Search NASA⌕ Search

SEARCH · Search NASA

Results for “asynchronous 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 127 records · Page 7

Scalable All-pairs Shortest Paths for Huge Graphs on Multi-GPU Clusters

We present an optimized Floyd-Warshall (Floyd-Warshall) algorithm that computes the All-pairs shortest path (APSP) for GPU accelerated clusters. The Floyd-Warshall algorithm due to its structural similarities to matrix-multiplication is well suited for highly parallel GPU architectures. To achieve high parallel efficiency, we address two key algorithmic challenges: reducing high communication overhead and addressing limited GPU memory. To reduce high communication costs, we redesign the parallel (a) to expose more parallelism, (b) aggressively overlap communication and computation with pipelined and asynchronous scheduling of operations, and (c) tailored MPI-collective. To cope with limited GPU memory, we employ an offload model, where the data resides on the host and is transferred to GPU on-demand. The proposed optimizations are supported with detailed performance models for tuning. Our optimized parallel Floyd-Warshall implementation is up to 5x faster than a strong baseline and achieves 8.1 PetaFLOPS/sec on 256~nodes of the Summit supercomputer at Oak Ridge National Laboratory. This performance represents 70% of the theoretical peak and 80% parallel efficiency. The offload algorithm can handle 2.5x larger graphs with a 20% increase in overall running time.

Sao, Piyush↗

Rethinking Programming Paradigms in the QC-HPC Context

Programming for today’s quantum computers is making significant strides toward modern workflows compatible with high performance computing (HPC), but fundamental challenges still remain in the integration of these vastly different technologies. Quantum computing (QC) programming languages share some common ground, as well as their emerging runtimes and algorithmic modalities. In this short paper, we explore avenues of refinement for the quantum processing unit (QPU) in the context of many-tasks management, asynchronous or otherwise, in order to understand the value it can play in linking QC with HPC. Through examples, we illustrate how its potential for scientific discovery might be realized.

Wong, Elaine↗

Numerical strategies for filtering partially observed stiff stochastic differential equations

In this paper, we present a fast numerical strategy for filtering stochastic differential equations with multiscale features. This method is designed such that it does not violate the practical linear observability condition and, more importantly, it does not require the computationally expensive cross correlation statistics between multiscale variables that are typically needed in standard filtering approach. The proposed filtering algorithm comprises of a 'macro-filter' that borrows ideas from the Heterogeneous Multiscale Methods and a 'micro-filter' that reinitializes the fast microscopic variables to statistically reflect the unbiased slow macroscopic estimate obtained from the macro-filter and macroscopic observations at asynchronous times. We will show that the proposed micro-filter is equivalent to solving an inverse problem for parameterizing differential equations. Numerically, we will show that this microscopic reinitialization is an important novel feature for accurate filtered solutions, especially when the microscopic dynamics is not mixing at all.

97 MATHEMATICS AND COMPUTING↗

Envisioning the Future Renewable and Resilient Energy Grids—A Power Grid Revolution Enabled by Renewables, Energy Storage, and Energy Electronics

Today’s power grids are facing tremendous challenges because of the ever-increasing power demand, system complexity, infrastructure cost, knowledge base, and policy and regulatory issues to achieve supply–demand power balance and resiliency with respect to more frequent extreme weather events and cyberattacks. It is particularly challenging when the transition toward 100% intermittent renewable energy sources is considered. Many countries are calling for building up more transmission and distribution lines to increase power delivery capacities. This article is an attempt to answer two urgent questions: Is more transmission and distribution infrastructure really needed to meet the increasing power demand? What kind of future grid infrastructure should we envision and build? This article attempts to answer these questions and proposes the concept of community-centric asynchronous renewable and resilient energy grids. By clearly differentiating the concepts of grid resilience and reliability, the importance of building resilient power electronics’ devices and robust system-level control algorithms to achieve 100% renewable energy integrated resilient grids is presented. To identify the shortcomings and propose advancements, power electronics’ technologies are categorized using the proposed concepts of natural source frequencies (NSf), energy storage, direct energy conversion/control and fault protection (DeCaFp), and high-efficiency energy consumption and buffering (heECaB) technology. The ability of networked microgrids to greatly reduce power outages and power system restoration time is demonstrated by leveraging robust decentralized and centralized control algorithms, identified through a comprehensive literature review. Future research areas are proposed to further enhance grid stability, controllability, cybersecurity, and protection against faults in the presence of 100% renewable sources by leveraging the advanced capabilities of NSf, DeCaFp, and heECaB devices and system-level control algorithms.

14 SOLAR ENERGY↗

An Asynchronous Task-based Fan-Both Sparse Cholesky Solver

Systems of linear equations arise at the heart of many scientific and engineering applications. Many of these linear systems are sparse; i.e., most of the elements in the coefficient matrix are zero. Direct methods based on matrix factorizations are sometimes needed to ensure accurate solutions. For example, accurate solution of sparse linear systems is needed in shift-invert Lanczos to compute interior eigenvalues. The performance and resource usage of sparse matrix factorizations are critical to time-to-solution and maximum problem size solvable on a given platform. In many applications, the coefficient matrices are symmetric, and exploiting symmetry will reduce both the amount of work and storage cost required for factorization. When the factorization is performed on large-scale distributed memory platforms, communication cost is critical to the performance of the algorithm. At the same time, network topologies have become increasingly complex, so that modern platforms exhibit a high level of performance variability. This makes scheduling of computations an intricate and performance-critical task. In this paper, we investigate the use of an asynchronous task paradigm, one-sided communication and dynamic scheduling in implementing sparse Cholesky factorization (symPACK) on large-scale distributed memory platforms. Our solver symPACK relies on efficient and flexible communication primitives provided by the UPC++ library. Performance evaluation shows good scalability and that symPACK outperforms state-of-the-art parallel distributed memory factorization packages, validating our approach on practical cases.

Jacquelin, Mathias↗

System Modeling and Simulation of In-Stream Hydrokinetic Turbines for Power Management and Control

Electricity generation from moving currents without using dams (i.e., in-stream hydrokinetic electricity) has the potential to introduce multiple GW of renewable power to U.S. grids. Here this study evaluates a control system designed to regulate the generator rotor rate (rpm) to improve power production from in-stream hydrokinetic turbines. The control algorithm is evaluated using numerical models of both a rigidly mounted tidal turbine (TT) and a moored ocean current turbine (OCT) coupled to an induction electric machine model. The moored simulation utilizes an innovative approach for coupling a multiple degrees-of-freedom (DOF) nonlinear hydrodynamic/mechanical turbine model with a nonlinear electromechanical generator model. Based on the turbine torque-speed characteristic, as well as the asynchronous machine features, a proportional–integral (PI) controller is used to generate a correction term for the frequency of the three-phase sinusoidal voltages that are supplied to the asynchronous generator. The speed control of the induction generator through the supply frequency is accomplished by a simplified voltage source inverter (VSI). The simplified VSI consists of control voltage sources (CVSs), while the comparison with a real VSI using diodes and transistors, which are controlled by pulse width modulation (PWM) technique, is also presented. Simulations are used to evaluate the developed algorithms showing that rpm fluctuations are around 0.02 for a tidal turbine operating in a wave field with a 6 m significant wave height and around 0.005 for a moored ocean current turbine operating in a wave field with a 2 m significant wave height.

16 TIDAL AND WAVE POWER↗

DeepHyper: Asynchronous Hyperparameter Search for Deep Neural Networks

Hyperparameters employed by deep learning (DL) methods play a substantial role in the performance and reliability of these methods in practice. Unfortunately, finding performance-optimizing hyperparameter settings is a notoriously difficult task. Hyperparameter search methods typically have limited production-strength implementations or do not target scalability within a highly parallel machine, portability across different machines, experimental comparison between different methods, and tighter integration with workflow systems. In this paper, we present DeepHyper, a Python package that provides a common interface for the implementation and study of scalable hyperparameter search methods. It adopts the Balsam workflow system to hide the complexities of running large numbers of hyperparameter configurations in parallel on high-performance computing (HPC) systems. We implement and study asynchronous model-based search methods that consist of sampling a small number of input hyperparameter configurations and progressively fitting surrogate models over the input-output space until exhausting a user-defined budget of evaluations. We evaluate the efficacy of these methods relative to approaches such as random search, genetic algorithms, Bayesian optimization, and hyperband on DL benchmarks on CPU- and GPU-based HPC systems.

Balaprakash, Prasanna↗

PSelInv – A distributed memory parallel algorithm for selected inversion: The non-symmetric case

This paper generalizes the parallel selected inversion algorithm called PSelInv to sparse non-symmetric matrices. We assume a general sparse matrix A has been decomposed as $PAQ$ = $LU$ on a distributed memory parallel machine, where L, U are lower and upper triangular matrices, and P, Q are permutation matrices, respectively. The PSelInvmethod computes selected elements of $A$ -1 . The selection is confined by the sparsity pattern of the matrix A T . Here our algorithm does not assume any symmetry properties of A, and our parallel implementation is memory efficient, in the sense that the computed elements of $A$ -T overwrites the sparse matrix $L + U$ in situ . PSelInv involves a large number of collective data communication activities within different processor groups of various sizes. In order to minimize idle time and improve load balancing, tree-based asynchronous communication is used to coordinate all such collective communication. Numerical results demonstrate that PSelInv can scale efficiently to 6,400 cores for a variety of matrices.

97 MATHEMATICS AND COMPUTING↗

Scalable Parallel Methods for Analyzing Metagenomics Data at Extreme Scale

The field of bioinformatics and computational biology is currently experiencing a data revolution. The exciting prospect of making fundamental biological discoveries is fueling the rapid development and deployment of numerous cost-effective, high-throughput next-generation sequencing technologies. The result is that the DNA and protein sequence repositories are being bombarded with new sequence information. Databases are continuing to report a Moore’s law-like growth trajectory in their database sizes, roughly doubling every 18 months. In what seems to be a paradigm-shift, individual projects are now capable of generating billions of raw sequence data that need to be analyzed in the presence of already annotated sequence information. While it is clear that data-driven methods, such as sequencing homology detection, are becoming the mainstay in the field of computational life sciences, the algorithmic advancements essential for implementing complex data analytics at scale have mostly lagged behind. Sequence homology detection is central to a number of bioinformatics applications including genome sequencing and protein family characterization. Given millions of sequences, the goal is to identify all pairs of sequences that are highly similar (or “homologous”) on the basis of alignment criteria. While there are optimal alignment algorithms to compute pairwise homology, their deployment for large-scale is currently not feasible; instead, heuristic methods are used at the expense of quality. In this dissertation, we present the design and evaluation of a parallel implementation for conducting optimal homology detection on distributed memory supercomputers. Our approach uses a combination of techniques from asynchronous load balancing (viz. work stealing, dynamic task counters), data replication, and exact-matching filters to achieve homology detection at scale. Results for a collection of 2.56M sequences show parallel efficiencies of ~75-100% on up to 8K cores, representing a time-to-solution of 33 seconds. We extend this work with a detailed analysis of single-node sequence alignment performance using the latest CPU vector instruction set extensions. Preliminary results reveal that current sequence alignment algorithms are unable to fully utilize widening vector registers.

59 BASIC BIOLOGICAL SCIENCES↗

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↗

Combining In-situ and In-transit Processing to Enable Extreme-Scale Scientific Analysis

With the onset of extreme-scale computing, I/O constraints make it increasingly difficult for scientists to save a sufficient amount of raw simulation data to persistent storage. One potential solution is to change the data analysis pipeline from a post-process centric to a concurrent approach based on either in-situ or in-transit processing. In this context computations are considered in-situ if they utilize the primary compute resources, while in-transit processing refers to offloading computations toa set of secondary resources using asynchronous data transfers. In this paper we explore the design and implementation of three common analysis techniques typically performed on large-scale scientific simulations: topological analysis, descriptive statistics, and visualization. We summarize algorithmic developments, describe a resource scheduling system to coordinate the execution ofvarious analysis workflows, and discuss our implementation using the DataSpaces and ADIOS frameworks that support efficient data movement between in-situ and in-transit computations. Wedemonstrate the efficiency of our lightweight, flexible framework by deploying it on the Jaguar XK6 to analyze data generated by S3D, a massively parallel turbulent combustion code. Our framework allows scientists dealing with the data deluge at extreme scale to perform analyses at increased temporal resolutions, mitigate I/O costs, and significantly improve the time to insight.

Bennett, Janine C.↗

A Surrogate-Based Asynchronous Decomposition Technique for Realistic Security-Constrained Optimal Power Flow Problems

Here we present a decomposition approach for obtaining good feasible solutions for the security-constrained, alternating-current, optimal power flow (SC-AC-OPF) problem at an industrial scale and under real-world time and computational limits. The approach was designed while preparing and participating in ARPA-E’s Grid Optimization Competition (GOC) Challenge 1. The challenge focused on a near-real-time version of the SC-AC-OPF problem, where a base operating point is optimized, taking into account possible single-element contingencies, after which the system adapts its operating point following the response of automatic frequency droop controllers and voltage regulators. Our solution approach for this problem relies on state-of-the-art nonlinear programming algorithms, and it employs nonconvex relaxations for complementarity constraints, a specialized two-stage decomposition technique with sparse approximations of recourse terms and contingency ranking and prescreening. The paper describes and justifies our approach and outlines the features of its implementation, including functions and derivatives evaluation, warm-starting strategies, and asynchronous parallelism. We discuss the results of the independent benchmark of our approach by ARPA-E’s GOC team in Challenge 1, where it was found to consistently produce high-quality solutions across a wide range of network sizes and difficulty, and conclude by outlining future extensions of the approach.

97 MATHEMATICS AND COMPUTING↗

Scheduling and Performance of Asynchronous Tasks in Fortran 2018 with FEATS

Most parallel scientific programs contain compiler directives (pragmas) such as those from OpenMP (Hermanns in Parallel programming in Fortran 95 using openMP, 2002. School of Aeronautical Engineering, Universidad Politécnica de Madrid, España, 2011), explicit calls to runtime library procedures such as those implementing the Message Passing Interface (MPI) (in A message-passing interface standard version 4.0, 2021. https://www.mpi-forum.org/docs/mpi-4.0/mpi40-report.pdf), or compiler-specific language extensions such as those provided by CUDA (Ruetsch and Fatica in CUDA Fortran for scientists and engineers: best practices for efficient CUDA Fortran programming, Elsevier, 2013). By contrast, the recent Fortran standards empower developers to express parallel algorithms without directly referencing lower-level parallel programming models (Numrich in Parallel programming with co-arrays, CRC Press, 2018, and Curcic in Modern Fortran: building efficient parallel applications, Manning Publications, 2020). Fortran’s parallel features place the language within the Partitioned Global Address Space (PGAS) class of programming models. When writing programs that exploit data parallelism, application developers often find it straightforward to develop custom parallel algorithms. Problems involving complex, heterogeneous, staged calculations, however, pose much greater challenges. Such applications require careful coordination of tasks in a manner that respects dependencies prescribed by a directed acyclic graph. When rolling one’s own solution proves difficult, extending a customizable framework becomes attractive. Further, the paper presents the design, implementation, and use of the Framework for Extensible Asynchronous Task Scheduling (FEATS), which we believe to be the first task scheduling tool written in modern Fortran. We describe the benefits and compromises associated with choosing Fortran as the implementation language, and we propose ways in which future Fortran standards can best support the use case in this paper.

97 MATHEMATICS AND COMPUTING↗

Asynchronous Graphs (Final Report)

The most performant massive-scale distributed graph analytic engines were essentially unusable for anything but the analytic they were tuned to solve. The project team had previously developed HavoqGT and used this project to demonstrate it as a flexible graph framework, aiming to extend algorithmic capabilities, improve underlying data structures, and develop novel communication paradigms to enable new data analysis missions. Highlights of the technology developed include (a) a new distributed communication paradigm dubbed You’ve Got Mail (YGM), (b) a performant exact and fuzzy HPC graph pattern matching approach, and (c) a distributed biased random walk simulation capability. The project was successful on several measurable fronts, including advancing computer science (reflected by publishing 14 peer-reviewed research papers yielding 4 publication awards and over 16 conference presentations), contributing tangibly to LLNL recruiting rare talent, and obtaining follow-on funding. These technologies were transferred to several FY19-20 programmatic projects and will continue to be leveraged by new research projects for several years.

97 MATHEMATICS AND COMPUTING↗

Image Gradient Decomposition for Parallel and Memory-Efficient Ptychographic Reconstruction

Ptychography is a popular microscopic imaging modality for many scientific discoveries and sets the record for highest image resolution. Unfortunately, the high image resolution for ptychographic reconstruction requires significant amount of memory and computations, forcing many applications to compromise their image resolution in exchange for a smaller memory footprint and a shorter reconstruction time. In this paper, we propose a novel image gradient decomposition method that significantly reduces the memory footprint for ptychographic reconstruction by tessellating image gradients and diffraction measurements into tiles. In addition, we propose a parallel image gradient decomposition method that enables asynchronous point-to-point communications and parallel pipelining with minimal overhead on a large number of GPUs. Our experiments on a Titanate material dataset (PbTiO3) with 16632 probe locations show that our Gradient Decomposition algorithm reduces memory footprint by 51 times. In addition, it achieves time-to-solution within 2.2 minutes by scaling to 4158 GPUs with a super-linear strong scaling efficiency at 364% compared to runtimes at 6 GPUs. This performance is 2.7 times more memory efficient, 9 times more scalable and 86 times faster than the state-of-the-art algorithm.

Wang, Xiao↗

Modular Spiking Neural Circuits for Mapping Long Short-Term Memory on a Neurosynaptic Processor

Due to the distributed and asynchronous nature of neural computation through low-energy spikes, brain-inspired hardware systems offer high energy efficiency and massive parallelism. One such platform is the IBM TrueNorth neurosynaptic system. Recently, TrueNorth compatible representation learning algorithms have emerged, achieving close to the state-of-the-art performance in various data sets. However, its application in temporal sequence processing models, such as recurrent neural networks (RNNs), is still only at the proof of concept level. There is an inherent difficulty in capturing temporal dynamics of an RNN using spiking neurons, which is only exasperated by the hardware constraints in connectivity and synaptic weight resolution. This paper presents a design flow that overcomes these difficulties and maps a special case of recurrent networks called long short-term memory (LSTM) onto a spike-based platform. The framework utilizes various approximation techniques, such as activation discretization, weight quantization, and scaling and rounding, spiking neural circuits that implement the complex gating mechanisms, and a store-and-release technique to enable neuron synchronization and faithful storage. While the presented techniques can be applied to map LSTM to any spiking neural network (SNN) simulator/emulator, here we choose the TrueNorth chip as the target platform by adhering to its hardware constraints. Three LSTM applications, parity check, extended Reber grammar, and question classification, are evaluated. The tradeoffs among accuracy, performance, and energy tradeoffs achieved on TrueNorth are demonstrated. Finally, this is compared with the performance on an SNN platform without hardware constraints, which represents the upper bound of the achievable accuracy.

97 MATHEMATICS AND COMPUTING↗

State Estimation for Distribution Networks with Asynchronous Sensors Using Stochastic Descent: Preprint

This paper investigates the problem of state estimation for distribution networks with asynchronous sensors comprising of a mix of smart meters and phasor measurement units (PMUs) with multiple sampling and reporting rates. We consider two independent scenarios of state estimation and tracking, with either voltages or currents as states. With these two sets, we investigate estimation under (a) full data, assuming all measurements are available and (b) limited data, where an online algorithmic approach is adopted to estimate the possibly time-varying states by processing measurements as and when available. The proposed algorithm, inspired by the classical Stochastic Gradient Descent (SGD) approach updates the states based on the previous estimate and the newly available measurements. Finally, we demonstrate the estimation and tracking efficacy through numerical simulations on the IEEE-37 test network, while also highlighting how estimation with currents as states leads to faster convergence.

asynchronous sensors↗

ConnectX-2 CORE-Direct Enabled Asynchronous Broadcast Collective Communications

This paper describes the design and implementation of InfiniBand (IB) CORE-Direct based blocking and nonblocking broadcast operations within the Cheetah collective operation framework. It describes a novel approach that fully ofFLoads collective operations and employs only user-supplied buffers. For a 64 rank communicator, the latency of CORE-Direct based hierarchical algorithm is better than production-grade Message Passing Interface (MPI) implementations, 150% better than the default Open MPI algorithm and 115% better than the shared memory optimized MVAPICH implementation for a one kilobyte (KB) message, and for eight mega-bytes (MB) it is 48% and 64% better, respectively. Flat-topology broadcast achieves 99.9% overlap in a polling based communication-computation test, and 95.1% overlap for a wait based test, compared with 92.4% and 17.0%, respectively, for a similar Central Processing Unit (CPU) based implementation.

99 GENERAL AND MISCELLANEOUS↗