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 325 records · Page 18

Avoiding excess computation in asynchronous evolutionary algorithms

Abstract Asynchronous evolutionary algorithms are becoming increasingly popular as a means of making full use of many processors while solving computationally expensive search and optimization problems. These algorithms excel at keeping large clusters fully utilized, but may sometimes inefficiently sample an excess of fast‐evaluating solutions at the expense of higher‐quality, slow‐evaluating ones. We have previously introduced a steady‐state parent selection strategy, SWEET (“Selection whilE EvaluaTing”), that sometimes selects individuals that are still being evaluated and allows them to reproduce early. We perform a takeover‐time analysis that confirms that this strategy gives slow‐evaluating individuals that have higher fitnesses an increased ability to multiply in the population. We also find that SWEET appears effective at improving optimization performance on problems in which solution quality is positively correlated with evaluation time. We evaluate our approach on six simulated real‐valued optimization problems and three real‐world applications: an autonomous vehicle controller problem that involves tuning a spiking neural network and two adversarial EA problems. We further evaluate SWEET versus a basic asynchronous process in a simulated setting. We present evidence that SWEET outperforms basic asynchronous processes in a use‐case in which performance is positively correlated with evaluation time, and performs comparably (and often better) than basic asynchronous processes in several use‐cases where performance is negatively correlated with evaluation time. That said, in the cases where performance and evaluation time are negatively correlated the variance of outcomes for SWEET is notably high.

97 MATHEMATICS AND COMPUTING↗

Modern Computational Techniques for the HMMER Sequence Analysis

This paper focuses on the latest research and critical reviews on modern computing architectures, software and hardware accelerated algorithms for bioinformatics data analysis with an emphasis on one of the most important sequence analysis applications—hidden Markov models (HMM). We show the detailed performance comparison of sequence analysis tools on various computing platforms recently developed in the bioinformatics society. The characteristics of the sequence analysis, such as data and compute-intensive natures, make it very attractive to optimize and parallelize by using both traditional software approach and innovated hardware acceleration technologies.

59 BASIC BIOLOGICAL SCIENCES↗

jShyLU Scalable Hybrid Preconditioner and Solver

ShyLU is numerical software to solve sparse linear systems of equations. ShyLU uses a hybrid direct-iterative Schur complement method, and may be used either as a preconditioner or as a solver. ShyLU is parallel and optimized for a single compute Solver node. ShyLU will be a package in the Trilinos software framework.

SciDAC↗

Paracousti v. 2.0.0

Paracousti simulates 3-D acoustic wave propagation in fixed (non-moving) complex media. It solves the linear acoustic equations of motion using the velocity-pressure system of first order linear differential equations on a finite-difference Cartesian grid using Newton’s law of motion and mass continuity equations. It also has the ability to incorporate acoustic attenuation to simulate non-recoverable energy losses via the velocity-memory-pressure system of linear differential equations. We assume stationary, non-heat conducting, adiabatic media (fluid) where the background sound speed and material density are fixed in time. Capabilities include massively parallel design, optimization for high contrast media interfaces, inclusion of arbitrary pressure and force sources defined by the user, inclusion of arbitrary pressure and velocity receivers defined by the user, acoustic wavefield snapshots in time for visualization, and convolutional perfectly matched layers to minimize artificial grid boundary reflections. Paracousti was built upon the foundational framework of TDAAPS (Time-Domain Atmospheric Acoustic Propagation Suite) by Neill Symons, Dave Aldridge, and Leiph Preston.

Preston, Leiph↗

Devastator Parallel Discrete Event Simulation Runtime (Devastator) v1.0

The Devastator runtime is a modern C++ implementation of optimistic parallel discrete event simulation methods. Devastator allows simulation application code to productively specify their component and event functionality with C++14 constructs. It utilizes GASNet-EX for distributed memory communication and includes parallel performance optimizations such as light-weight thread message queues and asynchronous GVT. Furthermore, it supports efficient event broadcasts and pause-rewind-resume functionality to support periodic load balancing and outer loop optimization algorithms.

Chan, Cy↗

Analysis and optimization of gyrokinetic toroidal simulations on homogenous and heterogenous platforms

The Gyrokinetic Toroidal Code (GTC) uses the particle-in-cell method to efficiently simulate plasma microturbulence. This paper presents novel analysis and optimization techniques to enhance the performance of GTC on large-scale machines. We introduce cell access analysis to better manage locality vs. synchronization tradeoffs on CPU and GPU-based architectures. Finally, our optimized hybrid parallel implementation of GTC uses MPI, OpenMP, and NVIDIA CUDA, achieves up to a 2× speedup over the reference Fortran version on multiple parallel systems, and scales efficiently to tens of thousands of cores.

97 MATHEMATICS AND COMPUTING↗

Experience with OpenMP for MADX-SC

MADX-SC allows the treatment of frozen space charge using beam-beam elements in a thin lattice, i.e. one can take advantage of the standard set-up of MAD-X lattices without the need for specialized codes for the space-charge (SC) evaluation. The idea is to simulate over many turns without the problem of noise as in the PIC SC codes. For the examples under study, like the PS and RHIC, it would be desirable to simulate up to 1 million turns or more. To this end one had to make an effort to optimize the scalar speed and, most importantly, get a speed-up of approximately a factor of 5 using OpenMP.

43 PARTICLE ACCELERATORS↗

Next Generation Suspension Dynamics Algorithms

This research project has the objective to extend the range of application, improve the efficiency and conduct simulations with the Fast Lubrication Dynamics (FLD) algorithm for concentrated particle suspensions in a Newtonian fluid solvent. The research involves a combination of mathematical development, new computational algorithms, and application to processing flows of relevance in materials processing. The mathematical developments clarify the underlying theory, facilitate verification against classic monographs in the field and provide the framework for a novel parallel implementation optimized for an OpenMP shared memory environment. The project considered application to consolidation flows of major interest in high throughput materials processing and identified hitherto unforeseen challenges in the use of FLD in these applications. Extensions to the algorithm have been developed to improve its accuracy in these applications.

97 MATHEMATICS AND COMPUTING↗

SBIR Phase I Final Report, TACO: Distributed and Heterogeneous Sparse Compiler

Tensor algebra is a powerful tool for computing, but writing optimized codes that operate on sparse tensors can be very complex. This project enables a Tensor Algebra Compiler (TACO) that simplifies this task from man-years to man-days and extends TACO to support complex and large distributed systems. This report details the hypotheses, approaches used, and findings in this project.

97 MATHEMATICS AND COMPUTING↗

Cobalt-Free Cathodes for Next Generation Li-Ion Batteries

In this U.S. Department of Energy sponsored project Nexceris, in collaboration with project partners; The Ohio State University and Navitas Advanced Systems have advanced the technical maturity of a non-cobalt containing cathode for next-generation Li-ion batteries. The cathode is based on the lithium manganese nickel-titanium oxide, LiNi 0.5 Mn 1.5 TiO 4 (LNMTO) high voltage spinel. To address limitations with poor cycle and calendar life an microstucturally hierarchical LNMO/LNMTO core-shell cathode powder has been developed that enables the formation of a solid-electrolyte interface that effectively passivates the cathode surface. The microstructural enhancements of the cathode material focus on preferentially enriching the surface with titanium. In parallel, new, optimized binder and electrolyte chemistries have been incorporated to address degradation mechanisms associated with high-voltage systems. Single-layer pouch cell and large-format 2-Ah cell testing have shown that an optimized LNMO/LNMTO core-shell powder significantly improves initial cell capacity and cycle life compared to homogeneous LNMO powder. To support development and the fabrication of 2-Ah cells a novel Hybrid Alternative Wet-Chemical Synthesis (HAWCS) process have been developed. This low-cost, synthesis approach enables the excellent compositional and particle morphology control achieved with co-precipitation without the strict process controls and associated expensive process equipment.

25 ENERGY STORAGE↗

Automatic Generation of Algorithms for High-Speed Reliable Lossy Data Compression (Final Report)

Fast reliable data compression is urgently needed for many leading-edge scientific instruments and for exascale high-performance computing applications because they produce vast amounts of data at extremely high rates. The goal of this project has been to develop a framework named LC that is able to automatically generate high-speed lossless and reliable lossy compression and decompression algorithms that can be customized for different kinds of data. The resulting LC framework is freely available on GitHub. To achieve high-speed operation, LC outputs optimized and parallelized CPU and GPU implementations of the generated algorithms. To ensure the quality of lossily compressed data, LC guarantees the user-provided error bound. To be able to customize the compression algorithm to various use cases, LC can synthesize millions of different algorithms and automatically search for the one that works best for the given data. We have already employed LC to create state-of-the-art lossless and lossy compressors for scientific data as well as leading lossless compressors for images. We hope that LC and the customized, fast, reliable, and CPU/GPU-compatible compression algorithms that it can generate will greatly benefit the many scientific applications that need not only high trustworthiness but also high performance.

97 MATHEMATICS AND COMPUTING↗

Cell-free Scaled Production and Adjuvant Addition to a Recombinant Major Outer Membrane Protein from Chlamydia muridarum for Vaccine Development

Subunit vaccines offer advantages over more traditional inactivated or attenuated whole-cell-derived vaccines in safety, stability, and standard manufacturing. To achieve an effective protein-based subunit vaccine, the protein antigen often needs to adopt a native-like conformation. This is particularly important for pathogensurface antigens that are membrane-bound proteins. Cell-free methods have been successfully used to produce correctly folded functional membrane protein through the co-translation of nanolipoprotein particles (NLPs), commonly known as nanodiscs. This strategy can be used to produce subunit vaccines consisting of membrane proteins in a lipid-bound environment. However, cell-free protein production is often limited to small scale (<1 mL). The amount of protein produced in small-scale production runs is usually sufficient for biochemical and biophysical studies. However, the cell-free process needs to be scaled up, optimized, and carefully tested to obtain enough protein for vaccine studies in animal models. Other processes involved in vaccine production, such as purification, adjuvant addition, and lyophilization, need to be optimized in parallel. This paper reports the development of a scaled-up protocol to express, purify, and formulate a membrane-bound protein subunit vaccine

59 BASIC BIOLOGICAL SCIENCES↗

Geometric registration and rectification of spaceborne SAR imagery

This paper describes the development of automated location and geometric rectification techniques for digitally processed synthetic aperture radar (SAR) imagery. A software package has been developed that is capable of determining the absolute location of an image pixel to within 60 m using only the spacecraft ephemeris data and the characteristics of the SAR data collection and processing system. Based on this location capability algorithms have been developed that geometrically rectify the imagery, register it to a common coordinate system and mosaic multiple frames to form extended digital SAR maps. These algorithms have been optimized using parallel processing techniques to minimize the operating time. Test results are given using Seasat SAR data.

Curlander, J. C.↗

Optimal expression evaluation for data parallel architectures

A data parallel machine represents an array or other composite data structure by allocating one processor per data item. A pointwise operation can be performed between two such arrays in unit time, provided their corresponding elements are allocated in the same processors. If the arrays are not aligned in this fashion, the cost of moving one or both of them is part of the cost of operation. The choice of where to perform the operation then affects this cost. If an expression with several operands is to be evaluated, there may be many choices of where to perform the intermediate operations. An efficient algorithm is given to find the minimum cost way to evaluate an expression, for several different data parallel architectures. The algorithm applies to any architecture in which the metric describing the cost of moving an array has a property called robustness. This encompasses most of the common data parallel communication architectures, including meshes of arbitrary dimension and hypercubes.

Gilbert, J. R.↗

Optimal expression evaluation for data parallel architectures

A data parallel machine represents an array or other composits data structure by allocating one processor per data item. A pointwise operation can be performed between two such arrays in unit time, provided their corresponding elements are allocated in the same processors. If the arrays are not aligned in this fashion, the cost of moving one or both of them is part of the cost of operation. The choice of where to perform the operation then affects this cost. If an expression with several operands is to be evaluated, there may be many choices of where to perform the intermediate operations. An efficient algorithm is given to find the minimum cost way to evaluate an expression, for several different data parallel architectures. The algorithm applies to any architecture in which the metric describing the cost of moving an array has a property called robustness. This encompasses most of the common data parallel communication architectures, including meshes of arbitrary dimension and hypercubes.

Gilbert, John R.↗