Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel optimization”

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 649 records · Page 36

Multimodal Bayesian registration of noisy functions using Hamiltonian Monte Carlo

Functional data registration is a necessary processing step for many applications. The observed data can be inherently noisy, often due to measurement error or natural process uncertainty; which most functional alignment methods cannot handle. A pair of functions can also have multiple optimal alignment solutions, which is not addressed in current literature. In this paper, a flexible Bayesian approach to functional alignment is presented, which appropriately accounts for noise in the data without any pre-smoothing required. Additionally, by running parallel MCMC chains, the method can account for multiple optimal alignments via the multi-modal posterior distribution of the warping functions. To most efficiently sample the warping functions, the approach relies on a modification of the standard Hamiltonian Monte Carlo to be well-defined on the infinite-dimensional Hilbert space. In this work, this flexible Bayesian alignment method is applied to both simulated data and real data sets to show its efficiency in handling noisy functions and successfully accounting for multiple optimal alignments in the posterior; characterizing the uncertainty surrounding the warping functions.

97 MATHEMATICS AND COMPUTING↗

Profiling the BLAST bioinformatics application for load balancing on high-performance computing clusters

Abstract Background The Basic Local Alignment Search Tool (BLAST) is a suite of commonly used algorithms for identifying matches between biological sequences. The user supplies a database file and query file of sequences for BLAST to find identical sequences between the two. The typical millions of database and query sequences make BLAST computationally challenging but also well suited for parallelization on high-performance computing clusters. The efficacy of parallelization depends on the data partitioning, where the optimal data partitioning relies on an accurate performance model. In previous studies, a BLAST job was sped up by 27 times by partitioning the database and query among thousands of processor nodes. However, the optimality of the partitioning method was not studied. Unlike BLAST performance models proposed in the literature that usually have problem size and hardware configuration as the only variables, the execution time of a BLAST job is a function of database size, query size, and hardware capability. In this work, the nucleotide BLAST application BLASTN was profiled using three methods: shell-level profiling with the Unix “time” command, code-level profiling with the built-in “profiler” module, and system-level profiling with the Unix “gprof” program. The runtimes were measured for six node types, using six different database files and 15 query files, on a heterogeneous HPC cluster with 500+ nodes. The empirical measurement data were fitted with quadratic functions to develop performance models that were used to guide the data parallelization for BLASTN jobs. Results Profiling results showed that BLASTN contains more than 34,500 different functions, but a single function, RunMTBySplitDB, takes 99.12% of the total runtime. Among its 53 child functions, five core functions were identified to make up 92.12% of the overall BLASTN runtime. Based on the performance models, static load balancing algorithms can be applied to the BLASTN input data to minimize the runtime of the longest job on an HPC cluster. Four test cases being run on homogeneous and heterogeneous clusters were tested. Experiment results showed that the runtime can be reduced by 81% on a homogeneous cluster and by 20% on a heterogeneous cluster by re-distributing the workload. Discussion Optimal data partitioning can improve BLASTN’s overall runtime 5.4-fold in comparison with dividing the database and query into the same number of fragments. The proposed methodology can be used in the other applications in the BLAST+ suite or any other application as long as source code is available.

59 BASIC BIOLOGICAL SCIENCES↗

Final Technical Report for "Applied Mathematics Research: Simulation Based Optimization and Application to Electromagnetic Inverse Problems"

The focus of research was: Developing adaptive mesh for the solution of Maxwell's equations; Developing a parallel framework for time dependent inverse Maxwell's equations; Developing multilevel methods for optimization problems with inequality constraints; A new inversion code for inverse Maxwell's equations in the 0th frequency (DC resistivity); A new inversion code for inverse Maxwell's equations in low frequency regime. Although the research concentrated on electromagnetic forward and in- verse problems the results of the research was applied to the problem of image registration.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Quantum Monte Carlo Endstation for Petascale Computing

NCSU research group has been focused on accomplising the key goals of this initiative: establishing new generation of quantum Monte Carlo (QMC) computational tools as a part of Endstation petaflop initiative for use at the DOE ORNL computational facilities and for use by computational electronic structure community at large; carrying out high accuracy quantum Monte Carlo demonstration projects in application of these tools to the forefront electronic structure problems in molecular and solid systems; expanding the impact of QMC methods and approaches; explaining and enhancing the impact of these advanced computational approaches. In particular, we have developed quantum Monte Carlo code (QWalk, www.qwalk.org) which was significantly expanded and optimized using funds from this support and at present became an actively used tool in the petascale regime by ORNL researchers and beyond. These developments have been built upon efforts undertaken by the PI's group and collaborators over the period of the last decade. The code was optimized and tested extensively on a number of parallel architectures including petaflop ORNL Jaguar machine. We have developed and redesigned a number of code modules such as evaluation of wave functions and orbitals, calculations of pfaffians and introduction of backflow coordinates together with overall organization of the code and random walker distribution over multicore architectures. We have addressed several bottlenecks such as load balancing and verified efficiency and accuracy of the calculations with the other groups of the Endstation team. The QWalk package contains about 50,000 lines of high quality object-oriented C++ and includes also interfaces to data files from other conventional electronic structure codes such as Gamess, Gaussian, Crystal and others. This grant supported PI for one month during summers, a full-time postdoc and partially three graduate students over the period of the grant duration, it has resulted in 13 published papers, 15 invited talks and lectures nationally and internationally. My former graduate student and postdoc Dr. Michal Bajdich, who was supported byt this grant, is currently a postdoc with ORNL in the group of Dr. F. Reboredo and Dr. P. Kent and is using the developed tools in a number of DOE projects. The QWalk package has become a truly important research tool used by the electronic structure community and has attracted several new developers in other research groups. Our tools use several types of correlated wavefunction approaches, variational, diffusion and reptation methods, large-scale optimization methods for wavefunctions and enables to calculate energy differences such as cohesion, electronic gaps, but also densities and other properties, using multiple runs one can obtain equations of state for given structures and beyond. Our codes use efficient numerical and Monte Carlo strategies (high accuracy numerical orbitals, multi-reference wave functions, highly accurate correlation factors, pairing orbitals, force biased and correlated sampling Monte Carlo), are robustly parallelized and enable to run on tens of thousands cores very efficiently. Our demonstration applications were focused on the challenging research problems in several fields of materials science such as transition metal solids. We note that our study of FeO solid was the first QMC calculation of transition metal oxides at high pressures.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Accelerating Lattice QCD Multigrid on GPUs Using Fine-Grained Parallelization

The past decade has witnessed a dramatic acceleration of lattice quantum chromodynamics calculations in nuclear and particle physics. This has been due to both significant progress in accelerating the iterative linear solvers using multi-grid algorithms, and due to the throughput improvements brought by GPUs. Deploying hierarchical algorithms optimally on GPUs is non-trivial owing to the lack of parallelism on the coarse grids, and as such, these advances have not proved multiplicative. Using the QUDA library, we demonstrate that by exposing all sources of parallelism that the underlying stencil problem possesses, and through appropriate mapping of this parallelism to the GPU architecture, we can achieve high efficiency even for the coarsest of grids. Results are presented for the Wilson-Clover discretization, where we demonstrate up to 10x speedup over present state-of-the-art GPU-accelerated methods on Titan. Finally, we look to the future, and consider the software implications of our findings.

Clark, M. A.↗

Optimizing Excited-State Electronic-Structure Codes for Intel Knights Landing: A Case Study on the BerkeleyGW Software

We profile and optimize calculations performed with the BerkeleyGW code on the Xeon-Phi architecture. BerkeleyGW depends both on hand-tuned critical kernels as well as on BLAS and FFT libraries. We describe the optimization process and performance improvements achieved. We discuss a layered parallelization strategy to take advantage of vector, thread and node-level parallelism. We discuss locality changes (including the consequence of the lack of L3 cache) and effective use of the on-package high-bandwidth memory. We show preliminary results on Knights-Landing including a roofline study of code performance before and after a number of optimizations. We find that the GW method is particularly well-suited for many-core architectures due to the ability to exploit a large amount of parallelism over plane-wave components, band-pairs, and frequencies.

97 MATHEMATICS AND COMPUTING↗

Exploring High-Dimensional Data Space: Identifying Optimal Process Conditions in Photovoltaics: Preprint

We demonstrate how advanced exploratory data analysis coupled to data-mining techniques can be used to scrutinize the high-dimensional data space of photovoltaics in the context of thin films of Al-doped ZnO (AZO), which are essential materials as a transparent conducting oxide (TCO) layer in CuInxGa1-xSe2 (CIGS) solar cells. AZO data space, wherein each sample is synthesized from a differentprocess history and assessed with various characterizations, is transformed, reorganized, and visualized in order to extract optimal process conditions. The data-analysis methods used include parallel coordinates, diffusion maps, and hierarchical agglomerative clustering algorithms combined with diffusion map embedding.

14 SOLAR ENERGY↗

Compiler-Directed Transformation for Higher-Order Stencils

As the cost of data movement increasingly dominates performance, developers of finite-volume and finite-difference solutions for partial differential equations (PDEs) are exploring novel higher-order stencils that increase numerical accuracy and computational intensity. This paper describes a new compiler reordering transformation applied to stencil operators that performs partial sums in buffers, and reuses the partial sums in computing multiple results. This optimization has multiple effect son improving stencil performance that are particularly important to higher-order stencils: exploits data reuse, reduces floating-point operations, and exposes efficient SIMD parallelism to backend compilers. We study the benefit of this optimization in the context of Geometric Multigrid (GMG), a widely used method to solvePDEs, using four different Jacobi smoothers built from 7-, 13-, 27-and 125-point stencils. We quantify performance, speedup, andnumerical accuracy, and use the Roofline model to qualify our results. Ultimately, we obtain over 4× speedup on the smoothers themselves and up to a 3× speedup on the multigrid solver. Finally, we demonstrate that high-order multigrid solvers have the potential of reducing total data movement and energy by several orders of magnitude.

97 MATHEMATICS AND COMPUTING↗

GPU-acceleration of the ELPA2 distributed eigensolver for dense symmetric and hermitian eigenproblems

The solution of eigenproblems is often a key computational bottleneck that limits the tractable system size of numerical algorithms, among them electronic structure theory in chemistry and in condensed matter physics. Large eigenproblems can easily exceed the capacity of a single compute node, thus must be solved on distributed-memory parallel computers. We here present GPU-oriented optimizations of the ELPA two-stage tridiagonalization eigensolver (ELPA2). On top of cuBLAS-based GPU offloading, we add a CUDA kernel to speed up the back-transformation of eigenvectors, which can be the computationally most expensive part of the two-stage tridiagonalization algorithm. Furthermore, we benchmark the performance of this GPU-accelerated eigensolver on two hybrid CPU–GPU architectures, namely a compute cluster based on Intel Xeon Gold CPUs and NVIDIA Volta GPUs, and the Summit supercomputer based on IBM POWER9 CPUs and NVIDIA Volta GPUs. Consistent with previous benchmarks on CPU-only architectures, the GPU-accelerated two-stage solver exhibits a parallel performance superior to the one-stage counterpart. Finally, we demonstrate the performance of the GPU-accelerated eigensolver developed in this work for routine semi-local KS-DFT calculations comprising thousands of atoms.

97 MATHEMATICS AND COMPUTING↗

Solving larger maximum clique problems using parallel quantum annealing

Quantum annealing has the potential to find low energy solutions of NP-hard problems that can be expressed as quadratic unconstrained binary optimization problems. However, the hardware of the quantum annealer manufactured by D-Wave Systems, which we consider in this work, is sparsely connected and moderately sized (on the order of thousands of qubits), thus necessitating a minor-embedding of a logical problem onto the physical qubit hardware. The combination of relatively small hardware sizes and the necessity of a minor-embedding can mean that solving large optimization problems is not possible on current quantum annealers. In this research, we show that a hybrid approach combining parallel quantum annealing with graph decomposition allows one to solve larger optimization problem accurately. We apply the approach to the Maximum Clique problem on graphs with up to 120 nodes and 6395 edges.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Exploiting Power Flow Manifold to Solve AC Optimal Power Flow

AC optimal power flow has proven difficult to solve with interior point methods on GPUs. This is largely due to challenging linear algebra problems that current state of the art massively parallel linear solvers struggle with. However, the advent of Riemannian optimization techniques and the fact that the power flow equations form a smooth manifold present an alternative approach. In this talk, we present the basics of Riemannian optimization techniques in which optimization is done directly on a manifold. Then we present computational results showing that Riemannian techniques are capable of producing solutions of comparable quality as interior point methods.

AC optimal power flow↗

Adaptive, Active Learning, and Multifidelity Monte Carlo Methods in the MOOSE Stochastic Tools Module

MOOSE is an open-source computational platform for constructing multi-physics models and executing them in a massively parallel fashion. It has a stochastic tools module (STM) for forward/inverse uncertainty quantification (UQ) and surrogate modeling. This presentation details some recent developments to the STM with respect to the implementation of adaptive, active learning, and multifidelity Monte Carlo methods for forward UQ of computational models. Specifically, the adaptive Monte Carlo methods include Markov Chain Monte Carlo (MCMC)-driven algorithms like adaptive importance sampling and parallelized subset simulation for statistical QoI estimation, rare events analysis, and stochastic gradient-free optimization. The active learning methods include Gaussian Process (GP) surrogates and their training via Adam optimization, design of acquisition functions, and integration with samplers like Monte Carlo, adaptive importance, and parallelized subset simulation. These active learning methods are also designed to work in a batch mode, wherein, the required calls to the full computational model are executed in parallel whenever a user-specified batch size is met. The multifidelity methods in STM are broadly divided into two categories: hierarchical, where a defined hierarchy exists among the low-fidelity models, and peer, where all the low-fidelity models are treated equally. A GP surrogate is used to learn the differences between the low- and high-fidelity models in both multifidelity categories, and acquisition functions from the active learning classes are used to decide whether to rely on a low-fidelity model or call the expensive high-fidelity model. Alongside the software description and usage, applications are also presented to nuclear engineering computational models including a TRISO nuclear fuel particle, a reactor pressure vessel, and a heat-pipe microreactor.

97 MATHEMATICS AND COMPUTING↗

Optimization of the moderators in the STS preliminary design

This report details the results for an optimization of the dimensions of the moderators in the preliminary design of the Spallation Neutron Source Second Target Station (STS). This study uses the optimization algorithms of Dakota and an unstructured mesh model for the moderators in MCNP. More details on the unstructured mesh model and the automated mesh generation can be found in [3]. Parallel to this effort, the same moderator geometries have been optimized using a constructive solid geometry (CSG) MCNP model. More details on this model and its results can be found in [4]. Three optimal designs are selected for each moderator: one that is optimized for maximum peak brightness, one for maximum time-integrated brightness, and one for a combination of peak and time-integrated brightness. The backbone of the optimization work flow is provided by Dakota. For each set of design parameters requested by Dakota, a new solid geometry is automatically built in Creo and SpaceClaim, and subsequently exported to Attila4MC to generate an unstructured mesh geometry for MCNP. After the MCNP calculation is finished, the objective function (e.g., brightness metric) is returned to Dakota. After the new design has been evaluated, a result-file is written, and Dakota proposes the next set of design parameters to be evaluated. The loop continues until a specified convergence criterion has been met. The design parameters of the cylindrical (upper) moderator include the hydrogen radius, the premoderator thickness (top, bottom, radial), the beryllium radius and the horizontal position of the moderator. The crucial design choice is the hydrogen radius. A radius of 62 mm is shown to provide the maximum time-integrated brightness. The maximum peak brightness occurs with a radius of 40 mm. A combined (middle) design, which balances peak and time-integrated brightnesses, is obtained with a hydrogen radius of 50 mm. The premoderator thicknesses and the beryllium radius are slightly larger in the design optimized for time-integrated brightness than in the design optimized for peak brightness. The sensitivity to these two parameters is relatively small close to the optimal configurations. The hydrogen vessel and vacuum vessel wall thicknesses are dependent on the radius of the liquid hydrogen due to structural integrity requirements. The increased wall thicknesses for larger vessels significantly penalize the time-integrated brightness, with the maximum obtainable value reduced by more than 10% relative to earlier studies which used fixed vessel wall thicknesses. The impact of the variable wall thicknesses is much less for the peak brightness and combined brightness designs. The design parameters of the tube (lower) moderator selected for the optimization are the tube length, the annular premoderator thickness, the beryllium radius and the horizontal position of the moderator. The tube length is the crucial parameter and is chosen large (210 mm) and small (125 mm) in the designs optimized for time-integrated and peak brightness respectively. A combined optimal design has a tube length of 170 mm. The premoderator thickness and the beryllium radius are chosen larger in the design optimized for time-integrated brightness.

42 ENGINEERING↗

TRACKING CODE DEVELOPMENT FOR BEAM DYNAMICS OPTIMIZATION

Dynamic aperture (DA) optimization with direct particle tracking is a straight forward approach when the computing power is permitted. It can have various realistic errors included and is more close than theoretical estimations. In this approach, a fast and parallel tracking code could be very helpful. In this presentation, we describe an implementation of storage ring particle tracking code TESLA for beam dynamics optimization. It supports MPI based parallel computing and is robust as DA calculation engine. This code has been used in the NSLS-II dynamics optimizations and obtained promising performance.

43 PARTICLE ACCELERATORS↗

SMT-Aware Instantaneous Footprint Optimization

Modern architectures employ simultaneous multithreading (SMT) to increase thread-level parallelism. SMT threads share many functional units and the whole memory hierarchy of a physical core. Without a careful code design, SMT threads can easily contend with each other for these shared resources, causing severe performance degradation. Minimizing SMT thread contention for HPC applications running on dedicated platforms is very challenging, because they usually spawn threads within Single Program Multiple Data (SPMD) models. To address this important issue, we introduce a simple scheme for SMT-aware code optimization, which aims to reduce the memory contention across SMT threads.

Instantaneous Footprint↗

HydraGNN v5.0

HydraGNN v5.0 expands the code base into a more portable, scalable, and flexible framework for scientific graph learning, with particular strength in atomistic machine-learning interatomic potentials and large-scale distributed training. The release adds Fully Sharded Data Parallel (FSDP) support alongside existing DDP and DeepSpeed paths, including FSDP-aware checkpointing and optimizer integration, and introduces a configurable multi-precision training workflow supporting FP32, BF16, and FP64 across GPUs and Intel XPUs. For atomistic modeling, HydraGNN v5.0 strengthens its MLIP capabilities through dynamic graph construction at every forward pass, energy-conserving force prediction via automatic differentiation, and per-atom energy loss formulations, while extending EGNN models to properly handle periodic boundary conditions. The release also broadens model expressiveness through graph-level attribute conditioning, adds new multi-task and model-parallel extensions such as MACE support and encoder/decoder branch optimization, and expands application coverage with integrated examples for datasets including OC25, Nabla2-DFT, QCML, Open Polymers 2026, and OPF. In parallel, HydraGNN v5.0 improves production readiness through performance optimizations for large-scale runs, stratified sampling and linear-regression preprocessing utilities, and tested installation scripts for DOE supercomputers including Frontier, Aurora, Perlmutter, and Andes. Overall, the release advances HydraGNN as a robust software platform for scalable graph neural networks across materials science, chemistry, and scientific machine learning workflows

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗

Avatar Tools

Supervised machine learning is the process of using past experience to predict the future. "Ensembles" are a machine-learning meta-method that can be applied to most machine learning algorithms. Ensembles generally greatly improve accuracy, reduce or remove most of the design issues presented by machine learning, and are admirably suited to parallel and distributed computation. The Avatar Tools codes are an implementation of ensembles specifically for decision trees. Some features that distinguish Avatar Tools from other "ensembles for decision trees" codes are: (1) Does the bookkeeping necessary for out of bag (OOB) validation. (2) Can use OOB validation to automatically determine optimal ensemble size. (3) Provides an MPI-based parallel implementation, for distributed operation. (4) Provides convenient tools for cross-validation, to assess the accuracy provided by a training set. SAND2020-3858 M Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Siefert, Christopher↗