Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel methods”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Extension of Landau-fluid closure to weakly collisional plasma regime

Both collisionless and collisional Landau fluid (LF) closure have been developed and implemented in two-fluid plasma simulation framework BOUT++, taking full advantage of the fast non-Fourier method (Dimits, 2014). The spectral range of good fit can be conveniently extended to larger domain by adding more Lorentzians. The scaling for upper limit of wavenumber resolved in collisionless LF operator and the fitting coefficients for the collisional LF operator, the later is extended to weakly collisional regime (ν$^{*}_{e}$ ~ 0.01), are presented in this paper. The flux limited expression q$^{FL}_{∥e}$ is reduced to free streaming expression q$^{FS}_{∥e}$ in collisionless limit and gives classical Spitzer–Härm result q$^{SH}_{∥e}$ in collisional limit as we expected. The collisional LF closure recovers the classical Spitzer–Härm result q$^{SH}_{∥e}$ in collisional limit and is same as the collisionless LF closure in collisionless limit. The test cases also obviously reflect the nonlocal effects from LF closures and responding to different boundary conditions in open surface region. Our report will make it more applicable and possible to include the Landau damping kinetic effect in the fluid simulation of tokamak plasma.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Layer-Parallel Training of Deep Residual Neural Networks

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, parallel-in-time methods have shown notable improvements in scalability. This paper demonstrates the use of those techniques for efficient and effective training of ResNets. The proposed algorithms replace the classical (sequential) forward and backward propagation through the network layers with a parallel nonlinear multigrid iteration applied to the layer domain. This adds a new dimension of parallelism across layers that is attractive when training very deep networks. From this basic idea, we derive multiple layer-parallel methods. The most efficient version employs a simultaneous optimization approach where updates to the network parameters are based on inexact gradient information in order to speed up the training process. Finally, using numerical examples from supervised classification, we demonstrate that the new approach achieves a training performance similar to that of traditional methods, but enables layer-parallelism and thus provides speedup over layer-serial methods through greater concurrency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

SAChES: Scalable Adaptive Chain-Ensemble Sampling.

We present the development of a parallel Markov Chain Monte Carlo (MCMC) method called SAChES, Scalable Adaptive Chain-Ensemble Sampling. This capability is targed to Bayesian calibration of com- putationally expensive simulation models. SAChES involves a hybrid of two methods: Differential Evo- lution Monte Carlo followed by Adaptive Metropolis. Both methods involve parallel chains. Differential evolution allows one to explore high-dimensional parameter spaces using loosely coupled (i.e., largely asynchronous) chains. Loose coupling allows the use of large chain ensembles, with far more chains than the number of parameters to explore. This reduces per-chain sampling burden, enables high-dimensional inversions and the use of computationally expensive forward models. The large number of chains can also ameliorate the impact of silent-errors, which may affect only a few chains. The chain ensemble can also be sampled to provide an initial condition when an aberrant chain is re-spawned. Adaptive Metropolis takes the best points from the differential evolution and efficiently hones in on the poste- rior density. The multitude of chains in SAChES is leveraged to (1) enable efficient exploration of the parameter space; and (2) ensure robustness to silent errors which may be unavoidable in extreme-scale computational platforms of the future. This report outlines SAChES, describes four papers that are the result of the project, and discusses some additional results.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Asynchronous domain decomposition methods for nonlinear PDEs

One- and two-level parallel asynchronous methods for the numerical solution of nonlinear systems of equations, especially those arising from (nonlinear) partial differential equations, are studied. The proposed methods are based on domain decomposition techniques. Local convergence theorems are presented in several cases, with appropriate hypotheses. Computational results on a shared memory multiprocessor machine for various problems exhibiting nonlinearities are reported, illustrating the potential of these asynchronous methods, especially for heterogeneous clusters.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

RingX: Scalable Parallel Attention for Long-Context Learning on HPC

The attention mechanism has become foundational for remarkable AI breakthroughs since the introduction of the Transformer, driving the demand for increasingly longer context to power frontier models such as large-scale reasoning language models and high-resolution image/video generators. However, its quadratic computational and memory complexities present substantial challenges. Current state-of-the-art parallel attention methods, such as ring attention, are widely adopted for long-context training but utilize a point-to-point communication strategy that fails to fully exploit the capabilities of modern HPC network architectures. In this work, we propose ringX, a scalable family of parallel attention methods optimized explicitly for HPC systems. By enhancing workload partitioning, refining communication patterns, and improving load balancing, ringX achieves up to 3.4 × speedup compared to conventional ring attention on the Frontier supercomputer. Optimized for both bi-directional and causal attention mechanisms, ringX demonstrates its effectiveness through training benchmarks of a Vision Transformer (ViT) on a climate dataset and a Generative Pre-Trained Transformer (GPT) model, Llama3 8B. Our method attains an end-to-end training speedup of approximately 1.5 × in both scenarios. To our knowledge, the achieved 38% model FLOPs utilization (MFU) for training Llama3 8B with a 1M-token sequence length on 4,096 GPUs represents one of the highest training efficiencies reported for long-context learning on HPC systems. Our code implementation is available at https://github.com/jqyin/ringX-attention.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗
DOE OSTI2025

A time-parallel multiple-shooting method for large-scale quantum optimal control

Quantum optimal control plays a crucial role in quantum computing by providing the interface between compiler and hardware. Solving the optimal control problem is particularly challenging for multi-qubit gates, due to the exponential growth in computational complexity with the system's dimensionality and the deterioration of optimization convergence. To ameliorate the computational complexity of time-integration, this paper introduces a multiple-shooting approach in which the time domain is divided into multiple windows and the intermediate states at window boundaries are treated as additional optimization variables. Further, this enables parallel computation of state evolution across time-windows, significantly accelerating objective function and gradient evaluations. Since the initial state matrix in each window is only guaranteed to be unitary upon convergence of the optimization algorithm, the conventional gate trace infidelity is replaced by a generalized infidelity that is convex for non-unitary state matrices. Continuity of the state across window boundaries is enforced by equality constraints. A quadratic penalty optimization method is used to solve the constrained optimal control problem, and an efficient adjoint technique is employed to calculate the gradients in each iteration. We demonstrate the effectiveness of the proposed method through numerical experiments on quantum Fourier transform gates in systems with 2, 3, and 4 qubits, noting a speedup of 80x for evaluating the gradient in the 4-qubit case, highlighting the method's potential for optimizing control pulses in multi-qubit quantum systems.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2017

SQDFT: Spectral Quadrature method for large-scale parallel O ( N ) Kohn–Sham calculations at high temperature

We present SQDFT: a large-scale parallel implementation of the Spectral Quadrature (SQ) method for $\mathscr{O}(N)$ Kohn–Sham Density Functional Theory (DFT) calculations at high temperature. Specifically, we develop an efficient and scalable finite-difference implementation of the infinite-cell Clenshaw–Curtis SQ approach, in which results for the infinite crystal are obtained by expressing quantities of interest as bilinear forms or sums of bilinear forms, that are then approximated by spatially localized Clenshaw–Curtis quadrature rules. We demonstrate the accuracy of SQDFT by showing systematic convergence of energies and atomic forces with respect to SQ parameters to reference diagonalization results, and convergence with discretization to established planewave results, for both metallic and insulating systems. Here, we further demonstrate that SQDFT achieves excellent strong and weak parallel scaling on computer systems consisting of tens of thousands of processors, with near perfect $\mathscr{O}(N)$ scaling with system size and wall times as low as a few seconds per self-consistent field iteration. Finally, we verify the accuracy of SQDFT in large-scale quantum molecular dynamics simulations of aluminum at high temperature.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2020

Accelerating Parallel Applications in Cloud Platforms via Adaptive Time-Slice Control

Cloud platforms can provide flexible and cost-effective environments for parallel applications. However, the resource over-commitment issues, i.e., cloud providers often provide much more executable virtual CPUs than available physical CPUs, still impede the synchronization operations of parallel applications, causing severe performance degradation. Existing methods optimize parallel applications by promoting the priorities of involved VMs. They cannot fully explore the performance of parallel applications, because they ignore the time-slice requirements of different phases of parallel applications. Furthermore, non-parallel applications experience unsatisfied performance because of low scheduling priorities. Given empirical analysis on time-slices of virtual machines (VMs), we find that shortening time-slices can mitigate synchronization overhead which incurs during communication phases, while over-short time-slices cause frequent cache misses in computation phases. Accordingly, we propose an Adaptive Time-slice Control (ATC) mechanism. ATC first detects the phases of parallel applications based on lock latency or cache misses. Then, ATC shortens time-slices during communication phases and prolongs time-slices during computation phases for parallel applications, and sets a uniform time-slice for non-parallel applications. Finally, we evaluate ATC using seven well-known benchmarks with 25+ applications. Experiments show that ATC obtains 1.5-75x performance gain for running parallel applications than state-of-the-art solutions, with nearly unaffected impact on non-parallel applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

Penalty-free method for multi-constrained optimization problems based on parallel simulated annealing

A method is presented for addressing constraints within the context of large-scale combinatorial optimization problems. The method, based on constraint annealing, eliminates the use of traditional constraint penalty factors by treating each constraint as separate and concurrently solved minimization problems within a global optimization search framework. Results are demonstrated for a core loading pattern optimization problem. (authors)

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Parallelizing autotuning for HPC applications: Unveiling the potential of the speculation strategy in Bayesian optimization

In the exascale computing era, tuning High-Performance Computing (HPC) applications has become a significant computational challenge. Although Bayesian optimization (BO) has emerged as a promising tool for HPC performance tuning, the BO workflow is inherently sequential (i.e., one function evaluation at a time) and cannot leverage the huge amount of parallel resources present in modern supercomputers, resulting in a considerable underutilization of their computational capabilities. This paper explores the trade-off between search quality and parallelism in BO, investigating a diverse set of methods. Building upon both previous approaches from the literature and novel methodologies introduced in this work, our study provides a deep analysis to accelerate BO performance tuning. By examining a set of synthetic functions and practical HPC applications, our exploration analyzes the interaction among various BO methods for parallelization, the quantity of parallel resources, the runtime distribution of target HPC applications, and the costs associated with different search orchestration mechanisms that have been overlooked in previous studies. Compared to sequential BO, our novel methodology achieves comparable quality while demonstrating robust scalability in search time as the amount of parallel resources increases; it also outperforms a state-of-the-art tuner, which supports parallelization, achieving up to 3.67x faster search time. We provide high-value insights for practitioners seeking to leverage the power of parallel computing for efficient HPC application tuning. Additionally, to further assist researchers in accelerating the performance tuning of their HPC applications, we provide an extension of an existing open-source tuning framework that incorporates our methods.

Bayesian optimization↗
DOE OSTI2018

Scalable Distributed Memory Community Detection Using Vite

Graph clustering, popularly known as community detection, is a fundamental graph operation used in several applications of relevance for network analysis and cybersecurity. Community detection is an operation of partitioning a network into an arbitrary number of “communities” such that each com munity represents a tightly-knit group of nodes with relatively sparser connections to the rest of the nodes in the network. The need to compute clustering on large-scale networks necessitates the development of efficient parallel algorithms capable of exploiting modern parallel architectures. However, due to their irregular and inherently sequential nature, many of the current algorithms for community detection are challenging to parallelize. In response to the 2018 Graph Challenge, we present Vite which is a distributed-memory parallel community detection method. Vite is a parallelization of the algorithmic template provided by a widely-used serial method (Louvain). Alongside, it uses several heuristics aimed at significantly improving parallelism and performance, while preserving output quality. Using the inputs from the 2018 Graph Challenge (static and streaming), we demonstrate superior performance and high quality solutions based on four parallelization heuristics.

community detection↗
DOE OSTI2021

A Massively Parallel Implementation of the CCSD(T) Method Using the Resolution-of-the-Identity Approximation and a Hybrid Distributed/Shared Memory Parallelization Model

In this work, a parallel algorithm is described for the coupled-cluster singles and doubles method augmented with a perturbative correction for triple excitations [CCSD(T)] using the resolution-of-the-identity (RI) approximation for two-electron repulsion integrals (ERIs). The algorithm bypasses the storage of four-center ERIs by adopting an integral-direct strategy. The CCSD amplitude equations are given in a compact quasi-linear form by factorizing them in terms of amplitude-dressed three-center intermediates. A hybrid MPI/OpenMP parallelization scheme is employed, which uses the OpenMP-based shared memory model for intranode parallelization and the MPI-based distributed memory model for internode parallelization. Parallel efficiency has been optimized for all terms in the CCSD amplitude equations. Two different algorithms have been implemented for the rate-limiting terms in the CCSD amplitude equations that entail and -scaling computational costs, where N O and N V denote the number of correlated occupied and virtual orbitals, respectively. One of the algorithms assembles the four-center ERIs requiring N V 4 and N O 2 N V 2 -scaling memory costs in a distributed manner on a number of MPI ranks, while the other algorithm completely bypasses the assembling of quartic memory-scaling ERIs and thus largely reduces the memory demand. It is demonstrated that the former memory-expensive algorithm is faster on a few hundred cores, while the latter memory-economic algorithm shows a better strong scaling in the limit of a few thousand cores. The program is shown to exhibit a near-linear scaling, in particular for the compute-intensive triples correction step, on up to 8000 cores. The performance of the program is demonstrated via calculations involving molecules with 24–51 atoms and up to 1624 atomic basis functions. As the first application, the complete basis set (CBS) limit for the interaction energy of the π-stacked uracil dimer from the S66 data set has been investigated. This work reports the first calculation of the interaction energy at the CCSD(T)/aug-cc-pVQZ level without local orbital approximation. The CBS limit for the CCSD correlation contribution to the interaction energy was found to be -8.01 kcal/mol, which agrees very well with the value -7.99 kcal/mol reported by Schmitz, Hättig, and Tew [ Phys. Chem. Chem. Phys. 2014 , 16 , 22167-22178]. The CBS limit for the total interaction energy was estimated to be -9.64 kcal/mol.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2016

3D magnetospheric parallel hybrid multi-grid method applied to planet–plasma interactions

We present a new method to exploit multiple refinement levels within a 3D parallel hybrid model, developed to study planet–plasma interactions. This model is based on the hybrid formalism: ions are kinetically treated whereas electrons are considered as a inertia-less fluid. Generally, ions are represented by numerical particles whose size equals the volume of the cells. Particles that leave a coarse grid subsequently entering a refined region are split into particles whose volume corresponds to the volume of the refined cells. The number of refined particles created from a coarse particle depends on the grid refinement rate. In order to conserve velocity distribution functions and to avoid calculations of average velocities, particles are not coalesced. Moreover, to ensure the constancy of particles' shape function sizes, the hybrid method is adapted to allow refined particles to move within a coarse region. Another innovation of this approach is the method developed to compute grid moments at interfaces between two refinement levels. Indeed, the hybrid method is adapted to accurately account for the special grid structure at the interfaces, avoiding any overlapping grid considerations. Some fundamental test runs were performed to validate our approach (e.g. quiet plasma flow, Alfven wave propagation). Lastly, we also show a planetary application of the model, simulating the interaction between Jupiter's moon Ganymede and the Jovian plasma.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2018

Dynamic Load Balancing Based on Constrained K-D Tree Decomposition for Parallel Particle Tracing

Particle tracing is a fundamental technique in flow field data visualization. In this work, we present a novel dynamic load balancing method for parallel particle tracing. Specifically, we employ a constrained k-d tree decomposition approach to dynamically redistribute tasks among processes. Each process is initially assigned a regularly partitioned block along with duplicated ghost layer under the memory limit. During particle tracing, the k-d tree decomposition is dynamically performed by constraining the cutting planes in the overlap range of duplicated data. This ensures that each process is reassigned particles as even as possible, and on the other hand the new assigned particles for a process always locate in its block. Result shows good load balance and high efficiency of our method.

Zhang, Jiang↗
DOE OSTI2025

Optimizing temperature distributions for training neural quantum states using parallel tempering

Parametrized artificial neural networks (ANNs) can be very expressive ansatzes for variational algorithms, reaching state-of-the-art energies on many quantum many-body Hamiltonians. Nevertheless, the training of the ANN can be slow and stymied by the presence of local minima in the parameter landscape. One approach to mitigate this issue is to use parallel tempering methods, and in this work, we focus on the role played by the temperature distribution of the parallel tempering replicas. Using an adaptive method that adjusts the temperatures in order to equate the exchange probability between neighboring replicas, we show that this temperature optimization can significantly increase the success rate of the variational algorithm with negligible computational cost by eliminating bottlenecks in the replicas' random walk. Furthermore, we demonstrate this using two different neural networks, a restricted Boltzmann machine and a feedforward network, which we use to study a toy problem based on a permutation invariant Hamiltonian with a pernicious local minimum and the 𝐽 1 −𝐽 2 model on a rectangular lattice.

Neural network simulations↗
DOE OSTI2023

A parallel, distributed memory implementation of the adaptive sampling configuration interaction method

The many-body simulation of quantum systems is an active field of research that involves several different methods targeting various computing platforms. Many methods commonly employed, particularly coupled cluster methods, have been adapted to leverage the latest advances in modern high-performance computing. Selected configuration interaction (sCI) methods have seen extensive usage and development in recent years. However, the development of sCI methods targeting massively parallel resources has been explored only in a few research works. Here, we present a parallel, distributed memory implementation of the adaptive sampling configuration interaction approach (ASCI) for sCI. In particular, we will address the key concerns pertaining to the parallelization of the determinant search and selection, Hamiltonian formation, and the variational eigenvalue calculation for the ASCI method. Load balancing in the search step is achieved through the application of memory-efficient determinant constraints originally developed for the ASCI-PT2 method. The presented benchmarks demonstrate near optimal speedup for ASCI calculations of Cr 2 (24e, 30o) with 10 6 , 10 7 , and 3 × 10 8 variational determinants on up to 16 384 CPUs. Importantly, to the best of the authors’ knowledge, this is the largest variational ASCI calculation to date.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗