Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel computing algorithms”

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 1,315 records · Page 73

Tokamak-independent software analysis suite for multi-spectral line-polarization MSE diagnostics

A tokamak-independent analysis suite has been developed to process data from Motional Stark Effect (mse) diagnostics. The software supports multi-spectral line-polarization mse diagnostics which simultaneously measure emission at the mse σ and π lines as well as at two "background" wavelengths that are displaced from the mse spectrum by a few nanometers. This analysis accurately estimates the amplitude of partially polarized background light at the σ and π wavelengths even in situations where the background light changes rapidly in time and space, a distinct improvement over traditional "time-interpolation" background estimation. The signal amplitude at many frequencies is computed using a numerical-beat algorithm which allows the retardance of the mse photo-elastic modulators (pem's) to be monitored during routine operation. It also allows the use of summed intensities at multiple frequencies in the calculation of polarization direction, which increases the effective signal strength and reduces sensitivity to pem retardance drift. The software allows the polarization angles to be corrected for calibration drift using a system that illuminates the mse diagnostic with polarized light at four known polarization angles within ten seconds of a plasma discharge. As a result, the software suite is modular, parallelized, and portable to other facilities.

97 MATHEMATICS AND COMPUTING↗

24.77 Pflops on a Gravitational Tree-Code to Simulate the Milky Way Galaxy with 18600 GPUs, In: SC '14: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis

We have simulated, for the first time, the long term evolution of the Milky Way Galaxy using 51 billion particles on the Swiss Piz Daint supercomputer with our N-body gravitational tree-code Bonsai. Herein, we describe the scientific motivation and numerical algorithms. The Milky Way model was simulated for 6 billion years, during which the bar structure and spiral arms were fully formed. This improves upon previous simulations by using 1000 times more particles, and provides a wealth of new data that can be directly compared with observations. We also report the scalability on both the Swiss Piz Daint and the US ORNL Titan. On Piz Daint the parallel efficiency of Bonsai was above 95%. The highest performance was achieved with a 242 billion particle Milky Way model using 18600 GPUs on Titan, thereby reaching a sustained GPU and application performance of 33.49 Pflops and 24.77 Pflops respectively.

Computer Science↗

A weighted state redistribution algorithm for embedded boundary grids

State redistribution is an algorithm that stabilizes cut cells for embedded boundary grid methods. This work extends the earlier algorithm in several important ways. First, state redistribution is extended to three spatial dimensions. Second, we discuss several algorithmic changes and improvements motivated by the more complicated cut cell geometries that can occur in higher dimensions. In particular, we introduce a weighted version with less dissipation in an easily generalizable framework. Third, we demonstrate that state redistribution can also stabilize a solution update that includes both advective and diffusive contributions. Notably, the stabilization algorithm is shown to be effective for incompressible as well as compressible reacting flows. Finally, we discuss the implementation of the algorithm for several exascale-ready simulation codes based on AMReX, demonstrating ease of use in combination with domain decomposition, hybrid parallelism and complex physics.

97 MATHEMATICS AND COMPUTING↗

Development of a New Fixed-source Sensitivity Tally Capability in the MCNP ® Code [Slides]

Current work includes FSEN capability development, continued verification of adjoint-weighted sensitivity method, and improvement of algorithm speed and parallelism capability. Future work is forecasted to include extensions to non-Boltzmann responses, adding more responses and particle types, and connection to new MCNP6.3 tally backend.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

SU-E-T-37: A GPU-Based Pencil Beam Algorithm for Dose Calculations in Proton Radiation Therapy

Purpose: Recent developments in radiation therapy have been focused on applications of charged particles, especially protons. Over the years several dose calculation methods have been proposed in proton therapy. A common characteristic of all these methods is their extensive computational burden. In the current study we present for the first time, to our best knowledge, a GPU-based PBA for proton dose calculations in Matlab. Methods: In the current study we employed an analytical expression for the protons depth dose distribution. The central-axis term is taken from the broad-beam central-axis depth dose in water modified by an inverse square correction while the distribution of the off-axis term was considered Gaussian. The serial code was implemented in MATLAB and was launched on a desktop with a quad core Intel Xeon X5550 at 2.67GHz with 8 GB of RAM. For the parallelization on the GPU, the parallel computing toolbox was employed and the code was launched on a GTX 770 with Kepler architecture. The performance comparison was established on the speedup factors. Results: The performance of the GPU code was evaluated for three different energies: low (50 MeV), medium (100 MeV) and high (150 MeV). Four square fields were selected for each energy, and the dose calculations were performed with both the serial and parallel codes for a homogeneous water phantom with size 300×300×300 mm3. The resolution of the PBs was set to 1.0 mm. The maximum speedup of ∼127 was achieved for the highest energy and the largest field size. Conclusion: A GPU-based PB algorithm for proton dose calculations in Matlab was presented. A maximum speedup of ∼127 was achieved. Future directions of the current work include extension of our method for dose calculation in heterogeneous phantoms.

60 APPLIED LIFE SCIENCES↗

Compressing unstructured mesh data from simulations using machine learning

The amount of data output from a computer simulation has grown to terabytes and petabytes as increasingly complex simulations are being run on massively parallel systems. As we approach exaflop computing in the next decade, it is expected that the I/O subsystem will not be able to write out these large volumes of data. In this paper, we explore the use of machine learning to compress the data before it is written out. Despite the computational constraints that limit us to using very simple learning algorithms, our results show that machine learning is a viable option for compressing unstructured data. Furthermore, we demonstrate that by simply using a better sampling algorithm to generate the training set, we can obtain more accurate results compared to random sampling, but at no extra cost. Further, by carefully selecting and incorporating points with high prediction error, we can improve reconstruction accuracy without sacrificing the compression rate.

97 MATHEMATICS AND COMPUTING↗

Exploring the interplay of resilience and energy consumption for a task-based partial differential equations preconditioner

Here, we discuss algorithm-based resilience to silent data corruptions (SDCs) in a task-based domain-decomposition preconditioner for partial differential equations (PDEs). The algorithm exploits a reformulation of the PDE as a sampling problem, followed by a solution update through data manipulation that is resilient to SDCs. The implementation is based on a server-client model where all state information is held by the servers, while clients are designed solely as computational units. Scalability tests run up to ~51K cores show a parallel efficiency greater than 90%. We use a 2D elliptic PDE and a fault model based on random single and double bit-flip to demonstrate the resilience of the application to synthetically injected SDC. We discuss two fault scenarios: one based on the corruption of all data of a target task, and the other involving the corruption of a single data point. We show that for our application, given the test problem considered, a four-fold increase in the number of faults only yields a 2% change in the overhead to overcome their presence, from 7% to 9%. We then discuss potential savings in energy consumption via dynamic voltage/frequency scaling, and its interplay with fault-rates, and application overhead.

97 MATHEMATICS AND COMPUTING↗

Neuromorphic scaling advantages for energy-efficient random walk computations

Neuromorphic computing, which aims to replicate the computational structure and architecture of the brain in synthetic hardware, has typically focused on artificial intelligence applications. What is less explored is whether such brain-inspired hardware can provide value beyond cognitive tasks. Here we show that the high degree of parallelism and configurability of spiking neuromorphic architectures makes them well suited to implement random walks via discrete-time Markov chains. Overall, these random walks are useful in Monte Carlo methods, which represent a fundamental computational tool for solving a wide range of numerical computing tasks. Using IBM’s TrueNorth and Intel’s Loihi neuromorphic computing platforms, we show that our neuromorphic computing algorithm for generating random walk approximations of diffusion offers advantages in energy-efficient computation compared with conventional approaches. We also show that our neuromorphic computing algorithm can be extended to more sophisticated jump-diffusion processes that are useful in a range of applications, including financial economics, particle physics and machine learning.

97 MATHEMATICS AND COMPUTING↗

Efficient Scheduling of Recursive Control Flow on GPUs

Graphics processing units (GPUs) have rapidly emerged as a very significant player in high performance computing. Single instruction multiple thread (SIMT) pipelines are typically used in GPUs to exploit parallelism and maximize performance. Although support for unstructured control flow has been included in GPUs, efficiently managing thread divergence for arbitrary parallel programs remains a critical challenge. In this paper, we focus on the problem of supporting recursion in modern GPUs. We design and comparatively evaluate various algorithms to manage thread divergence encountered in recursive programs. The results improve upon traditional post-dominator based reconvergence mechanisms designed to handle thread divergence due to control flow within a procedure.

GPUs↗

Brief announcement: Hypergraph parititioning for parallel sparse matrix-matrix multiplication

The performance of parallel algorithms for sparse matrix-matrix multiplication is typically determined by the amount of interprocessor communication performed, which in turn depends on the nonzero structure of the input matrices. In this paper, we characterize the communication cost of a sparse matrix-matrix multiplication algorithm in terms of the size of a cut of an associated hypergraph that encodes the computation for a given input nonzero structure. Obtaining an optimal algorithm corresponds to solving a hypergraph partitioning problem. Furthermore, our hypergraph model generalizes several existing models for sparse matrix-vector multiplication, and we can leverage hypergraph partitioners developed for that computation to improve application-specific algorithms for multiplying sparse matrices.

97 MATHEMATICS AND COMPUTING↗

I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization

In this paper, we propose a novel hardware accelerator for GCN inference called I-GCN that significantly improves data locality and reduces unnecessary computation through a new online graph restructuring algorithm we refer to as islandization. The proposed algorithm finds clusters of nodes with strong internal but weak external connections. The islandization process yields two major benefits. First, by processing islands rather than individual nodes, there is better on-chip data reuse and fewer off-chip memory accesses. Second, there is less redundant computation as aggregation for common/shared neighbors in an island can be reused. The parallel search, identification, and leverage of graph islands are all handled purely in hardware at runtime working in an incremental pipelined manner. This is done without any preprocessing of the graph data or adjustment of the GCN model structure.

Geng, Tong↗

Continuation and bifurcation analysis of large-scale dynamical systems with LOCA.

Dynamical systems theory provides a powerful framework for understanding the behavior of complex evolving systems. However applying these ideas to large-scale dynamical systems such as discretizations of multi-dimensional PDEs is challenging. Such systems can easily give rise to problems with billions of dynamical variables, requiring specialized numerical algorithms implemented on high performance computing architectures with thousands of processors. This talk will describe LOCA, the Library of Continuation Algorithms, a suite of scalable continuation and bifurcation tools optimized for these types of systems that is part of the Trilinos software collection. In particular, we will describe continuation and bifurcation analysis techniques designed for large-scale dynamical systems that are based on specialized parallel linear algebra methods for solving augmented linear systems. We will also discuss several other Trilinos tools providing nonlinear solvers (NOX), eigensolvers (Anasazi), iterative linear solvers (AztecOO and Belos), preconditioners (Ifpack, ML, Amesos) and parallel linear algebra data structures (Epetra and Tpetra) that LOCA can leverage for efficient and scalable analysis of large-scale dynamical systems.

99 GENERAL AND MISCELLANEOUS↗

Locality-Aware Parallel Process Mapping for Multi-Core HPC Systems

High Performance Computing (HPC) systems are composed of servers containing an ever-increasing number of cores. With such high processor core counts, non-uniform memory access (NUMA) architectures are almost universally used to reduce inter-processor and memory communication bottlenecks by distributing processors and memory throughout a server-internal networking topology. Application studies have shown that the tuning of processes placement in a server s NUMA networking topology to the application can have a dramatic impact on performance. The performance implications are magnified when running a parallel job across multiple server nodes, especially with large scale HPC applications. This paper presents the Locality-Aware Mapping Algorithm (LAMA) for distributing the individual processes of a parallel application across processing resources in an HPC system, paying particular attention to the internal server NUMA topologies. The algorithm is able to support both homogeneous and heterogeneous hardware systems, and dynamically adapts to the available hardware and user-specified process layout at run-time. As implemented in Open MPI, the LAMA provides 362,880 mapping permutations and is able to naturally scale out to additional hardware resources as they become available in future architectures.

99 GENERAL AND MISCELLANEOUS↗

A Coupling Methodology for Mesoscale-informed Nuclear Fuel Performance Codes

This study proposes an approach for capturing the effect of microstructural evolution on reactor fuel performance by coupling a mesoscale irradiated microstructure model with a finite element fuel performance code. To achieve this, the macroscale system is solved in a parallel, fully coupled, fully-implicit manner using the preconditioned Jacobian-free Newton Krylov (JFNK) method. Within the JFNK solution algorithm, microstructure-influenced material parameters are calculated by the mesoscale model and passed back to the macroscale calculation. Due to the stochastic nature of the mesoscale model, a dynamic fitting technique is implemented to smooth roughness in the calculated material parameters. The proposed methodology is demonstrated on a simple model of a reactor fuel pellet. In the model, INL’s BISON fuel performance code calculates the steady-state temperature profile in a fuel pellet and the microstructure-influenced thermal conductivity is determined with a phase field model of irradiated microstructures. This simple multiscale model demonstrates good nonlinear convergence and near ideal parallel scalability. By capturing the formation of large mesoscale voids in the pellet interior, the multiscale model predicted the irradiation-induced reduction in the thermal conductivity commonly observed in reactors.

97 MATHEMATICS AND COMPUTING↗

Computing the energy of a water molecule using multideterminants: A simple, efficient algorithm

Quantum Monte Carlo (QMC) methods such as variational Monte Carlo and fixed node diffusion Monte Carlo depend heavily on the quality of the trial wave function. Although Slater-Jastrow wave functions are the most commonly used variational ansatz in electronic structure, more sophisticated wave functions are critical to ascertaining new physics. One such wave function is the multi-Slater-Jastrow wave function which consists of a Jastrow function multiplied by the sum of Slater determinants. In this paper we describe a method for working with these wave functions in QMC codes that is easy to implement, efficient both in computational speed as well as memory, and easily parallelized. The computational cost scales quadratically with particle number making this scaling no worse than the single determinant case and linear with the total number of excitations. Additionally, we implement this method and use it to compute the ground state energy of a water molecule.

97 MATHEMATICS AND COMPUTING↗

Hierarchical fractional-step approximations and parallel kinetic Monte Carlo algorithms

We present a mathematical framework for constructing and analyzing parallel algorithms for lattice kinetic Monte Carlo (KMC) simulations. The resulting algorithms have the capacity to simulate a wide range of spatio-temporal scales in spatially distributed, non-equilibrium physiochemical processes with complex chemistry and transport micro-mechanisms. Rather than focusing on constructing exactly the stochastic trajectories, our approach relies on approximating the evolution of observables, such as density, coverage, correlations and so on. More specifically, we develop a spatial domain decomposition of the Markov operator (generator) that describes the evolution of all observables according to the kinetic Monte Carlo algorithm. This domain decomposition corresponds to a decomposition of the Markov generator into a hierarchy of operators and can be tailored to specific hierarchical parallel architectures such as multi-core processors or clusters of Graphical Processing Units (GPUs). Based on this operator decomposition, we formulate parallel Fractional step kinetic Monte Carlo algorithms by employing the Trotter Theorem and its randomized variants; these schemes, (a) are partially asynchronous on each fractional step time-window, and (b) are characterized by their communication schedule between processors. The proposed mathematical framework allows us to rigorously justify the numerical and statistical consistency of the proposed algorithms, showing the convergence of our approximating schemes to the original serial KMC. The approach also provides a systematic evaluation of different processor communicating schedules. We carry out a detailed benchmarking of the parallel KMC schemes using available exact solutions, for example, in Ising-type systems and we demonstrate the capabilities of the method to simulate complex spatially distributed reactions at very large scales on GPUs. Finally, we discuss work load balancing between processors and propose a re-balancing scheme based on probabilistic mass transport methods.

97 MATHEMATICS AND COMPUTING↗

Evaluation of Graph Analytics Frameworks Using the GAP Benchmark Suite

The analysis of connected data is an increasingly important application in high-performance computing. Such analyses can reveal fraudulent patterns in financial transactions, optimize telecommunications networks, predict information flow in social networks, etc. However, the landscape of graph analytics is highly diverse. Graph algorithms stress processor architectures differently, and no one graph can represent all topologies. Consequently, no single approach or framework is expected to be optimal for all graph analytics problems. To help make sense of this diverse landscape, we evaluated four approaches to graph analytics: GraphBLAS, Galois, BGL17, GraphIt; and compare them against hand-tuned implementations that take advantage of hardware features on our test platform. Graph- BLAS formulates graph analytics as sparse linear algebra. Galois provides syntactic constructs for data parallelism over irregular data structures. BGL17 is a generic C++ template library for implementing graph algorithms. GraphIt provides a domain- specific language to describe and optimize graph algorithms. We use the GAP Benchmark Suite to establish baseline performance and guide the side-by-side evaluation of each framework. GAP consists of 30 tests: six graph analytics algorithms (breadth- first search, single-source shortest path, PageRank, betweenness centrality, connected components, and triangle counting) run on five graphs, each with different topological characteristics (e.g., high diameter, skewed degree distribution, high average degree). High-performance reference implementations are included for each benchmark algorithm. Because a graph can be loaded into memory a number of ways (e.g., flat file on disk, compressed sparse format, data frames, retrieved from SQL or NoSQL databases), our evaluation focused on computational performance rather than I/O. Our results show the relative strengths of each framework.

Graph algorithms, Benchmarking, shared-memory prog↗

Introduction: Neuromorphic Materials

The explosive growth in data collection and the need to process it efficiently, as well as the desire to automate increasingly complex tasks in transportation, medical care, manufacturing, security and many other fields have motivated a growing interest in neuromorphic computing. Unlike the binary, transistorbased ON/OFF logic gates and separate logic and memory functionalities employed in digital computing, neuromorphic computing is inspired by animal brains that use interconnected synapses and neurons to perform processing, storage and transmission of information at the same location, while only consuming ~20 W or less of power. Motivated by the brain’s efficiency, adaptability, self-learning and resiliency qualities, neuromorphic computing can be broadly defined as an approach to processing and storing information using hardware and algorithms inspired by models of biological neural systems. Present research in neuromorphic computing encompasses approaches that vary significantly in their degree of neuro-inspiration, from systems that only incorporate features such as asynchronous, event-driven operation or use crossbar arrays of non-volatile memory (NVM) elements to accelerate deep neural networks (DNNs), to designs that embrace the extreme parallelism, sparsity, reconfigurability, adaptability, complexity and stochasticity observed in nervous systems. The term ‘neuromorphic’ computing is often credited to Carver Mead, who in the 1980s investigated Si-based analog electronics to replicate functions of the animal retina. Earlier important advances in this field include the work of Frank Rosenblatt, who proposed the concept of the perceptron, Bernard Widrow, who used this concept to build one of the first analog neural networks, the Adaline and many other researchers (see ref. 6 for an historical perspective on neuromorphic computing). With the recent increase in the use of artificial intelligence and large language models, and rising concerns over the associated energy costs, interest in neuromorphic hardware has expanded rapidly. According to some estimates, driven largely by the drastic growth in the training use of artificial intelligence (AI) models using the current computing architectures, the energy cost of computing is projected to reach the energy supply worldwide by 2045. Furthermore, while this is not a realistic outcome, it means that, if more efficient computing technologies are not developed -- soon -- the world will soon become one where demand for energy and market constraints limit the continued increase of societal access to AI and cloud services from data centers. Data centers used for training and use of these models consume hundreds of terawatt hours of electricity, already past 4% of the US electricity demand.

Circuits↗