Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallelization efficiency”

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 865 records · Page 48

MIXING THE SOLAR WIND PROTON AND ELECTRON SCALES: EFFECTS OF ELECTRON TEMPERATURE ANISOTROPY ON THE OBLIQUE PROTON FIREHOSE INSTABILITY

The double adiabatic expansion of the nearly collisionless solar wind plasma creates conditions for the firehose instability to develop and efficiently prevent the further increase of the plasma temperature in the direction parallel to the interplanetary magnetic field. The conditions imposed by the firehose instability have been extensively studied using idealized approaches that ignore the mutual effects of electrons and protons. Recently, more realistic approaches have been proposed that take into account the interplay between electrons and protons, unveiling new regimes of the parallel oscillatory modes. However, for oblique wave propagation the instability develops distinct branches that grow much faster and may therefore be more efficient than the parallel firehose instability in constraining the temperature anisotropy of the plasma particles. This paper reports for the first time on the effects of electron plasma properties on the oblique proton firehose (PFH) instability and provides a comprehensive vision of the entire unstable wave-vector spectrum, unifying the proton and the smaller electron scales. The plasma β and temperature anisotropy regimes considered here are specific for the solar wind and magnetospheric conditions, and enable the electrons and protons to interact via the excited electromagnetic fluctuations. For the selected parameters, simultaneous electron and PFH instabilities can be observed with a dispersion spectrum of the electron firehose (EFH) extending toward the proton scales. Growth rates of the PFH instability are markedly boosted by the anisotropic electrons, especially in the oblique direction where the EFH growth rates are orders of magnitude higher.

79 ASTRONOMY AND ASTROPHYSICS↗

Mixing the Solar Wind Proton and Electron Scales: Effects of Electron Temperature Anisotropy on the Oblique Proton Firehose Instability

The double adiabatic expansion of the nearly collisionless solar wind plasma creates conditions for the firehose instability to develop and efficiently prevent the further increase of the plasma temperature in the direction parallel to the interplanetary magnetic field. The conditions imposed by the firehose instability have been extensively studied using idealized approaches that ignore the mutual effects of electrons and protons. Recently, more realistic approaches have been proposed that take into account the interplay between electrons and protons, unveiling new regimes of the parallel oscillatory modes. However, for oblique wave propagation the instability develops distinct branches that grow much faster and may therefore be more efficient than the parallel firehose instability in constraining the temperature anisotropy of the plasma particles. This paper reports for the first time on the effects of electron plasma properties on the oblique proton firehose (PFH) instability and provides a comprehensive vision of the entire unstable wave-vector spectrum, unifying the proton and the smaller electron scales. The plasma β and temperature anisotropy regimes considered here are specific for the solar wind and magnetospheric conditions, and enable the electrons and protons to interact via the excited electromagnetic fluctuations. For the selected parameters, simultaneous electron and PFH instabilities can be observed with a dispersion spectrum of the electron firehose (EFH) extending toward the proton scales. Growth rates of the PFH instability are markedly boosted by the anisotropic electrons, especially in the oblique direction where the EFH growth rates are orders of magnitude higher.

plasmas↗

VAN-DAMME: GPU-accelerated and symmetry-assisted quantum optimal control of multi-qubit systems

We present an open-source software package, VAN-DAMME (Versatile Approaches to Numerically Design, Accelerate, and Manipulate Magnetic Excitations), for massively-parallelized quantum optimal control (QOC) calculations of multi-qubit systems. To enable large QOC calculations, the VAN-DAMME software package utilizes symmetry-based techniques with custom GPU-enhanced algorithms. This combined approach allows for the simultaneous computation of hundreds of matrix exponential propagators that efficiently leverage the intra-GPU parallelism found in high-performance GPUs. In addition, to maximize the computational efficiency of the VAN-DAMME code, we carried out several extensive tests on data layout, computational complexity, memory requirements, and performance. These extensive analyses allowed us to develop computationally efficient approaches for evaluating complex-valued matrix exponential propagators based on Padé approximants. To assess the computational performance of our GPU-accelerated VAN-DAMME code, we carried out QOC calculations of systems containing 10 - 15 qubits, which showed that our GPU implementation is 18.4× faster than the corresponding CPU implementation. Our GPU-accelerated enhancements allow efficient calculations of multi-qubit systems, which can be used for the efficient implementation of QOC applications across multiple domains.

97 MATHEMATICS AND COMPUTING↗

Sequence length scaling in vision transformers for scientific images on frontier

Vision Transformers (ViTs) are pivotal for foundational models in scientific imagery, including Earth science applications, due to their capability to process large sequence lengths. While transformers for text have inspired scaling sequence lengths in ViTs, adapting these for ViTs introduces unique challenges. We develop distributed sequence parallelism for ViTs, enabling them to handle up to 1M tokens. Our approach, leveraging DeepSpeed-Ulysses and Long-Sequence-Segmentation with model sharding, is the first to apply sequence parallelism in ViT training, achieving a 94% batch scaling efficiency on 2,048 AMD-MI250X GPUs. Evaluating sequence parallelism in ViTs, particularly in models up to 10B parameters, highlighted substantial bottlenecks. We countered these with hybrid sequence, pipeline, and flash attention strategies, to scale beyond single GPU memory limits. Our method significantly enhances climate modeling accuracy by 20% in temperature predictions, marking the first training of a vision transformer model to convergence with a sequence length of 188K tokens, using full self-attention.

Tsaris, Aristeidis (aris) [ORNL] (ORCID:0000000277↗

Parallel Solver Framework for Mixed-Integer PDE-Constrained Optimization

ROL-PEBBL is a C++, MPI-based parallel code for mixed-integer PDE-constrained optimization (MIPDECO). In these problems we wish to optimize (control, design, etc.) physical systems, which must obey the laws of physics, when some of the decision variables must take integer values. ROL-PEBBL combines a code to efficiently search over integer choices (PEBBL = Parallel Enumeration Branch-and-Bound Library) and a code for efficient nonlinear optimization, including PDE-constrained optimization (ROL = Rapid Optimization Library). In this report, we summarize the design of ROL-PEBBL and initial applications/results. For an artificial source-inversion problem, finding sources of pollution on a grid from sparse samples, ROL-PEBBLs solution for the nest grid gave the best optimization guarantee for any general solver that gives both a solution and a quality guarantee.

97 MATHEMATICS AND COMPUTING↗

Technical Report: Toward a Scalable Algorithm to Compute High-Dimensional Integrals of Arbitrary Functions

Neutron experiments at the Spallation Neutron Source (SNS) at Oak Ridge National Laboratory (ORNL) frequently generate large amounts of data (on the order of 106-1012 data points). Hence, traditional data analysis tools run on a single CPU take too long to be practical and scientists are unable to efficiently analyze all data generated by experiments. Our goal is to develop a scalable algorithm to efficiently compute high-dimensional integrals of arbitrary functions. This algorithm can then be used to integrate the four-dimensional integrals that arise as part of modeling intensity from the experiments at the SNS. Here, three different one-dimensional numerical integration solvers from the GNU Scientific Library were modified and implemented to solve four-dimensional integrals. The results of these solvers on a final integrand provided by scientists at the SNS can be compared to the results of other methods, such as quasi-Monte Carlo methods, computing the same integral. A parallelized version of the most efficient method can allow scientists the opportunity to more effectively analyze all experimental data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Parallel Finite Element Domain Decomposition for Structural/Acoustic Analysis

A domain decomposition (DD) formulation for solving sparse linear systems of equations resulting from finite element analysis is presented. The formulation incorporates mixed direct and iterative equation solving strategics and other novel algorithmic ideas that are optimized to take advantage of sparsity and exploit modern computer architecture, such as memory and parallel computing. The most time consuming part of the formulation is identified and the critical roles of direct sparse and iterative solvers within the framework of the formulation are discussed. Experiments on several computer platforms using several complex test matrices are conducted using software based on the formulation. Small-scale structural examples are used to validate thc steps in the formulation and large-scale (l,000,000+ unknowns) duct acoustic examples are used to evaluate the ORIGIN 2000 processors, and a duster of 6 PCs (running under the Windows environment). Statistics show that the formulation is efficient in both sequential and parallel computing environmental and that the formulation is significantly faster and consumes less memory than that based on one of the best available commercialized parallel sparse solvers.

Nguyen, Duc T.↗

Scalable domain decomposition solvers for stochastic PDEs in high performance computing

Stochastic spectral finite element models of practical engineering systems may involve solutions of linear systems or linearized systems for non-linear problems with billions of unknowns. For stochastic modeling, it is therefore essential to design robust, parallel and scalable algorithms that can efficiently utilize high-performance computing to tackle such large-scale systems. Domain decomposition based iterative solvers can handle such systems. And though these algorithms exhibit excellent scalabilities, significant algorithmic and implementational challenges exist to extend them to solve extreme-scale stochastic systems using emerging computing platforms. Intrusive polynomial chaos expansion based domain decomposition algorithms are extended here to concurrently handle high resolution in both spatial and stochastic domains using an in-house implementation. Sparse iterative solvers with efficient preconditioners are employed to solve the resulting global and subdomain level local systems through multi-level iterative solvers. We also use parallel sparse matrix–vector operations to reduce the floating-point operations and memory requirements. Numerical and parallel scalabilities of these algorithms are presented for the diffusion equation having spatially varying diffusion coefficient modeled by a non-Gaussian stochastic process. Scalability of the solvers with respect to the number of random variables is also investigated.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Parallel O(log n) algorithms for open- and closed-chain rigid multibody systems based on a new mass matrix factorization technique

In this paper, parallel O(log n) algorithms for computation of rigid multibody dynamics are developed. These parallel algorithms are derived by parallelization of new O(n) algorithms for the problem. The underlying feature of these O(n) algorithms is a drastically different strategy for decomposition of interbody force which leads to a new factorization of the mass matrix (M). Specifically, it is shown that a factorization of the inverse of the mass matrix in the form of the Schur Complement is derived as M(exp -1) = C - B(exp *)A(exp -1)B, wherein matrices C, A, and B are block tridiagonal matrices. The new O(n) algorithm is then derived as a recursive implementation of this factorization of M(exp -1). For the closed-chain systems, similar factorizations and O(n) algorithms for computation of Operational Space Mass Matrix lambda and its inverse lambda(exp -1) are also derived. It is shown that these O(n) algorithms are strictly parallel, that is, they are less efficient than other algorithms for serial computation of the problem. But, to our knowledge, they are the only known algorithms that can be parallelized and that lead to both time- and processor-optimal parallel algorithms for the problem, i.e., parallel O(log n) algorithms with O(n) processors. The developed parallel algorithms, in addition to their theoretical significance, are also practical from an implementation point of view due to their simple architectural requirements.

Fijany, Amir↗

NWChem: scalable parallel computational chemistry

NWChem is a general purpose computational chemistry code specifically designed to run on distributed memory parallel computers. The core functionality of the code focuses on molecular dynamics, Hartree-Fock and density functional theory methods for both plane-wave basis sets as well as Gaussian basis sets, tensor contraction engine based coupled cluster capabilities and combined quantum mechanics/molecular mechanics descriptions. It was realized from the beginning that scalable implementations of these methods required a programming paradigm inherently different from what message passing approaches could offer. In response a global address space library, the Global Array Toolkit, was developed. The programming model it offers is based on using predominantly one-sided communication. This model underpins most of the functionality in NWChem and the power of it is exemplified by the fact that the code scales to tens of thousands of processors. In this paper the core capabilities of NWChem are described as well as their implementation to achieve an efficient computational chemistry code with high parallel scalability. NWChem is a modern, open source, computational chemistry code1 specifically designed for large scale parallel applications2. To meet the challenges of developing efficient, scalable and portable programs of this nature a particular code design was adopted. This code design involved two main features. First of all, the code is build up in a modular fashion so that a large variety of functionality can be integrated easily. Secondly, to facilitate writing complex parallel algorithms the Global Array toolkit was developed. This toolkit allows one to write parallel applications in a shared memory like approach, but offers additional mechanisms to exploit data locality to lower communication overheads. This framework has proven to be very successful in computational chemistry but is applicable to any engineering domain. Within the context created by the features above NWChem has grown into a general purpose computational chemistry code that supports a wide variety of energy expressions and capabilities to calculate properties based there upon. The main energy expressions are classical mechanics force fields, Hartree-Fock and DFT both for finite systems and condensed phase systems, coupled cluster, as well as QM/MM. For most energy expressions single point calculations, geometry optimizations, excited states, and other properties are available. Below we briefly discuss each of the main energy expressions and the critical points involved in scalable implementations thereof.

99 GENERAL AND MISCELLANEOUS↗

Resonant drive and nonlinear suppression of gradient-driven instabilities via interaction with shear Alfven waves

The nonlinear interaction of shear Alfven waves and gradient-driven instabilities on pressure gradients in the Large Plasma Device (LAPD) [Gekelman et al., Rev. Sci. Instrum. 62, 2875 (1991)] at UCLA is explored. Nonlinear response at the beat frequency between two shear Alfven waves is shown to resonantly drive unstable modes as well as otherwise damped modes. Resonantly driving the damped modes is shown to suppress the originally unstable mode, leaving only the beat-driven response with an overall reduction in fluctuation amplitude. A threshold is observed in the suppression behavior, requiring that the driven damped mode power be of order 10% of the power in the saturated unstable mode. The interaction is also observed to be dependent on the parallel wavenumber of the driven beat wave; efficient coupling and suppression is only observed for co-propagating beat waves with small parallel wavenumber, consistent with the parallel wavenumber of the gradient-driven modes.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

SU-D-207-04: GPU-Based 4D Cone-Beam CT Reconstruction Using Adaptive Meshing Method

Purpose: Due to the limited number of projections at each phase, the image quality of a four-dimensional cone-beam CT (4D-CBCT) is often degraded, which decreases the accuracy of subsequent motion modeling. One of the promising methods is the simultaneous motion estimation and image reconstruction (SMEIR) approach. The objective of this work is to enhance the computational speed of the SMEIR algorithm using adaptive feature-based tetrahedral meshing and GPU-based parallelization. Methods: The first step is to generate the tetrahedral mesh based on the features of a reference phase 4D-CBCT, so that the deformation can be well captured and accurately diffused from the mesh vertices to voxels of the image volume. After the mesh generation, the updated motion model and other phases of 4D-CBCT can be obtained by matching the 4D-CBCT projection images at each phase with the corresponding forward projections of the deformed reference phase of 4D-CBCT. The entire process of this 4D-CBCT reconstruction method is implemented on GPU, resulting in significantly increasing the computational efficiency due to its tremendous parallel computing ability. Results: A 4D XCAT digital phantom was used to test the proposed mesh-based image reconstruction algorithm. The image Result shows both bone structures and inside of the lung are well-preserved and the tumor position can be well captured. Compared to the previous voxel-based CPU implementation of SMEIR, the proposed method is about 157 times faster for reconstructing a 10 -phase 4D-CBCT with dimension 256×256×150. Conclusion: The GPU-based parallel 4D CBCT reconstruction method uses the feature-based mesh for estimating motion model and demonstrates equivalent image Result with previous voxel-based SMEIR approach, with significantly improved computational speed.

60 APPLIED LIFE SCIENCES↗

SU-F-I-10: Spatially Local Statistics for Adaptive Image Filtering

Purpose: To facilitate adaptive image filtering operations, addressing spatial variations in both noise and signal. Such issues are prevalent in cone-beam projections, where physical effects such as X-ray scattering result in spatially variant noise, violating common assumptions of homogeneous noise and challenging conventional filtering approaches to signal extraction and noise suppression. Methods: We present a computational mechanism for probing into and quantifying the spatial variance of noise throughout an image. The mechanism builds a pyramid of local statistics at multiple spatial scales; local statistical information at each scale includes (weighted) mean, median, standard deviation, median absolute deviation, as well as histogram or dynamic range after local mean/median shifting. Based on inter-scale differences of local statistics, the spatial scope of distinguishable noise variation is detected in a semi- or un-supervised manner. Additionally, we propose and demonstrate the incorporation of such information in globally parametrized (i.e., non-adaptive) filters, effectively transforming the latter into spatially adaptive filters. The multi-scale mechanism is materialized by efficient algorithms and implemented in parallel CPU/GPU architectures. Results: We demonstrate the impact of local statistics for adaptive image processing and analysis using cone-beam projections of a Catphan phantom, fitted within an annulus to increase X-ray scattering. The effective spatial scope of local statistics calculations is shown to vary throughout the image domain, necessitating multi-scale noise and signal structure analysis. Filtering results with and without spatial filter adaptation are compared visually, illustrating improvements in imaging signal extraction and noise suppression, and in preserving information in low-contrast regions. Conclusion: Local image statistics can be incorporated in filtering operations to equip them with spatial adaptivity to spatial signal/noise variations. An efficient multi-scale computational mechanism is developed to curtail processing latency. Spatially adaptive filtering may impact subsequent processing tasks such as reconstruction and numerical gradient computations for deformable registration. NIH Grant No. R01-184173.

60 APPLIED LIFE SCIENCES↗

Modulated heat pulse propagation and partial transport barriers in chaotic magnetic fields

Direct numerical simulations of the time dependent parallel heat transport equation modeling heat pulses driven by power modulation in three-dimensional chaotic magnetic fields are presented. The numerical method is based on the Fourier formulation of a Lagrangian-Green's function method that provides an accurate and efficient technique for the solution of the parallel heat transport equation in the presence of harmonic power modulation. The numerical results presented provide conclusive evidence that even in the absence of magnetic flux surfaces, chaotic magnetic field configurations with intermediate levels of stochasticity exhibit transport barriers to modulated heat pulse propagation. In particular, high-order islands and remnants of destroyed flux surfaces (Cantori) act as partial barriers that slow down or even stop the propagation of heat waves at places where the magnetic field connection length exhibits a strong gradient. Results on modulated heat pulse propagation in fully stochastic fields and across magnetic islands are also presented. In qualitative agreement with recent experiments in large helical device and DIII-D, it is shown that the elliptic (O) and hyperbolic (X) points of magnetic islands have a direct impact on the spatio-temporal dependence of the amplitude of modulated heat pulses.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Subspace recursive Fermi-operator expansion strategies for large-scale DFT eigenvalue problems on HPC architectures

Quantum mechanical calculations for material modeling using Kohn–Sham density functional theory (DFT) involve the solution of a nonlinear eigenvalue problem for N smallest eigenvector-eigenvalue pairs, with N proportional to the number of electrons in the material system. Here, these calculations are computationally demanding and have asymptotic cubic scaling complexity with the number of electrons. Large-scale matrix eigenvalue problems arising from the discretization of the Kohn–Sham DFT equations employing a systematically convergent basis traditionally rely on iterative orthogonal projection methods, which are shown to be computationally efficient and scalable on massively parallel computing architectures. However, as the size of the material system increases, these methods are known to incur dominant computational costs through the Rayleigh–Ritz projection step of the discretized Kohn–Sham Hamiltonian matrix and the subsequent subspace diagonalization of the projected matrix. This work explores the potential of polynomial expansion approaches based on recursive Fermi-operator expansion as an alternative to the subspace diagonalization of the projected Hamiltonian matrix to reduce the computational cost. Subsequently, we perform a detailed comparison of various recursive polynomial expansion approaches to the traditional approach of explicit diagonalization on both multi-node central processing unit and graphics processing unit architectures and assess their relative performance in terms of accuracy, computational efficiency, scaling behavior, and energy efficiency.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

High-performance epistasis detection in quantitative trait GWAS

epiSNP is a program for identifying pairwise single nucleotide polymorphism (SNP) interactions (epistasis) in quantitative-trait genome-wide association studies (GWAS). A parallel MPI version (EPISNPmpi) was created in 2008 to address this computationally expensive analysis on large data sets with many quantitative traits and SNP markers. However, the falling cost of genotyping has led to an explosion of large-scale GWAS data sets that challenge EPISNPmpi’s ability to compute results in a reasonable amount of time. Therefore, we optimized epiSNP for modern multi-core and highly parallel many-core processors to efficiently handle these large data sets. This paper describes the serial optimizations, dynamic load balancing using MPI-3 RMA operations, and shared-memory parallelization with OpenMP to further enhance load balancing and allow execution on the Intel Xeon Phi coprocessor (MIC). For a large GWAS data set, our optimizations provided a 38.43× speedup over EPISNPmpi on 126 nodes using 2 MICs on TACC’s Stampede Supercomputer. We also describe a Coarray Fortran (CAF) version that demonstrates the suitability of PGAS languages for problems with this computational pattern. We show that the Coarray version performs competitively with the MPI version on the NERSC Edison Cray XC30 supercomputer. Finally, the performance benefits of hyper-threading for this application on Edison (average 1.35× speedup) are demonstrated.

97 MATHEMATICS AND COMPUTING↗

Implementing Atmospheric Infrared Sounder (AIRS) and Cross-Track Infrared Sounder (CrIS) Cloud-Clearing Algorithm into the NASA GEOS: Focus on the 2017 Atlantic Tropical Cyclone Season

Numerical Weather Prediction (NWP) centers assimilate cloud-free infrared (IR) radiances because the assimilation of all-sky IR radiances is not yet operationally achievable. The cloud-clearing procedure offers a simpler, but effective strategy that produces cloud-affected radiances suitable for assimilation in partially cloudy regions. Several studies conducted by this team have demonstrated that IR Cloud-Cleared Radiances (CCRs), if thinned more aggressively than clear-sky radiances, can improve analysis and forecasts, particularly in meteorologically active areas. However, CCRs are not used by operational centers due partly to the thought that the process of cloud-clearing may affect latency and introduce difficult-to-control external dependencies. This study presents the results of implementing an Atmospheric Infrared Sounder (AIRS) and Cross-Track Infrared Sounder (CrIS) cloud-clearing procedure into the NASA Goddard Earth Observing System (GEOS) to demonstrate the portability of the procedure. The AIRS and CrIS cloud-clearing algorithms have been deprived of external dependencies, made customizable to any specific model, and the computational efficiency has been improved via parallelization. The revised AIRS and CrIS cloud-clearing algorithms allow a customized choice of channel selection, the use of a user-specified model's fields as first guess, and can perform in real time. Data assimilation experiments with the hybrid 4DEnVar GEOS system were successfully performed for the 2017 tropical cyclones (TC) season with a focus on three major hurricanes (Harvey, Irma, and Maria). This study shows that assimilation of locally-generated CCRs have a positive impact on both global skill and TC representation, compared to the assimilation of AIRS and CrIS clear-sky radiances, and a comparable or slightly improved impact compared to assimilation of CCRs produced by external sources, such as NASA's Distributed Active Archive Centers and NOAA’s Comprehensive Large Array-data Stewardship System. The customization and computational efficiency of the revised procedure would enable its usability in a real-time forecast context.

Niama Boukachaba↗