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 1,765 records · Page 98

GASP Advancements With Symbolic Computations, Optimization, and Decoupled Numerical Methods

NASA is exploring advancements in hybrid-electric propulsion concepts for aircraft design. A new analysis capability has been deployed at NASA’s Ames Research Center using a new mathematical modeling framework in Python that leverages symbolic representation of mathematical expressions, optimization-based problem formulations, and standalone numerical methods. This capability, called Gascon, has been verified against NASA’s General Aviation Synthesis Program (GASP) results for several vehicles that exercise the analysis capability for a variety of aircraft classes and engine models, including both turbofans and turboprops. We believe this capability will set the stage for more rapid development of novel aircraft models with more flexible design assessments using optimization, and more traceable analysis for reproducibility. Additionally, a novel Pareto optimization-based design space exploration that shows the trade between range flown and fuel burn by manipulating the thrust split during cruise for a true parallel hybrid aircraft was developed by leveraging the unique features of Gascon.

aircraft design↗

High-Performance I/O: HDF5 for Lattice QCD

Practitioners of lattice QCD/QFT have been some of the primary pioneer users of the state-of-the-art high-performance-computing systems, and contribute towards the stress tests of such new machines as soon as they become available. As with all aspects of high-performance-computing, I/O is becoming an increasingly specialized component of these systems. In order to take advantage of the latest available high-performance I/O infrastructure, to ensure reliability and backwards compatibility of data files, and to help unify the data structures used in lattice codes, we have incorporated parallel HDF5 I/O into the SciDAC supported USQCD software stack. Here we present the design and implementation of this I/O framework. Our HDF5 implementation outperforms optimized QIO at the 10-20% level and leaves room for further improvement by utilizing appropriate dataset chunking.

Kurth, Thorsten↗

High-Performance I/O: HDF5 for Lattice QCD

Practitioners of lattice QCD/QFT have been some of the primary pioneer users of the state-of-the-art high-performance-computing systems, and contribute towards the stress tests of such new machines as soon as they become available. As with all aspects of high-performance-computing, I/O is becoming an increasingly specialized component of these systems. In order to take advantage of the latest available high-performance I/O infrastructure, to ensure reliability and backwards compatibility of data files, and to help unify the data structures used in lattice codes, we have incorporated parallel HDF5 I/O into the SciDAC supported USQCD software stack. Here we present the design and implementation of this I/O framework. Our HDF5 implementation outperforms optimized QIO at the 10-20% level and leaves room for further improvement by utilizing appropriate dataset chunking.

97 MATHEMATICS AND COMPUTING↗

Real Time Optima Tracking Using Harvesting Models of the Genetic Algorithm

Tracking optima in real time propulsion control, particularly for non-stationary optimization problems is a challenging task. Several approaches have been put forward for such a study including the numerical method called the genetic algorithm. In brief, this approach is built upon Darwinian-style competition between numerical alternatives displayed in the form of binary strings, or by analogy to 'pseudogenes'. Breeding of improved solution is an often cited parallel to natural selection in.evolutionary or soft computing. In this report we present our results of applying a novel model of a genetic algorithm for tracking optima in propulsion engineering and in real time control. We specialize the algorithm to mission profiling and planning optimizations, both to select reduced propulsion needs through trajectory planning and to explore time or fuel conservation strategies.

Baskaran, Subbiah↗

How to cluster in parallel with neural networks

Partitioning a set of N patterns in a d-dimensional metric space into K clusters - in a way that those in a given cluster are more similar to each other than the rest - is a problem of interest in astrophysics, image analysis and other fields. As there are approximately K(N)/K (factorial) possible ways of partitioning the patterns among K clusters, finding the best solution is beyond exhaustive search when N is large. Researchers show that this problem can be formulated as an optimization problem for which very good, but not necessarily optimal solutions can be found by using a neural network. To do this the network must start from many randomly selected initial states. The network is simulated on the MPP (a 128 x 128 SIMD array machine), where researchers use the massive parallelism not only in solving the differential equations that govern the evolution of the network, but also by starting the network from many initial states at once, thus obtaining many solutions in one run. Researchers obtain speedups of two to three orders of magnitude over serial implementations and the promise through Analog VLSI implementations of speedups comensurate with human perceptual abilities.

Kamgar-Parsi, Behzad↗

Effects of Propylene Carbonate Content in CsPF 6 -Containing Electrolytes on the Enhanced Performances of Graphite Electrode for Lithium-Ion Batteries

The effects Of propylene carbonate (PC) content in CsPF6-containing electrolytes on the performances of graphite electrode in lithium half cells and in graphite parallel to LiNi0.80Co0.15Al0.05O2 (NCA) full cells are investigated. It is found that the performance of graphite electrode is significantly-affected by PC content in the CsPF6-containing electrolytes. An optimal PC content of 20% by weight in the solvent mixtures is identified. The enhanced electrochemical performance of graphite electrode can be attributed to the synergistic effects of the PC solvent and the Cs+ additive. The synergistic effects of Cs+ additive and appropriate amount of PC enable the formation of a robust, ultrathin, and compact solid electrolyte interphase (SEI) layer on the surface of graphite electrode, which is only permeable for desolvated Li+ ions and allows fast Li+ ion transport through it. Therefore, this SEI layer effectively suppresses the PC cointercalation and largely alleviates the Li dendrite formation on graphite electrode during lithiation even at relatively high current densities. The presence of low-melting-point PC solvent improves the sustainable operation of graphite parallel to NCA full cells under a wide temperature range. The fundamental findings also shed light On the importance of manipulating/maintaining the electrode/electrolyte interphasial stability in various energy-storage devices.

25 ENERGY STORAGE↗

Newton trust-region methods with primary variable switching for simulating high temperature multiphase porous media flow

Coupling multiphase flow with energy transport due to high temperature heat sources introduces significant new challenges since boiling and condensation processes can lead to dry-out conditions with subsequent re-wetting. The transition between two-phase and single-phase behavior can require changes to the primary dependent variables adding discontinuities as well as extending constitutive nonlinear relations to extreme physical conditions. Practical simulations of large-scale engineered domains lead to Jacobian systems with a very large number of unknowns that must be solved efficiently using iterative methods in parallel on high-performance computers. Performance assessment of potential nuclear repositories, carbon sequestration sites and geothermal reservoirs can require numerous Monte-Carlo simulations to explore uncertainty in material properties, boundary conditions, and failure scenarios. Due to the numerical challenges, standard NR iteration may not converge over the range of required simulations and require more sophisticated optimization method like trust-region. In this study, we use the open-source simulator PFLOTRAN for the important practical problem of the safety assessment of future nuclear waste repositories in the U.S. DOE geologic disposal safety assessment Framework. The simulator applies the PETSc parallel framework and a backward Euler, finite volume discretization. We demonstrate failure of the conventional NR method and the success of trust-region modifications to Newton’s method for a series of test problems of increasing complexity. Trust-region methods essentially modify the Newton step size and direction under some circumstances where the standard NR iteration can cause the solution to diverge or oscillate. Furthermore, we show how the Newton Trust-Region method can be adapted for Primary Variable Switching (PVS) when the multiphase state changes due to boiling or condensation. The simulations with high-temperature heat sources which led to extreme nonlinear processes with many state changes in the domain did not converge with NR, but they do complete successfully with the trust-region methods modified for PVS. This implementation effectively decreased weeks of simulation time needing manual adjustments to complete a simulation down to a day. Finally, we show the strong scalability of the methods on a single node and multiple nodes in an HPC cluster.

54 ENVIRONMENTAL SCIENCES↗

High resolution simulations of ignition capsule designs for the National Ignition Facility

Ignition capsule designs for the National Ignition Facility (NIF) [G. H. Miller, E. I. Moses, and C. R. Wuest, Opt. Eng. 443, 2841 (2004)] have continued to evolve in light of improved physical data inputs, improving simulation techniques, and - most recently - experimental data from a growing number of NIF sub-ignition experiments. This paper summarizes a number of recent changes to the cryogenic capsule design and some of our latest techniques in simulating its performance. Specifically, recent experimental results indicated harder x-ray drive spectra in NIF hohlraums than were predicted and used in previous capsule optimization studies. To accommodate this harder drive spectrum, a series of high-resolution 2-D simulations, resolving Legendre mode numbers as high as two thousand, were run and the germanium dopant concentration and ablator shell thicknesses re-optimized accordingly. Simultaneously, the possibility of cooperative or nonlinear interaction between neighboring ablator surface defects has motivated a series of fully 3-D simulations run with the massively parallel HYDRA code. These last simulations include perturbations seeded on all capsule interfaces and can use actual measured shell surfaces as initial conditions. 3-D simulations resolving Legendre modes up to two hundred on large capsule sectors have run through ignition and burn, and higher resolution simulations resolving as high as mode twelve hundred have been run to benchmark high-resolution 2-D runs. Finally, highly resolved 3-D simulations have also been run of the jet-type perturbation caused by the fill tube fitted to the capsule. These 3-D simulations compare well with the more typical 2-D simulations used in assessing the fill tube's impact on ignition. Coupled with the latest experimental inputs from NIF, our improving simulation capability yields a fuller and more accurate picture of NIF ignition capsule performance.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Optimization of the N ∥ Upshift in the DIII-D high field side lower hybrid current drive experiment

High field side lower hybrid current drive (LHCD) is one potential candidate for efficient non-inductive current drive in tokamak power plants, and the first test of this technology will occur on the DIII-D tokamak during the 2024 campaign. Previous LFS launch experiments operated in the multi-pass regime and relied on scrape-off layer interactions to close the spectral gap. In the DIII-D experiment, single-pass damping is achievable via an upshift in the parallel refractive index N ∥ caused by mode converting twice (slow → fast → slow). This mode conversion affects the ray trajectories and can lead to enhanced N ∥ upshift depending on where mode conversion occurs. Compared to multi-pass absorption experiments, the optimization of launched N ∥ and plasma parameters can be counter-intuitive: increased density may increase efficiency and smaller N ∥,launch tend to damp closer to the separatrix. A hard x-ray camera installed to measure the bremsstrahlung (50–250 keV) radiation from LHCD-generated fast electrons is capable of verifying the trends reporting in this paper through comparison to the ray-tracing/Fokker–Planck codes GENRAY/CQL3D.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

SPECTER: efficient evaluation of the spectral EMD

The Energy Mover’s Distance (EMD) has seen use in collider physics as a metric between events and as a geometric method of defining infrared and collinear safe observables. Recently, the Spectral Energy Mover’s Distance (SEMD) has been proposed as a more analytically tractable alternative to the EMD. In this work, we obtain a closed-form expression for the Riemannian-like p = 2 SEMD metric between events, eliminating the need to numerically solve an optimal transport problem. Additionally, we show how the SEMD can be used to define event and jet shape observables by minimizing the distance between events and parameterized energy flows (similar to the EMD), and we obtain closed-form expressions for several of these observables. We also present the Specter framework, an efficient and highly parallelized implementation of the SEMD metric and SEMD-derived shape observables as an analogue of the previously-introduced Shaper for EMD-based computations. We demonstrate that computing the SEMD with Specter can be up to a thousand times faster than computing the EMD with standard optimal transport libraries.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Multi-petascale highly efficient parallel supercomputer

A Multi-Petascale Highly Efficient Parallel Supercomputer of 100 petaflop-scale includes node architectures based upon System-On-a-Chip technology, where each processing node comprises a single Application Specific Integrated Circuit (ASIC). The ASIC nodes are interconnected by a five dimensional torus network that optimally maximize the throughput of packet communications between nodes and minimize latency. The network implements collective network and a global asynchronous network that provides global barrier and notification functions. Integrated in the node design include a list-based prefetcher. The memory system implements transaction memory, thread level speculation, and multiversioning cache that improves soft error rate at the same time and supports DMA functionality allowing for parallel processing message-passing.

97 MATHEMATICS AND COMPUTING↗

Multigrid Reduction in Time for Nonlinear Parabolic Problems: A Case Study

The need for parallelism in the time dimension is being driven by changes in computer architectures, where performance increases are now provided through greater concurrency, not faster clock speeds. This creates a bottleneck for sequential time marching schemes because they lack parallelism in the time dimension. Multigrid reduction in time (MGRIT) is an iterative procedure that allows for temporal parallelism by utilizing multigrid reduction techniques and a multilevel hierarchy of coarse time grids. MGRIT has been shown to be effective for linear problems, with speedups of up to 50 times. The goal of this work is the efficient solution of nonlinear problems with MGRIT, where efficiency is defined as achieving similar performance when compared to an equivalent linear problem. The benchmark nonlinear problem is the p-Laplacian, where p=4 corresponds to a well-known nonlinear diffusion equation and p=2 corresponds to the standard linear diffusion operator, our benchmark linear problem. The key difficulty encountered is that the nonlinear time-step solver becomes progressively more expensive on coarser time levels as the time-step size increases. To overcome such difficulties, multigrid research has historically targeted an accumulated body of experience regarding how to choose an appropriate solver for a specific problem type. To that end, this paper develops a library of MGRIT optimizations and modifications, most important an alternate initial guess for the nonlinear time-step solver and delayed spatial coarsening, that will allow many nonlinear parabolic problems to be solved with parallel scaling behavior comparable to the corresponding linear problem.

parareal↗

Machine Learning Based Parallel I/O Predictive Modeling: A Case Study on Lustre File Systems

Parallel I/O hardware and software infrastructure is a key contributor to performance variability for applications running on large-scale HPC systems. This variability confounds efforts to predict application performance for characterization, modeling, optimization, and job scheduling. We propose a modeling approach that improves predictive ability by explicitly treating the variability and by leveraging the sensitivity of application parameters on performance to group applications with similar characteristics. We develop a Gaussian process-based machine learning algorithm to model I/O performance and its variability as a function of application and file system characteristics. We demonstrate the effectiveness of the proposed approach using data collected from the Edison system at the National Energy Research Scientific Computing Center. The results show that the proposed sensitivity-based models are better at prediction when compared with application-partitioned or unpartitioned models. We highlight modeling techniques that are robust to the outliers that can occur in production parallel file systems. Using the developed metrics and modeling approach, we provide insights into the file system metrics that have a significant impact on I/O performance.

I/O performance variability↗

Cluster-to-cluster data transfer with data compression over wide-area networks

The recent emergence of ultra high-speed networks up to 100 Gb/s has posed numerous challenges and has led to many investigations on efficient protocols to saturate 100 Gb/s links. However, end-to-end data transfers involve many components, not only protocols, affecting overall transfer performance. These components include disk I/O subsystem, additional computation associated with data streams, and network adapters. For example, achievable bandwidth by TCP may not be implementable if disk I/O or CPU becomes a bottleneck in end-to-end data transfer. In this paper, we first model all the system components involved in end-to-end data transfer as a graph. We then formulate the problem whose goal is to achieve maximum data transfer throughput using parallel data flows. We also propose a variable data flow GridFFP XIO stack to improve data transfer with data compression. Our contributions lie in how to optimize data transfers considering all the system components involved rather than in accurately modeling all the system components involved. Our proposed formulations and solutions are evaluated through experiments on the ESnet 100G testbed and a wide-area cluster-to-cluster testbed. The experimental results on the ESnet 100G testbed show that our approach is several times faster than Globus Online-8 x faster for datasets with many 10 MB files and 3-4 x faster for other datasets of larger size files. The experimental results on the cluster-to-cluster testbed show that our variable data flow approach is up to 4 x faster than a normal cluster data transfer.

Disk-to-Disk Transfer↗

Rapid discovery and evolution of nanosensors containing fluorogenic amino acids

Binding-activated optical sensors are powerful tools for imaging, diagnostics, and biomolecular sensing. However, biosensor discovery is slow and requires tedious steps in rational design, screening, and characterization. Here we report on a platform that streamlines biosensor discovery and unlocks directed nanosensor evolution through genetically encodable fluorogenic amino acids (FgAAs). Building on the classical knowledge-based semisynthetic approach, we engineer ~15 kDa nanosensors that recognize specific proteins, peptides, and small molecules with up to 100-fold fluorescence increases and subsecond kinetics, allowing real-time and wash-free target sensing and live-cell bioimaging. An optimized genetic code expansion chemistry with FgAAs further enables rapid (~3 h) ribosomal nanosensor discovery via the cell-free translation of hundreds of candidates in parallel and directed nanosensor evolution with improved variant-specific sensitivities (up to ~250-fold) for SARS-CoV-2 antigens. Altogether, this platform could accelerate the discovery of fluorogenic nanosensors and pave the way to modify proteins with other non-standard functionalities for diverse applications.

Biosensors↗

A new architecture for fast ultrasound imaging

Some ultrasound imaging applications require high frame rate, for example 3D imaging and automated inspections of large components. Being the signal-processing throughput of the system the main bottleneck, parallel beamforming is required to achieve hundreds to thousands of images per second. Simultaneous A-scan line beamforming in all active channels is required to reach the intended high frame rate. To this purpose, a new parallel beamforming architecture that exploits the currently available processing resources available in state-of-the-art FPGAs is proposed. The work aims to get the optimal resource usage, high scalability and flexibility for different applications. To achieve these goals, the basic beamforming function is reformulated to be adapted to the DSP-cell architecture of state-of-the-art FPGAs. This allows performing simultaneous dynamic focusing on multiple A-scan lines. Some realistic examples are analyzed, evaluating resource requirements and maximum operating frequency. For example, a 128-channel system, with 128 scan lines and acquiring at 20 MSPS, can be built with 4 mid-range FPGAs, achieving up to 18000 frames per second, just limited by the maximum PRF. The gold standard Synthetic Transmit Aperture method (also called Total Focusing Method) can be carried out in real time at a processing rate of 140 high-resolution images per second (16 cm depth on steel)

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

GUNDAM: a toolkit for fast spatial correlation functions in galaxy surveys

ABSTRACT We describe the capabilities of a new software package to calculate two-point correlation functions (2PCFs) of large galaxy samples. The code can efficiently estimate 3D/projected/angular 2PCFs with a variety of statistical estimators and bootstrap errors, and is intended to provide a complete framework (including calculation, storage, manipulation, and plotting) to perform this type of spatial analysis with large redshift surveys. Gundam implements a very fast skip list/linked list algorithm that efficiently counts galaxy pairs and avoids the computation of unnecessary distances. It is several orders of magnitude faster than a naive pair counter, and matches or even surpass other advanced algorithms. The implementation is also embarrassingly parallel, making full use of multicore processors or large computational clusters when available. The software is designed to be flexible, user friendly and easily extensible, integrating optimized, well-tested packages already available in the astronomy community. Out of the box, it already provides advanced features such as custom weighting schemes, fibre collision corrections and 2D correlations. Gundam will ultimately provide an efficient toolkit to analyse the large-scale structure ‘buried’ in upcoming extremely large data sets generated by future surveys.

Donoso, E.↗

An Algorithmic and Software Pipeline for Very Large Scale Scientific Data Compression with Error Guarantees

Efficient data compression is becoming increasingly critical for storing scientific data because many scientific applications produce vast amounts of data. This paper presents an end-to-end algorithmic and software pipeline for data compression that guarantees both error bounds on primary data (PD) and derived data, known as Quantities of Interest (QoI).We demonstrate the effectiveness of the pipeline by compressing fusion data generated by a large-scale fusion code, XGC, which produces tens of petabytes of data in a single day. We demonstrate that the compression is conducted by setting aside computational resources known as staging nodes, and does not impact the simulation performance. For efficient parallel I/O, the pipeline uses ADIOS2, which many codes such as XGC already use for their parallel I/O. We show that our approach can compress the data by two orders of magnitude while guaranteeing high accuracy on both the PD and the QoIs. Further, the amount of resources required by compression is a few percent of the resources required by simulation while ensuring that the compression time for each stage is less than the corresponding simulation time.This pipeline consists of three main steps. The first step decomposes the data using domain decomposition into small subdomains. Each subdomain is then compressed independently to achieve a high level of parallelism. The second step uses existing techniques that guarantee error bounds on the primary data for each subdomain. The third step uses a post-processing optimization technique based on Lagrange multipliers to reduce the QoI errors for data corresponding to each subdomain. The Lagrange multipliers generated can be further quantized or truncated to increase the compression level. All of the above characteristics of our approach make it highly practical to apply on-the-fly compression while guaranteeing errors on QoIs that are critical to the scientists.

Banerjee, Tania↗