the crystallographic features of an electrode during battery operation.

36 MATERIALS SCIENCE↗
DOE OSTI2016

Tigres Workflow Library: Supporting Scientific Pipelines on HPC Systems

The growth in scientific data volumes has resulted in the need for new tools that enable users to operate on and analyze data on large-scale resources. In the last decade, a number of scientific workflow tools have emerged. These tools often target distributed environments, and often need expert help to compose and execute the workflows. Data-intensive workflows are often ad-hoc, they involve an iterative development process that includes users composing and testing their workflows on desktops, and scaling up to larger systems. In this paper, we present the design and implementation of Tigres, a workflow library that supports the iterative workflow development cycle of data-intensive workflows. Tigres provides an application programming interface to a set of programming templates i.e., sequence, parallel, split, merge, that can be used to compose and execute computational and data pipelines. We discuss the results of our evaluation of scientific and synthetic workflows showing Tigres performs with minimal template overheads (mean of 13 seconds over all experiments). We also discuss various factors (e.g., I/O performance, execution mechanisms) that affect the performance of scientific workflows on HPC systems.

97 MATHEMATICS AND COMPUTING↗