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 613 records · Page 34

...And Eat it Too: High Read Performance in Write-Optimized HPC I/O Middleware File Formats

As HPC applications run on increasingly high process counts on larger and larger machines, both the frequency of checkpoints needed for fault tolerance and the resolution and size of Data Analysis Dumps are expected to increase proportionally. In order to maintain an acceptable ratio of time spent performing useful computation work to time spent performing I/O, write bandwidth to the underlying storage system must increase proportionally to this increase in the checkpoint and computation size. Unfortunately, popular scientific self-describing file formats such as netCDF and HDF5 are designed with a focus on portability and flexibility. Extra care and careful crafting of the output structure and API calls is required to optimize for write performance using these APIs. To provide sufficient write bandwidth to continue to support the demands of scientific applications, the HPC community has developed a number of I/O middleware layers, that structure output into write-optimized file formats. However, the obvious concern with any write optimized file format would be a corresponding penalty on reads. In the log-structured filesystem, for example, a file generated by random writes could be written efficiently, but reading the file back sequentially later would result in very poor performance. Simulation results require efficient read-back for visualization and analytics, and though most checkpoint files are never used, the efficiency of a restart is very important in the face of inevitable failures. The utility of write speed improving middleware would be greatly diminished if it sacrificed acceptable read performance. In this paper we examine the read performance of two write-optimized middleware layers on large parallel machines and compare it to reading data natively in popular file formats. The two I/O middleware layer examined in this paper are the Adaptable IO System (ADIOS), a library-based approach developed at Oak Ridge National Laboratory to provide a high-level IO API that can be used in place of netCDF or HDF5 to do much more aggressive write-behind and efficient reordering of data locations within the file; and the Parallel Log-structured Filesystem (PLFS), a stackable FUSE filesystem approach developed at Los Alamos National Laboratory that decouples concurrent writes to improve the speed of checkpoints. Since ADIOS is an I/O componentization that affords selection of different I/O methods at or during runtime, through a single API, users can have access to MPI-IO, Posix-IO, HDF5, netCDF, and staging methods. The ADIOS BP file format is a new log-file format that has a superset of the features of both HDF5 and netCDF, but is designed to be portable and flexible while being optimized for writing. PLFS, on the other hand, is mounted as a stackable filesystem on top of an existing parallel filesystem. Reads or writes to the PLFS filesystem are transparently translated into operations on per-process log files stored in the underlying parallel filesystem. Since PLFS performs this translation without application modification, users can write in HDF5, netCDF, or app-specific file formats and PLFS will store the writes in a set of efficiently written log-formatted files, while presenting the user with a logical 'flat' file on reads. Despite their different approaches, the commonality behind both of these middleware systems is that they both write to a log file format. As shown in previous publications, writes are fully optimized in both systems, sometimes resulting in 100x improvements over writing data in popular file formats. But as mentioned above, writing is only one part of the story. In this paper we examine the read performance of our middleware layers on large parallel machines and compare these to reading data either natively or from other popular file formats. We compare the reading performance in two different scenarios: (1) Reading back restarts from the same number of processors as wrote the data and (2) Reading back restart data from a different number of processors. We observe that not only can write-optimized I/O middleware be built to not penalize read speeds, but for important workloads, techniques that improve write performance can, perhaps counterintuitively, improve read speeds over reading from a contiguously organized file format. In the remainder of this paper, we investigate this further through case studies of PLFS and ADIOS on simulation checkpoint restarts.

99 GENERAL AND MISCELLANEOUS↗

High-Level Synthesis of Irregular Applications: A Case Study on Influence Maximization

The Influence Maximization problem is the problem of identifying a small cohort of actors from a broader population that, when initially activated in a diffusion process, are expected to result in a large number of activations in the population. While the problem is known to be NP-hard, several approximation algorithms have been devised by leveraging its submodular structure. While these algorithms are theoretically efficient, they are computationally very expensive in practice. This work advances the current state-of-the-art parallelization scheme for the IMM algorithm by devising the adoption of custom hardware accelerators implemented on FPGAs by leveraging High Level Synthesis from OpenCL. We study the performance of our proposed approach by exploring optimizations tailored at improving the parallel efficiency of the accelerators and highlight their effects and limitations in accelerating complex graph analytic applications. Our experimental evaluation shows that FPGA acceleration can improve the performance of the LT diffusion model up to 1.72x for the entire application and up to 2.90x for its most important kernel with respect to a CPU only parallel execution. The FPGA acceleration of the LT model shows also a 1.54x reduction in energy consumption when compared to a parallel CPU only run.

Neff, Reece W.↗

Wakefield Computations for the CLIC PETS using the Parallel Finite Element Time-Domain Code T3P

In recent years, SLAC's Advanced Computations Department (ACD) has developed the high-performance parallel 3D electromagnetic time-domain code, T3P, for simulations of wakefields and transients in complex accelerator structures. T3P is based on advanced higher-order Finite Element methods on unstructured grids with quadratic surface approximation. Optimized for large-scale parallel processing on leadership supercomputing facilities, T3P allows simulations of realistic 3D structures with unprecedented accuracy, aiding the design of the next generation of accelerator facilities. Applications to the Compact Linear Collider (CLIC) Power Extraction and Transfer Structure (PETS) are presented.

43 PARTICLE ACCELERATORS↗

An improved multilevel optimization approach for the design of complex engineering systems

Multilevel optimization methods are being considered for the design of complex systems on distributed networks of computers or even parallel processors. An obstacle to the use of multilevel methods is that they can be computationally expensive because of the cycling necessary to account for the coupling between the subproblems. This research effort aims at increasing the efficiency of multilevel optimization by adapting two techniques that are widely used in conventional one-level optimization: constraint approximation and temporary constraint deletion. These improvements are implemented and tested on three-, ten- and 52-bar planar truss designs. The results show that for larger problems (approximately 100 design variables and larger), the cost of analysis dominates the total cost so that multilevel optimization is no more expensive than one-level optimization. If parallel processing is used or the analysis process itself is decomposed, then multilevel optimization stands to become more economical than one-level optimization.

Barthelemy, J.-F. M.↗

Noise-aware optimization in nominally identical manufacturing and measuring systems for high-throughput parallel workflows

Device-to-device variability in experimental noise critically impacts reproducibility, especially in automated, high-throughput systems like additive manufacturing farms. While manageable in small labs, such variability can escalate into serious risks at larger scales, such as architectural 3D printing, where noise may cause structural or economic failures. This contribution presents a noise-aware decision-making algorithm that quantifies and models device-specific noise profiles to manage variability adaptively. It uses distributional analysis and pairwise divergence metrics with clustering to choose between single-device and robust multi-device Bayesian optimization strategies. Unlike conventional methods that assume homogeneous devices or enforce generic robustness, the proposed framework explicitly determines whether shared optimization across devices is appropriate based on the degree of inter-device noise heterogeneity. This enables improved performance, reproducibility, and efficiency. An experimental case study involving three nominally identical 3D printers (same brand, model, and close serial numbers) demonstrates reduced redundancy, lower resource usage, and improved reliability, along with improved convergence stability and solution quality through the selection of the appropriate optimization strategy based on the degree of inter-device noise heterogeneity. Overall, this framework establishes a general approach for precision- and resource-aware optimization in scalable, automated experimental platforms, demonstrated here on a representative multi-device 3D printing case study.

Schenk, Christina↗

Optimal quantum learning of a unitary transformation

We address the problem of learning an unknown unitary transformation from a finite number of examples. The problem consists in finding the learning machine that optimally emulates the examples, thus reproducing the unknown unitary with maximum fidelity. Learning a unitary is equivalent to storing it in the state of a quantum memory (the memory of the learning machine) and subsequently retrieving it. We prove that, whenever the unknown unitary is drawn from a group, the optimal strategy consists in a parallel call of the available uses followed by a 'measure-and-rotate' retrieving. Differing from the case of quantum cloning, where the incoherent 'measure-and-prepare' strategies are typically suboptimal, in the case of learning the 'measure-and-rotate' strategy is optimal even when the learning machine is asked to reproduce a single copy of the unknown unitary. We finally address the problem of the optimal inversion of an unknown unitary evolution, showing also in this case the optimality of the 'measure-and-rotate' strategies and applying our result to the optimal approximate realignment of reference frames for quantum communication.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

High Speed Civil Transport Design Using Collaborative Optimization and Approximate Models

The design of supersonic aircraft requires complex analysis in multiple disciplines, posing, a challenge for optimization methods. In this thesis, collaborative optimization, a design architecture developed to solve large-scale multidisciplinary design problems, is applied to the design of supersonic transport concepts. Collaborative optimization takes advantage of natural disciplinary segmentation to facilitate parallel execution of design tasks. Discipline-specific design optimization proceeds while a coordinating mechanism ensures progress toward an optimum and compatibility between disciplinary designs. Two concepts for supersonic aircraft are investigated: a conventional delta-wing design and a natural laminar flow concept that achieves improved performance by exploiting properties of supersonic flow to delay boundary layer transition. The work involves the development of aerodynamics and structural analyses, and integration within a collaborative optimization framework. It represents the most extensive application of the method to date.

Manning, Valerie Michelle↗

Monte Carlo calculations of electron beam quality conversion factors for several ion chamber types

Purpose: To provide a comprehensive investigation of electron beam reference dosimetry using Monte Carlo simulations of the response of 10 plane-parallel and 18 cylindrical ion chamber types. Specific emphasis is placed on the determination of the optimal shift of the chambers’ effective point of measurement (EPOM) and beam quality conversion factors. Methods: The EGSnrc system is used for calculations of the absorbed dose to gas in ion chamber models and the absorbed dose to water as a function of depth in a water phantom on which cobalt-60 and several electron beam source models are incident. The optimal EPOM shifts of the ion chambers are determined by comparing calculations of R{sub 50} converted from I{sub 50} (calculated using ion chamber simulations in phantom) to R{sub 50} calculated using simulations of the absorbed dose to water vs depth in water. Beam quality conversion factors are determined as the calculated ratio of the absorbed dose to water to the absorbed dose to air in the ion chamber at the reference depth in a cobalt-60 beam to that in electron beams. Results: For most plane-parallel chambers, the optimal EPOM shift is inside of the active cavity but different from the shift determined with water-equivalent scaling of the front window of the chamber. These optimal shifts for plane-parallel chambers also reduce the scatter of beam quality conversion factors, k{sub Q}, as a function of R{sub 50}. The optimal shift of cylindrical chambers is found to be less than the 0.5 r{sub cav} recommended by current dosimetry protocols. In most cases, the values of the optimal shift are close to 0.3 r{sub cav}. Values of k{sub ecal} are calculated and compared to those from the TG-51 protocol and differences are explained using accurate individual correction factors for a subset of ion chambers investigated. High-precision fits to beam quality conversion factors normalized to unity in a beam with R{sub 50} = 7.5 cm (k{sub Q}{sup ′}) are provided. These factors avoid the use of gradient correction factors as used in the TG-51 protocol although a chamber dependent optimal shift in the EPOM is required when using plane-parallel chambers while no shift is needed with cylindrical chambers. The sensitivity of these results to parameters used to model the ion chambers is discussed and the uncertainty related to the practical use of these results is evaluated. Conclusions: These results will prove useful as electron beam reference dosimetry protocols are being updated. The analysis of this work indicates that cylindrical ion chambers may be appropriate for use in low-energy electron beams but measurements are required to characterize their use in these beams.

07 ISOTOPE AND RADIATION SOURCES↗

Parallel algorithm for dominant points correspondences in robot binocular stereo vision

This paper presents an algorithm to find the correspondences of points representing dominant feature in robot stereo vision. The algorithm consists of two main steps: dominant point extraction and dominant point matching. In the feature extraction phase, the algorithm utilizes the widely used Moravec Interest Operator and two other operators: the Prewitt Operator and a new operator called Gradient Angle Variance Operator. The Interest Operator in the Moravec algorithm was used to exclude featureless areas and simple edges which are oriented in the vertical, horizontal, and two diagonals. It was incorrectly detecting points on edges which are not on the four main directions (vertical, horizontal, and two diagonals). The new algorithm uses the Prewitt operator to exclude featureless areas, so that the Interest Operator is applied only on the edges to exclude simple edges and to leave interesting points. This modification speeds-up the extraction process by approximately 5 times. The Gradient Angle Variance (GAV), an operator which calculates the variance of the gradient angle in a window around the point under concern, is then applied on the interesting points to exclude the redundant ones and leave the actual dominant ones. The matching phase is performed after the extraction of the dominant points in both stereo images. The matching starts with dominant points in the left image and does a local search, looking for corresponding dominant points in the right image. The search is geometrically constrained the epipolar line of the parallel-axes stereo geometry and the maximum disparity of the application environment. If one dominant point in the right image lies in the search areas, then it is the corresponding point of the reference dominant point in the left image. A parameter provided by the GAV is thresholded and used as a rough similarity measure to select the corresponding dominant point if there is more than one point the search area. The correlation is used as a final decision tool when there is still more than one point in the search area. If there is no dominant point in the search area of if the points in the search area are below a correlation threshold, then the dominant point in the reference image is occluded and can not be corresponded. The algorithm has been modeled, implemented and shown to be fast, robust and parallel. The parallelism is created from three main features: locality of the operators; a memory optimization scheme; and the ability to fully parallelize the extraction phase which is the most computational intensive task in the algorithm. The last feature is achieved by performing the extraction phase on the two images simultaneously.

Al-Tammami, A.↗

PANDORA: A Parallel Dendrogram Construction Algorithm for Single Linkage Clustering on GPU

This paper introduces Pandora, a parallel algorithm for computing dendrograms, the hierarchical cluster trees for single linkage clustering (SLC). Current parallel approaches construct dendrograms by partitioning a minimum spanning tree and removing edges. However, they struggle with skewed, hard-to-parallelize real-world dendrograms. Consequently, computing dendrograms is the sequential bottleneck in HDBSCAN*[21], a popular SLC variant. Pandora uses recursive tree contraction to address this limitation. Pandora contracts nodes to construct progressively smaller trees. It computes the smallest contracted dendrogram and expands it by inserting contracted edges. This recursive strategy is highly parallel, skew-independent, work-optimal, and well-suited for GPUs and multicores. We develop a performance portable implementation of Pandora in Kokkos[31] and evaluate its performance on multicore CPUs and multi-vendor GPUs (e.g., Nvidia, AMD) for dendrogram construction in HDBSCAN*. Multithreaded Pandora is 2.2x faster than the current best-multithreaded implementation. Our GPU version achieves 6-20x speedup on AMD GPUs and 10-37x on NVIDIA GPUs over multithreaded Pandora. Pandora removes HDBSCAN*’s sequential bottleneck, greatly boosting efficiency, particularly with GPUs.

Sao, Piyush↗

State of the art in electromagnetic modeling for the Compact Linear Collider

SLAC's Advanced Computations Department (ACD) has developed the parallel 3D electromagnetic time-domain code T3P for simulations of wakefields and transients in complex accelerator structures. T3P is based on state-of-the-art Finite Element methods on unstructured grids and features unconditional stability, quadratic surface approximation and up to 6th-order vector basis functions for unprecedented simulation accuracy. Optimized for large-scale parallel processing on leadership supercomputing facilities, T3P allows simulations of realistic 3D structures with fast turn-around times, aiding the design of the next generation of accelerator facilities. Applications include simulations of the proposed two-beam accelerator structures for the Compact Linear Collider (CLIC) - wakefield damping in the Power Extraction and Transfer Structure (PETS) and power transfer to the main beam accelerating structures are investigated.

43 PARTICLE ACCELERATORS↗

Performance Enhancements for the Lattice-Boltzmann Solver in the LAVA Framework

Performance enhancements in NASA's recently developed Lattice Boltzmann solver within the Launch Ascent and Vehicle Aerodynamics (LAVA) framework are presented. Two key algorithmic developments are highlighted. A coarse-fine interface treatment that discretely conserves mass and momentum has been implemented and successfully verified and validated. Code optimizations targeting improved serial and parallel performance were presented. For a simple turbulent Taylor-Green Vortex problem, we were able to demonstrate a 2.3 times speedup over the baseline code for a single Skylake-SP node containing 40 physical cores, and a 2.14 times speedup for 64 nodes containing 2560 physical cores. In addition, we were able to show that the optimizations enabled us to scale the code almost perfectly to 20480 physical cores where, including ghost cells, the problem size was 10 billion cells.

Barad, Michael↗

Performance Enhancements for the Lattice-Boltzmann Solver in the LAVA Framework

Performance enhancements in NASA's recently developed Lattice Boltzmann solver within the Launch Ascent and Vehicle Aerodynamics (LAVA) framework are presented. Two key algorithmic developments are highlighted. A coarse-fine interface treatment that discretely conserves mass and momentum has been implemented and successfully verified and validated. Code optimizations targeting improved serial and parallel performance were presented. For a simple turbulent Taylor-Green Vortex problem, we were able to demonstrate a 2.3 times speedup over the baseline code for a single Skylake-SP node containing 40 physical cores, and a 2.14 times speedup for 64 nodes containing 2560 physical cores. In addition, we were able to show that the optimizations enabled us to scale the code almost perfectly to 20480 physical cores where, including ghost cells, the problem size was 10 billion cells.

LAVA↗

The optimization of a DC injector for the Energy Recovery Linac upgrade to APS

An energy recovery linac based light source is a potential revolutionary upgrade to the Advanced Photon Source (APS) at Argonne National Laboratory. The concept relies on several key research areas, one of which is the generation of ultra-low emittance, high-average-current electron beams. In this paper, we present our investigation of a dc-gun-based system for ultra-low emittance bunches in the 20 pC range. A parallel multi-objective numerical optimization is performed in multi-parameter space. Parameters varied include experimentally feasible drive-laser shapes, the DC gun voltage, the thermal energy of the emitted photo-electrons and other electric or magnetic field strengths, RF cavity phase etc. Our goal is to deliver a {approx}10 MeV, 20 pC bunch at the entrance of the linac with an emittance of 0.1 {micro}m or lower, rms bunch length of 2 {approx} 3 ps, and energy spread no larger than 140 keV. We present the machine parameters needed to generate such an injector beam, albeit without a merger.

43 PARTICLE ACCELERATORS↗

Bayesian Optimized Deep Ensemble for Uncertainty Quantification of Deep Neural Networks: a System Safety Case Study on Sodium Fast Reactor Thermal Stratification Modeling

Deep neural networks (DNNs) are increasingly important to scientific computing and engineering system simulations. Accurate uncertainty quantification (UQ) for DNNs is critical in safety-sensitive engineering domains. Traditional Deep Ensemble (DE) methods, while easy to implement, frequently suffer from poorly calibrated uncertainty estimates and limited predictive accuracy due to reliance on fixed architectures with varied weight initializations. To address these issues, we introduce a workflow that combines Bayesian Optimization (BO) and DE. The workflow is modular, scalable, and integrates parallel BO initialized with Sobol sequences to individually optimize the hyperparameters of each ensemble member. This method enhances ensemble diversity, improves predictive accuracy, and provides reliable uncertainty estimates. We evaluate the proposed BODE approach in a sodium fast reactor thermal stratification modeling case study, where we used a densely connected convolutional neural network to predict turbulent viscosity during the reactor transient with consideration of data noise. We benchmark its performance against several optimization approaches, including baseline deep ensemble, evolutionary algorithm-optimized ensemble, ensemble formed via random search combined with greedy selection, and a BO ensemble using random initialization. Here, our results demonstrate superior performance of the developed BODE approach. In noise-free scenarios, BODE notably reduces incorrect aleatoric uncertainty and significantly enhances predictive accuracy. Under conditions of 5% and 10% Gaussian noise, BODE adaptively quantifies uncertainty proportional to data noise, achieving up to an 80% reduction in root mean square error compared to baseline methods and producing well-calibrated prediction intervals.

Bayesian optimization↗

Methodology and method and appartus for signaling with capacity optimized constellations

Communication systems are described that use geometrically shaped constellations that have increased capacity compared to conventional constellations operating within a similar SNR band. In several embodiments, the geometrically shaped is optimized based upon a capacity measure such as parallel decoding capacity or joint capacity. In many embodiments, a capacity optimized geometrically shaped constellation can be used to replace a conventional constellation as part of a firmware upgrade to transmitters and receivers within a communication system. In a number of embodiments, the geometrically shaped constellation is optimized for an Additive White Gaussian Noise channel or a fading channel.

Barsoum, Maged F.↗