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 973 records · Page 54

Optimizing checkpoint data placement with guaranteed burst buffer endurance in large-scale hierarchical storage systems

Non-volatile devices, such as SSDs, will be an integral part of the deepening storage hierarchy on large-scale HPC systems. These devices can be on the compute nodes as part of a distributed burst buffer service or they can be external. Wherever they are located in the hierarchy, one critical design issue is the SSD endurance under the write-heavy workloads, such as the checkpoint I/O for scientific applications. For these environments, it is widely assumed that checkpoint operations can occur once every 60 min and for each checkpoint step as much as half of the system memory can be written out. Unfortunately, for large-scale HPC applications, the burst buffer SSDs can be worn out much more quickly given the extensive amount of data written at every checkpoint step. One possible solution is to control the amount of data written by reducing the checkpoint frequency. However, a direct effect caused by reduced checkpoint frequency is the increased vulnerability window of system failures and therefore potentially wasted computation time, especially for large-scale compute jobs.

Computer Science↗

Review of SPECT collimator selection, optimization, and fabrication for clinical and preclinical imaging

In single photon emission computed tomography, the choice of the collimator has a major impact on the sensitivity and resolution of the system. Traditional parallel-hole and fan-beam collimators used in clinical practice, for example, have a relatively poor sensitivity and subcentimeter spatial resolution, while in small-animal imaging, pinhole collimators are used to obtain submillimeter resolution and multiple pinholes are often combined to increase sensitivity. This paper reviews methods for production, sensitivity maximization, and task-based optimization of collimation for both clinical and preclinical imaging applications. New opportunities for improved collimation are now arising primarily because of (i) new collimator-production techniques and (ii) detectors with improved intrinsic spatial resolution that have recently become available. These new technologies are expected to impact the design of collimators in the future. The authors also discuss concepts like septal penetration, high-resolution applications, multiplexing, sampling completeness, and adaptive systems, and the authors conclude with an example of an optimization study for a parallel-hole, fan-beam, cone-beam, and multiple-pinhole collimator for different applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Hierarchical Parallelism in Finite Difference Analysis of Heat Conduction

Based on the concept of hierarchical parallelism, this research effort resulted in highly efficient parallel solution strategies for very large scale heat conduction problems. Overall, the method of hierarchical parallelism involves the partitioning of thermal models into several substructured levels wherein an optimal balance into various associated bandwidths is achieved. The details are described in this report. Overall, the report is organized into two parts. Part 1 describes the parallel modelling methodology and associated multilevel direct, iterative and mixed solution schemes. Part 2 establishes both the formal and computational properties of the scheme.

Padovan, Joseph↗

From Physics Model to Results: An Optimizing Framework for Cross-Architecture Code Generation

Starting from a high-level problem description in terms of partial differential equations using abstract tensor notation, the Chemora framework discretizes, optimizes, and generates complete high performance codes for a wide range of compute architectures. Chemora extends the capabilities of Cactus, facilitating the usage of large-scale CPU/GPU systems in an efficient manner for complex applications, without low-level code tuning. Chemora achieves parallelism through MPI and multi-threading, combining OpenMP and CUDA. Optimizations include high-level code transformations, efficient loop traversal strategies, dynamically selected data and instruction cache usage strategies, and JIT compilation of GPU code tailored to the problem characteristics. The discretization is based on higher-order finite differences on multi-block domains. Chemora's capabilities are demonstrated by simulations of black hole collisions. This problem provides an acid test of the framework, as the Einstein equations contain hundreds of variables and thousands of terms.

Blazewicz, Marek↗

Reconfigurable Model Execution in the OpenMDAO Framework

NASA's OpenMDAO framework facilitates constructing complex models and computing their derivatives for multidisciplinary design optimization. Decomposing a model into components that follow a prescribed interface enables OpenMDAO to assemble multidisciplinary derivatives from the component derivatives using what amounts to the adjoint method, direct method, chain rule, global sensitivity equations, or any combination thereof, using the MAUD architecture. OpenMDAO also handles the distribution of processors among the disciplines by hierarchically grouping the components, and it automates the data transfer between components that are on different processors. These features have made OpenMDAO useful for applications in aircraft design, satellite design, wind turbine design, and aircraft engine design, among others. This paper presents new algorithms for OpenMDAO that enable reconfigurable model execution. This concept refers to dynamically changing, during execution, one or more of: the variable sizes, solution algorithm, parallel load balancing, or set of variables-i.e., adding and removing components, perhaps to switch to a higher-fidelity sub-model. Any component can reconfigure at any point, even when running in parallel with other components, and the reconfiguration algorithm presented here performs the synchronized updates to all other components that are affected. A reconfigurable software framework for multidisciplinary design optimization enables new adaptive solvers, adaptive parallelization, and new applications such as gradient-based optimization with overset flow solvers and adaptive mesh refinement. Benchmarking results demonstrate the time savings for reconfiguration compared to setting up the model again from scratch, which can be significant in large-scale problems. Additionally, the new reconfigurability feature is applied to a mission profile optimization problem for commercial aircraft where both the parametrization of the mission profile and the time discretization are adaptively refined, resulting in computational savings of roughly 10% and the elimination of oscillations in the optimized altitude profile.

Hwang, John T.↗

Gyrokinetic toroidal simulations on leading multi- and manycore HPC systems

The gyrokinetic Particle-in-Cell (PIC) method is a critical computational tool enabling petascale fusion simulation re-search. In this work, we present novel multi- and manycore-centric optimizations to enhance performance of GTC, a PIC-based production code for studying plasma microtur-bulence in tokamak devices. Our optimizations encompass all six GTC sub-routines and include multi-level particle and grid decompositions designed to improve multi-node parallel scaling, particle binning for improved load balance, GPU acceleration of key subroutines, and memory-centric optimizations to improve single-node scaling and reduce memory utilization. The new hybrid MPI-OpenMP and MPI-OpenMP-CUDA GTC versions achieve up to a 2× speedup over the production Fortran code on four parallel systems - clusters based on the AMD Magny-Cours, Intel Nehalem-EP, IBM BlueGene/P, and NVIDIA Fermi architectures. Finally, strong scaling experiments provide insight into parallel scalability, memory utilization, and programmability trade-offs for large-scale gyrokinetic PIC simulations, while attaining a 1.6× speedup on 49,152 XE6 cores.

97 MATHEMATICS AND COMPUTING↗

A novel electron gun for inline MRI-linac configurations

Purpose: This work introduces a new electron gun geometry capable of robust functioning in the presence of a high strength external magnetic field for axisymmetric magnetic resonance imaging (MRI)-linac configurations. This allows an inline MRI-linac to operate without the need to isolate the linear accelerator (linac) using a magnetic shield. This MRI-linac integration approach not only leaves the magnet homogeneity unchanged but also provides the linac flexibility to move along the magnet axis of symmetry if the source to target distance needs to be adjusted. Methods: Simple electron gun geometry modifications of a Varian 600C electron gun are considered and solved in the presence of an external magnetic field in order to determine a set of design principles for the new geometry. Based on these results, a new gun geometry is proposed and optimized in the fringe field of a 0.5 T open bore MRI magnet (GE Signa SP). A computer model for the 6 MeV Varian 600C linac is used to determine the capture efficiency of the new electron gun-linac system in the presence of the fringe field of the same MRI scanner. The behavior of the new electron gun plus the linac system is also studied in the fringe fields of two other magnets, a 1.0 T prototype open bore magnet and a 1.5 T GE Conquest scanner. Results: Simple geometrical modifications of the original electron gun geometry do not provide feasible solutions. However, these tests show that a smaller transverse cathode diameter with a flat surface and a slightly larger anode diameter could alleviate the current loss due to beam interactions with the anode in the presence of magnetic fields. Based on these findings, an initial geometry resembling a parallel plate capacitor with a hole in the anode is proposed. The optimization procedure finds a cathode-anode distance of 5 mm, a focusing electrode angle of 5°, and an anode drift tube length of 17.1 mm. Also, the linac can be displaced with ±15 cm along the axis of the 0.5 T magnet without capture efficiency reduction below the experimental value in zero field. In this range of linac displacements, the electron beam generated by the new gun geometry is more effectively injected into the linac in the presence of an external magnetic field, resulting in approximately 20% increase of the target current compared to the original gun geometry behavior at zero field. The new gun geometry can generate and accelerate electron beams in external magnetic fields without current loss for fields higher than 0.11 T. The new electron-gun geometry is robust enough to function in the fringe fields of the other two magnets with a target current loss of no more than 16% with respect to the current obtained with no external magnetic fields. Conclusions: In this work, a specially designed electron gun was presented which can operate in the presence of axisymmetric strong magnetic fringe fields of MRI magnets. Computer simulations show that the electron gun can produce high quality beams which can be injected into a straight through linac such as Varian 600C and accelerated with more efficiency in the presence of the external magnetic fields. Also, the new configuration allows linac displacements along the magnet axis in a range equal to the diameter of the imaging spherical volume of the magnet under consideration. The new electron gun-linac system can function in the fringe field of a MRI magnet if the field strength at the cathode position is higher than 0.11 T. The capture efficiency of the linac depends on the magnetic field strength and the field gradient. The higher the gradient the better the capture efficiency. The capture efficiency does not degrade more than 16%.

43 PARTICLE ACCELERATORS↗

Execution time supports for adaptive scientific algorithms on distributed memory machines

Optimizations are considered that are required for efficient execution of code segments that consists of loops over distributed data structures. The PARTI (Parallel Automated Runtime Toolkit at ICASE) execution time primitives are designed to carry out these optimizations and can be used to implement a wide range of scientific algorithms on distributed memory machines. These primitives allow the user to control array mappings in a way that gives an appearance of shared memory. Computations can be based on a global index set. Primitives are used to carry out gather and scatter operations on distributed arrays. Communications patterns are derived at runtime, and the appropriate send and receive messages are automatically generated.

Berryman, Harry↗

Execution time support for scientific programs on distributed memory machines

Optimizations are considered that are required for efficient execution of code segments that consists of loops over distributed data structures. The PARTI (Parallel Automated Runtime Toolkit at ICASE) execution time primitives are designed to carry out these optimizations and can be used to implement a wide range of scientific algorithms on distributed memory machines. These primitives allow the user to control array mappings in a way that gives an appearance of shared memory. Computations can be based on a global index set. Primitives are used to carry out gather and scatter operations on distributed arrays. Communications patterns are derived at runtime, and the appropriate send and receive messages are automatically generated.

Berryman, Harry↗

Aerodynamic optimization studies on advanced architecture computers

The approach to carrying out multi-discipline aerospace design studies in the future, especially in massively parallel computing environments, comprises of choosing (1) suitable solvers to compute solutions to equations characterizing a discipline, and (2) efficient optimization methods. In addition, for aerodynamic optimization problems, (3) smart methodologies must be selected to modify the surface shape. In this research effort, a 'direct' optimization method is implemented on the Cray C-90 to improve aerodynamic design. It is coupled with an existing implicit Navier-Stokes solver, OVERFLOW, to compute flow solutions. The optimization method is chosen such that it can accomodate multi-discipline optimization in future computations. In the work , however, only single discipline aerodynamic optimization will be included.

Chawla, Kalpana↗

Helicopter trim analysis by shooting and finite element methods with optimally damped Newton iterations

Helicopter trim settings of periodic initial state and control inputs are investigated for convergence of Newton iteration in computing the settings sequentially and in parallel. The trim analysis uses a shooting method and a weak version of two temporal finite element methods with displacement formulation and with mixed formulation of displacements and momenta. These three methods broadly represent two main approaches of trim analysis: adaptation of initial-value and finite element boundary-value codes to periodic boundary conditions, particularly for unstable and marginally stable systems. In each method, both the sequential and in-parallel schemes are used, and the resulting nonlinear algebraic equations are solved by damped Newton iteration with an optimally selected damping parameter. The impact of damped Newton iteration, including earlier-observed divergence problems in trim analysis, is demonstrated by the maximum condition number of the Jacobian matrices of the iterative scheme and by virtual elimination of divergence. The advantages of the in-parallel scheme over the conventional sequential scheme are also demonstrated.

Achar, N. S.↗

Parallelizing Single Source Shortest Path with OpenSHMEM

Single Source Shortest Path (SSSP) is one of the widely occurring graph problems where the paths are discovered from an origin vertex to all other vertices in the graph. In this paper, we discuss our experience parallelizing SSSP using OpenSHMEM. We start with the serial Dijkstra and Bellman-Ford algorithms, parallelize these algorithms, and adapt them to the Partitioned Global Address Space (PGAS) programming model. We implement the parallel algorithms using OpenSHMEM and introduce a series of optimizations to achieve higher scaling and performance characteristics. The implementation is evaluated on Titan with various graphs including synthetic Recursive Matrix (R-MAT) and small-world network graphs as well as real-world graphs from Facebook, Twitter, LiveJournal, and the road maps of California and Texas.

97 MATHEMATICS AND COMPUTING↗

Mechanisms of nickel sorption by a bacteriogenic birnessite

A synergistic experimental-computational approach was used to study the molecular-scale mechanisms of Ni sorption at varying loadings and at pH 6-8 on the biogenic hexagonal birnessite produced by Pseudomonas putida GB-1. We found that Ni is scavenged effectively by bacterial biomass-birnessite assemblages. At surface excess values below 0.18 mol Ni kg{sup -1} sorbent (0.13 mol Ni mol{sup -1} Mn), the biomass component of the sorbent did not interfere with Ni sorption on mineral sites. Extended X-ray absorption fine structure (EXAFS) spectra showed two dominant coordination environments: Ni bound as a triple-corner-sharing (Ni-TCS) complex at vacancy sites and Ni incorporated (Ni-inc) into the MnO{sub 2} sheet, with the latter form of Ni favored at high sorptive concentrations and decreased proton activity. In parallel to our spectral analysis, first-principles geometry optimizations based on density functional theory (DFT) were performed to investigate the structure of Ni surface complexes at vacancy sites. Excellent agreement was achieved between EXAFS- and DFT-derived structural parameters for Ni-TCS and Ni-inc. Reaction-path calculations revealed a pH-dependent energy barrier associated with the transition from Ni-TCS to Ni-inc. Our results are consistent with the rate-limited incorporation of Ni at vacancy sites in our sorption samples, but near-equilibrium state of Ni in birnessite phases found in nodule samples. This study thus provides direct and quantitative evidence of the factors governing the occurrence of Ni adsorption versus Ni incorporation in biogenic hexagonal birnessite, a key mineral in the terrestrial manganese cycle.

54 ENVIRONMENTAL SCIENCES↗

Distributed memory, GPU accelerated Fock construction for hybrid, Gaussian basis density functional theory

With the growing reliance of modern supercomputers on accelerator-based architecture such a graphics processing units (GPUs), the development and optimization of electronic structure methods to exploit these massively parallel resources has become a recent priority. While significant strides have been made in the development GPU accelerated, distributed memory algorithms for many modern electronic structure methods, the primary focus of GPU development for Gaussian basis atomic orbital methods has been for shared memory systems with only a handful of examples pursing massive parallelism. Here in this work, we present a set of distributed memory algorithms for the evaluation of the Coulomb and exact exchange matrices for hybrid Kohn–Sham DFT with Gaussian basis sets via direct density-fitted (DF-J-Engine) and seminumerical (sn-K) methods, respectively. The absolute performance and strong scalability of the developed methods are demonstrated on systems ranging from a few hundred to over one thousand atoms using up to 128 NVIDIA A100 GPUs on the Perlmutter supercomputer.

97 MATHEMATICS AND COMPUTING↗

Automatic Detection and Evaluation of Solar Cell Micro-Cracks in Electroluminescence Images Using Matched Filters

A method for detecting micro-cracks in solar cells using two dimensional matched filters was developed, derived from the electroluminescence intensity profile of typical micro-cracks. We describe the image processing steps to obtain a binary map with the location of the micro-cracks. Finally, we show how to automatically estimate the total length of each micro-crack from these maps, and propose a method to identify severe types of micro-cracks, such as parallel, dendritic, and cracks with multiple orientations. With an optimized threshold parameter, the technique detects over 90 % of cracks larger than 3 cm in length. The method shows great potential for quantifying micro-crack damage after manufacturing or module transportation for the determination of a module quality criterion for cell cracking in photovoltaic modules.

14 SOLAR ENERGY↗

Progress and R/D challenges for FCC-ee SRF

The FCC-ee machines present a huge challenge for the RF systems, which need to be adapted to very diverse beam conditions going from moderate energy and high current for the Z machine to high energy and low beam current for the ttbar. This inverse scaling results naturally from a fixed budget for the synchrotron radiation, which the SRF cavities need to compensate. A global solution was elaborated for the FCC Conceptual Design Report (Abada in Eur Phys J Spec Top 228):261–623, 2019), and is referred here as the baseline. Recently, further studies have led to a new optimized baseline, still based on traditional elliptical cavities. In parallel, a novel concept, named the Slotted Waveguide ELLiptical (SWELL), was proposed with the potential of greatly simplified logistics and reduced costs. Under several aspects, all these changes call for enhanced performance of the RF systems. A vigorous R&D program has therefore continued since the publication of the CDR, with the aim of pushing the performance and demonstrating the feasibility of a more advanced baseline and, more recently, of the SWELL option. The progress and challenges of this ambitious program were presented in the dedicated SRF sessions at FCC week 2022 and are summarized in this paper.

47 OTHER INSTRUMENTATION↗

Galactos: computing the anisotropic 3-point correlation function for 2 billion galaxies

The nature of dark energy and the complete theory of gravity are two central questions currently facing cosmology. A vital tool for addressing them is the 3-point correlation function (3PCF), which probes deviations from a spatially random distribution of galaxies. However, the 3PCF's formidable computational expense has prevented its application to astronomical surveys comprising millions to billions of galaxies. We present Galactos, a high-performance implementation of a novel, O( N 2 ) algorithm that uses a load-balanced k-d tree and spherical harmonic expansions to compute the anisotropic 3PCF. Our implementation is optimized for the Intel Xeon Phi architecture, exploiting SIMD parallelism, instruction and thread concurrency, and significant L1 and L2 cache reuse, reaching 39% of peak performance on a single node. Galactos scales to the full Cori system, achieving 9.8 PF (peak) and 5.06 PF (sustained) across 9636 nodes, making the 3PCF easily computable for all galaxies in the observable universe.

79 ASTRONOMY AND ASTROPHYSICS↗

PyBioNetFit

Systems biology models written in the BioNetGen language often contain parameters that must be fit based on experimental data. PyBioNetFit is a software tool designed to fit parameters of BioNetGen models. The user is expected to provide a BioNetGen model that contains unknown parameters, along with one or more text files containing experimental data. PyBioNetFit will perform a series of calls to the BioNetGen simulator using different parameter sets, to identify the parameter set that best fits the data. The parameter search is dictated by the user's choice of one of several metaheuristic optimization algorithms, including differential evolution, particle swarm optimization, scatter search, and simulated annealing. The software supports parallelized computing on multi-core computers and on computing clusters. We expect this software to be a useful tool for researchers designing BioNetGen models in collaboration with experimentalists.

Mitra, Eshan↗