Search NASA⌕ Search

SEARCH · Search NASA

Results for “distributed parallelization”

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 361 records · Page 20

Synergy of two lower hybrid waves with different frequencies on EAST

Lower hybrid current drive (LHCD) is one of the major approaches maintaining long pulse discharges on EAST. There are two lower hybrid (LH) systems on EAST launching waves at 4.6 GHz and 2.45 GHz into the plasma, respectively, and the input power of the 4.6 GHz wave is typically dominant. Here, the synergy of the two waves and the modification of the power deposition of the 4.6 GHz wave by coupling the 2.45 GHz wave are investigated theoretically. According to the phase space analysis, the wave propagation domains of the two LH waves always overlap substantially with each other for typical LHCD experimental parameters on EAST, indicating that the coupling between them might be strong. Ray-tracing/Fokker-Planck simulations for a LH current drive experiment on EAST show that the change of the power deposition profile due to the coupling could be understood by the rise and fall of the tails of the parallel electron distribution functions on different flux surfaces. If either the injected wave power at 2.45 GHz is comparable with that at 4.6 GHz or the incident N ∥ of the 2.45 GHz wave reaches a high value (e.g., $5.7/\sqrt{T_{e,0}}$), the power deposition profile of the 4.6 GHz wave can be modified greatly due to the coupling with the 2.45 GHz wave. With the parameters compatible with the ability of the LH wave system on EAST, injection of the 2.45 GHz wave can still modify the power deposition profile of the 4.6 GHz wave significantly by combining those two approaches. Finally, it is shown how a 4.6 GHz wave which cannot be Landau damped when injected alone is absorbed in low density plasmas with a magnetic shear reversal configuration in the presence of a 2.45 GHz wave.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Scalable quantum computational science: A perspective from block-encodings and polynomial transformations

Significant developments made in quantum hardware and error correction recently have been driving quantum computing toward practical utility. However, gaps remain between abstract quantum algorithmic development and practical applications in computational sciences. In this perspective article, we propose several properties that scalable quantum computational science methods should possess. We further discuss how block-encodings and polynomial transformations can potentially serve as a unified framework with the desired properties. Recent advancements on these topics are presented, including the construction and assembly of block-encodings, and various generalizations of quantum signal processing (QSP) algorithms to perform polynomial transformations. The scalability of QSP methods on parallel and distributed quantum architectures is also highlighted. Promising applications in simulation and observable estimation in chemistry, physics, and optimization problems are presented. We hope this perspective serves as a gentle introduction to state-of-the-art quantum algorithms for the computational science community and inspires future development of scalable quantum computational science methodologies that bridge theory and practice.

Bayesian inference↗

MADmap: A MASSIVELY PARALLEL MAXIMUM LIKELIHOOD COSMIC MICROWAVE BACKGROUND MAP-MAKER

MADmap is a software application used to produce maximum likelihood images of the sky from time-ordered data which include correlated noise, such as those gathered by cosmic microwave background (CMB) experiments. It works efficiently on platforms ranging from small workstations to the most massively parallel supercomputers. Map-making is a critical step in the analysis of all CMB data sets, and the maximum likelihood approach is the most accurate and widely applicable algorithm; however, it is a computationally challenging task. This challenge will only increase with the next generation of ground-based, balloon-borne, and satellite CMB polarization experiments. The faintness of the B-mode signal that these experiments seek to measure requires them to gather enormous data sets. MADmap is already being run on up to O(10{sup 11}) time samples, O(10{sup 8}) pixels, and O(10{sup 4}) cores, with ongoing work to scale to the next generation of data sets and supercomputers. We describe MADmap's algorithm based around a preconditioned conjugate gradient solver, fast Fourier transforms, and sparse matrix operations. We highlight MADmap's ability to address problems typically encountered in the analysis of realistic CMB data sets and describe its application to simulations of the Planck and EBEX experiments. The massively parallel and distributed implementation is detailed and scaling complexities are given for the resources required. MADmap is capable of analyzing the largest data sets now being collected on computing resources currently available, and we argue that, given Moore's Law, MADmap will be capable of reducing the most massive projected data sets.

79 ASTRONOMY AND ASTROPHYSICS↗

FAST AND OPTIMAL COSMIC MICROWAVE BACKGROUND LENSING USING STATISTICAL INTERPOLATION ON THE SPHERE

We describe an accurate and fast pixel-based statistical method to interpolate fields of arbitrary spin on the sphere. We call this method Fast and Lean Interpolation on the Sphere (FLINTS). The method predicts the optimal interpolated values based on the theory of isotropic Gaussian random fields and provides an accurate error estimate at no additional cost. We use this method to compute lensed cosmic microwave background (CMB) maps precisely and quickly, achieving a relative precision of 0.02% at a HEALPIX resolution of N {sub side} = 4096, for a bandlimit of l{sub max}= 4096 in the same time it takes to simulate the original, unlensed CMB map. The method is suitable for efficient, distributed memory parallelization. The power spectra of our lensed maps are accurate to better than 0.5% at l= 3000 for the temperature, the E and B modes of the polarization. As expected theoretically, we demonstrate that, on realistic cases, this method is between two and three orders of magnitude more precise than other known interpolation methods for the same computational cost.

79 ASTRONOMY AND ASTROPHYSICS↗

LATTE: open-source, high-performance traveltime computation, tomography and source location in acoustic and elastic media

Traveltime-based tomography and source location are fundamental approaches for imaging subsurface structures and understanding the spatiotemporal distribution of seismicity from local to global scales. We present an open-source, high-performance framework integrating eikonal equation solvers and adjoint-state theory for traveltime computation, velocity tomography, source location and joint tomography-location in 2-D/3-D acoustic and elastic media. We introduce novel regularization schemes based on total generalized p-variation, structural similarity and multitask machine learning to enhance the fidelity and interpretability of inverted models and source locations. Key features of our implementation also include the ability to leverage both absolute-difference and double-difference traveltime misfits for high-fidelity velocity tomography and source parameter estimation; support for traveltime computation and inversion in diverse 2-D/3-D scenarios with arbitrary source and receiver distributions; and a perturbation-based optimal step-size estimation method to reduce computational costs. In addition, our implementation employs shared-memory and distributed-memory parallelization to provide an efficient solution for traveltime computation, tomography, and source location. In conclusion, we validate the efficacy and accuracy of our approach through multiple synthetic data examples.

58 GEOSCIENCES↗

In-beam 𝛾-ray spectroscopy of 29 S populated in direct knockout, dissipative reactions, and fragmentation

Excited states in the neutron-deficient nucleus 29 S were populated in one-neutron knockout and several-nucleon removal reactions and studied using in-beam 𝛾-ray spectroscopy. New excited states and 𝛾-ray transitions were established using the Segmented Germanium Array SeGA and the 𝛾-ray tracking array GRETINA. The new transitions observed in the highly dissipative tail of the parallel momentum distribution from one-nucleon knockout and in five- and nine-nucleon removal reactions were utilized to calculate mirror energy differences with 29 Al . Highly dissipative reactions further prove to be a valuable tool in populating excited states typically inaccessible in direct reactions. The relative populations of the states in 29 S from the several-nucleon removal reactions were found to be consistent, suggesting for the first time that five-nucleon removal behaves predominately like statistical fragmentation.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

In-beam γ-ray spectroscopy of 32 Mg via direct reactions

Background: The nucleus 32 Mg (N=20 and Z=12) plays a central role in the so-called “island of inversion,” where in the ground states sd-shell neutrons are promoted to the fp-shell orbitals across the shell gap, resulting in the disappearance of the canonical neutron magic number N=20. Purpose: The primary goals of this work are to extend the level scheme of 32Mg, provide spin-parity assignments to excited states, and discuss the microscopic structure of each state through comparisons with theoretical calculations. Method: In-beam γ-ray spectroscopy of 32 Mg was performed using two direct-reaction probes: one-neutron (two-proton) knockout reactions on 33 Mg ( 34 Si). Final-state exclusive cross sections and parallel momentum distributions were extracted from the experimental data and compared with eikonal-based reaction model calculations combined with shell-model overlap functions. Results: Owing to the remarkable selectivity of the one-neutron and two-proton knockout reactions, a significantly updated level scheme for 32 Mg, which exhibits negative-parity intruder and positive-parity normal states, was constructed. The experimental results were confronted with four different nuclear structure models. Conclusions: In some of these models, different aspects of 32 Mg and the transition into the island of inversion are well described. However, unexplained discrepancies remain, and, even with the help of these state-of-the-art theoretical approaches, the structure of this key nucleus is not yet fully captured.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Probing the weakly-bound neutron orbit of {sup 31}Ne with total reaction and one-neutron removal cross sections

A candidate of a neutron-halo nucleus, {sup 31}Ne, contains a single neutron in the pf shell. Within the Glauber and eikonal models, we analyze reactions used to study {sup 31}Ne. We show in a {sup 30}Ne+n model that the magnitudes of the total reaction and above all of the one-neutron removal cross sections of {sup 31}Ne on {sup 12}C and {sup 208}Pb targets strongly depend on the orbital angular momentum of the neutron, thereby providing us with efficient ways to determine both the spin-parity and structure of the ground state of {sup 31}Ne. Besides these inclusive observables, we also calculate energy and parallel-momentum distributions for the breakup of {sup 31}Ne and show their strong dependence on the orbital of the valence neutron in the bound state of {sup 31}Ne.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Electron Current Drive by Fusion-Product-Excited Lower Hybrid Drift Instability

We present first principles simulations of the direct collisionless coupling of the free energy of fusion-born ions into electron current in a magnetically confined fusion plasma. These simulations demonstrate, for the first time, a key building block of some 'alpha channeling' scenarios for tokamak experiments. Spontaneously excited obliquely propagating waves in the lower hybrid frequency range undergo Landau damping on resonant electrons, drawing out an asymmetric tail in the electron parallel velocity distribution, which carries a current.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

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↗

Newly Released Capabilities in the Distributed-Memory SuperLU Sparse Direct Solver

We present the new features available in the recent release of SuperLU_DIST, Version 8.1.1. SuperLU_DIST is a distributed-memory parallel sparse direct solver. The new features include (1) a 3D communication-avoiding algorithm framework that trades off inter-process communication for selective memory duplication, (2) multi-GPU support for both NVIDIA GPUs and AMD GPUs, and (3) mixed-precision routines that perform single-precision LU factorization and double-precision iterative refinement. Apart from the algorithm improvements, we also modernized the software build system to use CMake and Spack package installation tools to simplify the installation procedure. Throughout the article, we describe in detail the pertinent performance-sensitive parameters associated with each new algorithmic feature, show how they are exposed to the users, and give general guidance of how to set these parameters. We illustrate that the solver’s performance both in time and memory can be greatly improved after systematic tuning of the parameters, depending on the input sparse matrix and underlying hardware.

97 MATHEMATICS AND COMPUTING↗

Communication Lower Bounds and Optimal Algorithms for Symmetric Matrix Computations

In this article, we focus on the communication costs of three symmetric matrix computations: (i) multiplying a matrix with its transpose, known as a symmetric rank-k update (SYRK) (ii) adding the result of the multiplication of a matrix with the transpose of another matrix and the transpose of that result, known as a symmetric rank-2k update (SYR2K) (iii) performing matrix multiplication with a symmetric input matrix (SYMM). All three computations appear in the Level 3 Basic Linear Algebra Subroutines (BLAS) and have wide use in applications involving symmetric matrices. We establish communication lower bounds for these kernels using sequential and distributed-memory parallel computational models, and we show that our bounds are tight by presenting communication-optimal algorithms for each setting. Our lower bound proofs rely on applying a geometric inequality for symmetric computations and analytically solving constrained nonlinear optimization problems. As a result, the symmetric matrix and its corresponding computations are accessed and performed according to a triangular block partitioning scheme in the optimal algorithms.

Al Daas, Hussam [Rutherford Appleton Laboratory, D↗

A Survey on Error-Bounded Lossy Compression for Scientific Datasets

Error-bounded lossy compression has been effective in significantly reducing the data storage/transfer burden while preserving the reconstructed data fidelity very well. Many error-bounded lossy compressors have been developed for a wide range of parallel and distributed use cases for years. They are designed with distinct compression models and principles, such that each of them features particular pros and cons. In this article, we provide a comprehensive survey of emerging error-bounded lossy compression techniques. The key contribution is fourfold. (1) We summarize a novel taxonomy of lossy compression into six classic models. (2) We provide a comprehensive survey of 10 commonly used compression components/modules. (3) We summarized pros and cons of 47 state-of-the-art lossy compressors and present how state-of-the-art compressors are designed based on different compression techniques. (4) We discuss how customized compressors are designed for specific scientific applications and use-cases. We believe this survey is useful to multiple communities including scientific applications, high-performance computing, lossy compression, and big data.

Error-Bounded Lossy Compression↗

Performance Models for the Spike Banded Linear System Solver

With availability of large-scale parallel platforms comprised of tens-of-thousands of processors and beyond, there is significant impetus for the development of scalable parallel sparse linear system solvers and preconditioners. An integral part of this design process is the development of performance models capable of predicting performance and providing accurate cost models for the solvers and preconditioners. There has been some work in the past on characterizing performance of the iterative solvers themselves. In this paper, we investigate the problem of characterizing performance and scalability of banded preconditioners. Recent work has demonstrated the superior convergence properties and robustness of banded preconditioners, compared to state-of-the-art ILU family of preconditioners as well as algebraic multigrid preconditioners. Furthermore, when used in conjunction with efficient banded solvers, banded preconditioners are capable of significantly faster time-to-solution. Our banded solver, the Truncated Spike algorithm is specifically designed for parallel performance and tolerance to deep memory hierarchies. Its regular structure is also highly amenable to accurate performance characterization. Using these characteristics, we derive the following results in this paper: (i) we develop parallel formulations of the Truncated Spike solver, (ii) we develop a highly accurate pseudo-analytical parallel performance model for our solver, (iii) we show excellent predication capabilities of our model – based on which we argue the high scalability of our solver. Our pseudo-analytical performance model is based on analytical performance characterization of each phase of our solver. These analytical models are then parameterized using actual runtime information on target platforms. An important consequence of our performance models is that they reveal underlying performance bottlenecks in both serial and parallel formulations. All of our results are validated on diverse heterogeneous multiclusters – platforms for which performance prediction is particularly challenging. Finally, we provide predict the scalability of the Spike algorithm using up to 65,536 cores with our model. In this paper we extend the results presented in the Ninth International Symposium on Parallel and Distributed Computing.

Manguoglu, Murat↗

MapReduce MPI library (MR-MPI) v. 1.0

The MapReduce MPI library is a software tool for performing MapReduce operations on a distributed memory parallel computer via message passing (MPI). These are data-processing or computational operations which achieve parallelism by breaking a large task into two stages, a map and a reduce . Each of these are formulated as simple on-processor functions which the user can easily write. The library assigns independent tasks to processors and performs the parallel data movement and transformations behind the scenes.

PLIMPTON, STEVEN↗

Reeber v2.0

Reeber is a library for shared- and distributed-memory parallel computation of merge trees

Morozov, Dmitriy↗

ECP-ExaGraph/Submodular-b-matching

A b-MATCHING is a subset of edges M such that at most b(v) edges in M are incident on each vertex v, where b(v) is specified. We present a distributed-memory parallel algorithm, b-SUITOR, that computes a b-MATCHING with more than half the maximum weight in a graph with weights on the edges

Ferdous, S M↗