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 1,189 records · Page 66

Broadcasting a message in a parallel computer

Methods, systems, and products are disclosed for broadcasting a message in a parallel computer. The parallel computer includes a plurality of compute nodes connected together using a data communications network. The data communications network optimized for point to point data communications and is characterized by at least two dimensions. The compute nodes are organized into at least one operational group of compute nodes for collective parallel operations of the parallel computer. One compute node of the operational group assigned to be a logical root. Broadcasting a message in a parallel computer includes: establishing a Hamiltonian path along all of the compute nodes in at least one plane of the data communications network and in the operational group; and broadcasting, by the logical root to the remaining compute nodes, the logical root's message along the established Hamiltonian path.

97 MATHEMATICS AND COMPUTING↗

Refining Lucy Mission Delta-V During Spacecraft Design Using Trajectory Optimization Within High-Fidelity Monte Carlo Maneuver Analysis

Recent advances linking medium-fidelity trajectory optimization and high-fidelity trajectory propagation/maneuver design software with Monte Carlo maneuver analysis and parallel processing enabled realistic statistical delta-V estimation well before launch. Completing this high-confidence, refined statistical maneuver analysis early enabled release of excess delta-V margin for increased dry mass margin for the Lucy Jupiter Trojan flyby mission. By 3.3 years before launch, 16 of 34 TCMs had 1000 re-optimized trajectory design samples, yielding tens of m/s lower 99%-probability delta-V versus targeting maneuvers to one optimal trajectory. One year later, 1000 re-optimized samples of all deterministic maneuvers and subsequent flybys further lowered estimated delta-V.

Trojan↗

VINE-A NUMERICAL CODE FOR SIMULATING ASTROPHYSICAL SYSTEMS USING PARTICLES. II. IMPLEMENTATION AND PERFORMANCE CHARACTERISTICS

We continue our presentation of VINE. In this paper, we begin with a description of relevant architectural properties of the serial and shared memory parallel computers on which VINE is intended to run, and describe their influences on the design of the code itself. We continue with a detailed description of a number of optimizations made to the layout of the particle data in memory and to our implementation of a binary tree used to access that data for use in gravitational force calculations and searches for smoothed particle hydrodynamics (SPH) neighbor particles. We describe the modifications to the code necessary to obtain forces efficiently from special purpose 'GRAPE' hardware, the interfaces required to allow transparent substitution of those forces in the code instead of those obtained from the tree, and the modifications necessary to use both tree and GRAPE together as a fused GRAPE/tree combination. We conclude with an extensive series of performance tests, which demonstrate that the code can be run efficiently and without modification in serial on small workstations or in parallel using the OpenMP compiler directives on large-scale, shared memory parallel machines. We analyze the effects of the code optimizations and estimate that they improve its overall performance by more than an order of magnitude over that obtained by many other tree codes. Scaled parallel performance of the gravity and SPH calculations, together the most costly components of most simulations, is nearly linear up to at least 120 processors on moderate sized test problems using the Origin 3000 architecture, and to the maximum machine sizes available to us on several other architectures. At similar accuracy, performance of VINE, used in GRAPE-tree mode, is approximately a factor 2 slower than that of VINE, used in host-only mode. Further optimizations of the GRAPE/host communications could improve the speed by as much as a factor of 3, but have not yet been implemented in VINE. Finally, we find that although parallel performance on small problems may reach a plateau beyond which more processors bring no additional speedup, performance never decreases, a factor important for running large simulations on many processors with individual time steps, where only a small fraction of the total particles require updates at any given moment.

79 ASTRONOMY AND ASTROPHYSICS↗

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consists of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.

97 MATHEMATICS AND COMPUTING↗

Quadratic optimal cooperative control synthesis with flight control application

An optimal control-law synthesis approach is presented that involves simultaneous solution for two cooperating controllers operating in parallel. One controller's structure includes stochastic state estimation and linear feedback of the state estimates, while the other controller involves direct linear feedback of selected system output measurements. This structure is shown to be optimal under the constraint of linear feedback of system outputs in one controller. Furthermore, it is appropriate for flight control synthesis where the full-state optimal stochastic controller can be adjusted to be representative of an optimal control model of the human pilot in a stochastic regulation task. The method is experimentally verified in the case of the selection of pitch-damper gain for optimum pitch tracking, where optimum implies the best subjective pilot rating in the task. Finally, results from application of the method to synthesize a controller for a multivariable fighter aircraft are presented, and implications of the results of this method regarding the optimal plant dynamics for tracking are discussed.

Schmidt, D. K.↗

Active Learning for Metamaterial Optimization on HPC and QC Integrated Systems

Active learning algorithms, integrating machine learning, quantum computing and optics simulation in an iterative loop, offer a promising approach to optimizing metamaterials. However, these algorithms can face difficulties in optimizing highly complex structures due to computational limitations. High-performance computing (HPC) and quantum computing (QC) integrated systems can address these issues by enabling parallel computing. In this study, we develop an active learning algorithm working on HPC-QC integrated systems. We evaluate the performance of optimization processes within active learning (i.e., training a machine learning model, problem-solving with quantum computing, and evaluating optical properties through wave-optics simulation) for highly complex metamaterial cases. Our results showcase that utilizing multiple cores on the integrated system can significantly reduce computational time, thereby enhancing the efficiency of optimization processes. Therefore, we expect that leveraging HPC-QC integrated systems helps effectively tackle large-scale optimization challenges in general.

Kim, Seongmin↗

A Concept for Airborne Precision Spacing for Dependent Parallel Approaches

The Airborne Precision Spacing concept of operations has been previously developed to support the precise delivery of aircraft landing successively on the same runway. The high-precision and consistent delivery of inter-aircraft spacing allows for increased runway throughput and the use of energy-efficient arrivals routes such as Continuous Descent Arrivals and Optimized Profile Descents. This paper describes an extension to the Airborne Precision Spacing concept to enable dependent parallel approach operations where the spacing aircraft must manage their in-trail spacing from a leading aircraft on approach to the same runway and spacing from an aircraft on approach to a parallel runway. Functionality for supporting automation is discussed as well as procedures for pilots and controllers. An analysis is performed to identify the required information and a new ADS-B report is proposed to support these information needs. Finally, several scenarios are described in detail.

Barmore, Bryan E.↗

Controlled Selective CVD Growth of ZnO Nanowires Enabled by Mask‐Free Fabrication Approach using Aqueous Fe Catalytic Inks

Abstract Fabrication process that enables selective growth of vertically oriented zinc oxide (ZnO) nanowires (NWs) via chemical vapor deposition method and mask‐free patterning approach is reported. It is shown that synthesis of high‐quality ZnO nanowires in various architectures is achievable by optimizing the growth conditions and by precise patterning of catalytic ink precursors. Parallel direct‐write patterning method is utilized to fabricate arrays of different architectures on Si/SiO 2 substrates and directly on devices at preselected locations. The production of high‐quality, crystalline ZnO NWs is demonstrated using aqueous iron catalytic inks. The composition of the ink and the lateral size of the patterns deposited on substrates are shown to affect the resulting nanowires and thus, allowing to control the geometry (length and diameter) of the individual ZnO NWs in the patterned assemblies. The results indicate that our protocols are tailored to the fabrication of ZnO NWs with specific surface geometries and interface functionalities for variety of targeted device applications.

Alameri, Dheyaa↗

Evaluating the networking characteristics of the Cray XC-40 Intel Knights Landing-based Cori supercomputer at NERSC

There are many potential issues associated with deploying the Intel Xeon Phi™ (code named Knights Landing [KNL]) manycore processor in a large-scale supercomputer. One in particular is the ability to fully utilize the high-speed communications network, given that the serial performance of a Xeon Phi TM core is a fraction of a Xeon®core. In this paper, we take a look at the trade-offs associated with allocating enough cores to fully utilize the Aries high-speed network versus cores dedicated to computation, e.g., the trade-off between MPI and OpenMP. In addition, we evaluate new features of Cray MPI in support of KNL, such as internode optimizations. We also evaluate one-sided programming models such as Unified Parallel C. We quantify the impact of the above trade-offs and features using a suite of National Energy Research Scientific Computing Center applications.

97 MATHEMATICS AND COMPUTING↗

Asynchronous Richardson iterations: theory and practice

We consider asynchronous versions of the first- and second-order Richardson methods for solving linear systems of equations. These methods depend on parameters whose values are chosen a priori. We explore the parameter values that can be proven to give convergence of the asynchronous methods. This is the first such analysis for asynchronous second-order methods. We find that for the first-order method, the optimal parameter value for the synchronous case also gives an asynchronously convergent method. For the second-order method, the parameter ranges for which we can prove asynchronous convergence do not contain the optimal parameter values for the synchronous iteration. In practice, however, the asynchronous second-order iterations may still converge using the optimal parameter values, or parameter values close to the optimal ones, despite this result. We explore this behavior with a multithreaded parallel implementation of the asynchronous methods.

97 MATHEMATICS AND COMPUTING↗

The MPI_T events interface: An early evaluation and overview of the interface

Understanding the behavior of parallel applications that use the Message Passing Interface (MPI) is critical for optimizing communication performance. Performance tools for MPI currently rely on the PMPI Profiling Interface or the MPI Tool Information Interface, MPI_T, for portably collecting information for performance measurement and analysis. While tools using these interfaces have proven to be extremely valuable for performance tuning, these interfaces only provide synchronous information, i.e., when an MPI or an MPI_T function is called. There is currently no option for collecting information about asynchronous events from within the MPI library. Here, we propose a callback-driven interface for event notification from MPI implementations. Our approach is integrated in the existing MPI_T interface and provides a portable API for tools to discover and register for events of interest. We implement our MPI_T Events interface in Open MPI and demonstrate its functionality and usability with a small logging tool (MEL) as well as an early integration into the comprehensive measurement infrastructure Score-P.

97 MATHEMATICS AND COMPUTING↗

Development of a Reactive Force Field for Simulating Photoinitiated Acrylate Polymerization

Light-driven and photo-curable polymer based additive manufacturing (AM) has enormous potential due to its excellent resolution and precision. Acrylated radical chain-growth polymerized resins are widely used in photopolymer AM due to their fast kinetics, and often serve as a departure point for developing other resin materials for photopolymer-based AM technologies. For successful control of the photopolymer resins, the molecular basis of the acrylate free-radical polymerization has to be understood in detail. We present an optimized reactive force field (ReaxFF) for molecular dynamics (MD) simulations of acrylate polymer resins that captures radical polymerization thermodynamics and kinetics. The force field is trained against an extensive training set including density functional theory (DFT) calculations of reaction pathways along the radical polymerization from methyl acrylate to methyl butyrate, bond dissociation energies, and structures and partial charges of several molecules and radicals. We also found that it was critical to train the force field against an incorrect, nonphysical reaction pathway observed in simulations that used parameters not optimized for acrylate polymerization. As a result, the parameterization process utilizes a parallelized search algorithm, and the resulting model can describe polymer resin formation, crosslinking density, conversion rate, and residual monomers of the complex acrylate mixtures.

36 MATERIALS SCIENCE↗

Spatially Resolved Mapping of Three-Dimensional Molecular Orientations with ~2 nm Spatial Resolution through Tip-Enhanced Raman Scattering

We record local optical field images of silver nanocubes (75 nm) using tip-enhanced Raman (TER) spectral imaging. The images that we observe are consistent with several recent reports from our group, but here, we demonstrate sub-2 nm spatial resolution in local optical field nanoimaging under ambient laboratory conditions. This is achieved by scanning the substrate (nanocube on Si) relative to a 4-thiobenzonitrile (TBN)-functionalized Ag-coated TER probe. The spatial resolution that we obtain necessitates that only a few molecules govern the recorded optical response; molecular orientation becomes an important consideration in such measurements. We model the orientation through geometry optimization of a TBN molecule chemisorbed onto an Ag79 cluster (sphere with a ~1 nm diameter). Using the computed orientation of the cluster-bound molecule, we then model the optical response using formalism that accounts for the orientation of the molecule relative to vector components of the local optical fields. We find optimal agreement between experiment and theory. In effect, this work reveals the parallels between single-molecule Raman scattering and high-spatial-resolution TER spectroscopy, even when the images themselves cannot be used to visualize a single molecule in real space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Exaflops Biomedical Knowledge Graph Analytics

We are motivated by newly proposed methods for mining large-scale corpora of scholarly publications (e.g., full biomedical literature), which consists of tens of millions of papers spanning decades of research. In this setting, analysts seek to discover relationships among concepts. They construct graph representations from annotated text databases and then formulate the relationship-mining problem as an all-pairs shortest paths (APSP) and validate connective paths against curated biomedical knowledge graphs (e.g., Spoke). In this context, we present Coast (Exascale Communication-Optimized All-Pairs Shortest Path) and demonstrate 1.004 EF/s on 9,200 Frontier nodes (73,600 GCDs). We develop hyperbolic performance models (HYPERMOD), which guide optimizations and parametric tuning. The proposed Coast algorithm achieved the memory constant parallel efficiency of 99% in the single-precision tropical semiring. Looking forward, Coast will enable the integration of scholarly corpora like PubMed into the Spoke biomedical knowledge graph.

Kannan, Ramakrishnan {ramki}↗

SPEL: Software tool for Porting E3SM Land Model with OpenACC in a Function Unit Test Framework

Most high-end computers adopt hybrid architecture, porting a large-scale scientific code onto accelerators is necessary. The paper presents a generic method for porting large-scale scientific code onto accelerators using compiler directives within a modularized function unit test platform. We have implemented the method and designed a software tool (SPEL) to port the E3SM Land Model (ELM) onto the GPUs in the Summit computer. SPEL automatically generates GPU-ready test modules for all ELM functions, such as CanopyFlux, SoilTemperature, and EcosystemDynamics. SPEL breaks the ELM into a collection of standalone unit test programs for easy code verification and further performance improvement. We further optimize several ELM test modules with advanced techniques, including memory reduction, reconstructed parallel loops, and asynchronous GPU kernel launch. We hope our study will inspire new toolkit developments that expedite large-scale scientific code porting with compiler directives.

Schwartz, Peter↗

An agent-based deployment decision-support system for electric vehicle services

METS-R ADDSEVS simulator is a high fidelity, parallel, agent-based evacuation simulator for multi-modal energy-optimal trip scheduling in real-time (METS-R) at transportation hubs. It consists of two modules. The first one is the traffic simulator module; the second one is the high-performance computing (HPC) module. More details can be found at https://umnilab.github.io/METS-R_doc/.

Lei, Zengxiang↗