Search NASA⌕ Search

SEARCH · Search NASA

Results for “data parallel 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 829 records · Page 46
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

Reconstructing three-dimensional protein crystal intensities from sparse unoriented two-axis X-ray diffraction patterns

Recently, there has been a growing interest in adapting serial microcrystallography (SMX) experiments to existing storage ring (SR) sources. For very small crystals, however, radiation damage occurs before sufficient numbers of photons are diffracted to determine the orientation of the crystal. The challenge is to merge data from a large number of such `sparse' frames in order to measure the full reciprocal space intensity. To simulate sparse frames, a dataset was collected from a large lysozyme crystal illuminated by a dim X-ray source. The crystal was continuously rotated about two orthogonal axes to sample a subset of the rotation space. With the EMC algorithm [expand–maximize–compress; Loh & Elser (2009). Phys. Rev. E , 80 , 026705], it is shown that the diffracted intensity of the crystal can still be reconstructed even without knowledge of the orientation of the crystal in any sparse frame. Moreover, parallel computation implementations were designed to considerably improve the time and memory scaling of the algorithm. The results show that EMC-based SMX experiments should be feasible at SR sources.

Chemistry↗
DOE OSTI2022

Building an Integrated Ecosystem of Computational and Observational Facilities to Accelerate Scientific Discovery

Future scientific discoveries will rely on flexible ecosystems that incorporate modern scientific instruments, high performance computing resources, parallel distributed data storage, and performant networks across multiple, independent facilities. In addition to connecting physical resources, such an ecosystem presents many challenges in logistics and accessibility, especially in orchestrating computations and experiments that span across leadership computing systems and experimental instruments. Past efforts have typically been application-specific or limited to interfaces for computing resources. This paper proposes a general framework for integrating computation resources and instrument operations, addressing challenges in code development/execution, data staging and collection, software stack, control mechanisms, resource authorization and governance, and hardware integration. We also describe a demonstration use case wherein a Bayesian optimization algorithm running on an edge computing resource guides a scanning probe microscope to autonomously and intelligently characterize a material sample. This science edge ecosystem framework will provide a blueprint for federating multi-institutional, disparate resources and orchestrating scientific workflows across them to enable next-generation discoveries.

Somnath, Suhas↗
DOE OSTI2023

Distributed approximate minimal Steiner trees with millions of seed vertices on billion-edge graphs

In this report, we present a parallel 2-approximation Steiner minimal tree algorithm and its MPI-based distributed implementation. In place of expensive distance computations between all pairs of seed vertices, the solution we employ exploits a cheaper Voronoi cell computation. Our design leverages asynchronous processing and message prioritization to accelerate convergence of distance computations, and harnesses vertex and edge centric processing to offer fast time-to-solution. We demonstrate scalability and performance using real-world graphs with up to 128 billion edges and 512 compute nodes, and show the ability to find Steiner trees with up to one million seed vertices. Using 12 data instances, we present comparison with the state-of-the-art exact solver, SCIP-Jack, and two sequential 2-approximate algorithms. We empirically show that, on average, the total distance of the Steiner tree identified by our solution is 1.1290 times greater than the Steiner minimal tree – well within the theoretical approximation bound of 2.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

A Multi-Model Adaptive Kalman Filtering Approach to Power System Dynamic State Estimation

Accurate information about dynamic states (such as rotor angle and speed of a synchronous machine) is important for monitoring and controlling power system rotor-angle stability. In this paper, a multi-model adaptive Kalman filtering (MMAKF) approach is proposed to accurately and robustly estimate power system dynamic states. This approach consists of three major steps: (i) multiple Kalman filtering approaches, i.e., the extended Kalman filter (EKF), unscented Kalman filter (UKF), ensemble Kalman filter (EnKF), and cubature Kalman filter (CKF), are run concurrently in parallel to estimate the dynamic states of a synchronous generator using phasor measurement unit data; (ii) probability indexes, which quantify the likelihood of each estimation model, are determined at each time step using hypothesis testing based on the measurement innovation; (iii) the a posteriori estimate of states is obtained using the best-fix approach. The two-area four-machine system is used to evaluate the effectiveness of the proposed MMAKF approach. It is shown through the Monte-Carlo method that the estimation accuracy and robustness of the proposed approach is better than those from any individual filtering algorithm.

multi-model adaptive Kalman Filtering, Power Syste↗
DOE OSTI2025

Track reconstruction as a service for collider physics

Optimizing charged-particle track reconstruction algorithms is crucial for efficient event reconstruction in Large Hadron Collider (LHC) experiments due to their significant computational demands. Existing track reconstruction algorithms have been adapted to run on massively parallel coprocessors, such as graphics processing units (GPUs), to reduce processing time. Nevertheless, challenges remain in fully harnessing the computational capacity of coprocessors in a scalable and non-disruptive manner. This paper proposes an inference-as-a-service approach for particle tracking in high energy physics experiments. To evaluate the efficacy of this approach, two distinct tracking algorithms are tested: Patatrack, a rule-based algorithm, and Exa.TrkX, a machine learning-based algorithm. The as-a-service implementations show enhanced GPU utilization and can process requests from multiple CPU cores concurrently without increasing per-request latency. The impact of data transfer is minimal and insignificant compared to running on local coprocessors. This approach greatly improves the computational efficiency of charged particle tracking, providing a solution to the computing challenges anticipated in the High-Luminosity LHC era.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2017

Glass-like energy and property landscape of Pt nanoclusters

Pt nanoclusters play an important role in catalysis-related applications. Essential to their activities are their geometries and energy landscapes. In this work, we studied the energy landscapes of Pt clusters using a parallel differential evolution optimization algorithm and an accelerated ab initio atomic relaxation method, which allowed us to explore unprecedentedly large numbers of geometry local minima at ab initio level. We found many lower-energy isomers with low symmetry in their geometry. The energy landscapes were demonstrated to be glass-like with a large number of local minimum structures close to the global minimum. The electronic and magnetic properties of most glass-like local minima were dramatically different from the global minimum, and they should be observed in the experimental measurements. The connections between these local minima were further analyzed using data mining techniques.

Chen, Zhanghui↗
DOE OSTI2020

Description of Sensor Assignment Optimization Method as Deployed on a Multi-Node Cluster

Data analytic methods are being developed to address the problem of how to assign a sensor set in a nuclear facility such that a requisite level of process monitoring capability is realized and that the sensor set is sufficiently rich to determine the status of the individual sensors with respect to need for calibration. There is an awareness in the nuclear industry that data analytics combined with rich sensor sets represent a means to improve operations and reduce costs. In the industry the calibration problem has been previously approached as an empirical data-driven problem with several methods having been developed. However, the experience of the utilities over the past ten years with these methods indicates that the absence of physics-based information renders the data-driven approach less reliable. Complicating factors such as the inherent variability of operation (both equipment alignment and operating condition) can confound a pure data-driven approach while there are no rigorous guidelines for determining what constitutes an adequate sensor set. The solution under development to overcome these shortcomings supplements the data analytic method with process information in a so-called process-constrained data-analytic approach. Simple balance equations are written for generic components (e.g., mechanical pump, valve, and heat exchanger). These do not require a priori knowledge of process parameters, such as heat transfer coefficients or friction factors. All that is needed on the part of the utility user is to identify the components and how they are connected. This report describes the development of a parallel computing capability for determining the optimal sensor set. The optimal sensor set problem suffers from the curse of dimensionality. Computation time increases exponentially as the size of the system grows. To overcome this difficulty a pre-conditioner algorithm is developed to find an approximate solution close the actual solution. This serves as a seed for the full-blown algorithm and acts to constrain the space that must searched. The optimization algorithms are described and the implementation on a parallel computing platform is described. The application of the method to a use case we are solving in collaboration with our utility partner served to illustrate how the default sensor set in a nuclear plant may not provide sufficient coverage to infer sensor calibration status.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1991

Applications of the massively parallel machine, the MasPar MP-1, to Earth sciences

The computational workload of upcoming NASA science missions, especially the ground data processing for the Earth Observing System, is projected to be quite large (in the 50 to 100 gigaFLOPS range) and corespondingly very expensive to perform using conventional supercomputer systems. High performance, general purpose massively parallel computer systems such as the MasPar MP-1 are being investigated by NASA as a more cost effective alternative. Massively parallel systems are targeted for accelerated development and maturation by NASA's upcoming five-year High Performance Computing and Communications Program. A summary of the broad range of applications currently running on the MP-1 at NASA/Goddard are presented in this paper along with descriptions of the parallel algorithmic techniques employed in five applications that have bearing on Earth sciences.

Fischer, James R.↗
NASA NTRSDate not supplied

Field-Programmable Gate Array Implementation of a Single Photon-Counting Receive Modem

We present a field-programmable gate array (FPGA) implementation of a single photon-counting receive modem for a pulse position modulated signal. The modem is compliant with the Consultative Committee for Space Data Systems (CCSDS) High Photon Efficiency (HPE) Optical Communications Coding and Synchronization standard and is capable of a maximum data rate of 267 Mbps. The system is designed on a commercial off-the-shelf FPGA platform and utilizes superconducting nanowire single photon counting detectors, analog to digital converters (ADC s) to sample the detectors, and two FPGAs. Symbol timing recovery, photon counting, convolutional deinterleaving, and codeword synchronization areis performed in the first FPGA. The second FPGA performs iterative decoding on each codeword of the serially concatenated pulse position modulated (SCPPM) signal. A digital filter is included to compensate for timing jitter of the detector, and the decoder throughput can be modified adjusted through reconfigurable parallelization. The decoder also implements a resource-efficient, algorithmic polynomial interleaver and deinterleaver. Both FPGAs can be reconfigured to switch between pulse position modulation (PPM)-16 and PPM-32 with code rates 1/3, 1/2, and 2/3. In this paper, we describe the receiver architecture and FPGA implementation of the timing recovery loop and SCPPM decoder, FPGA utilization for the different modes, and receive modem characterization test results.

Field-programmable Gate Array↗
DOE OSTI2021

A k-mer based approach for classifying viruses without taxonomy identifies viral associations in human autism and plant microbiomes

Viruses are an underrepresented taxa in the study and identification of microbiome constituents; however, they play an essential role in health, microbiome regulation, and transfer of genetic material. Only a few thousand viruses have been isolated, sequenced, and assigned a taxonomy, which limits the ability to identify and quantify viruses in the microbiome. Additionally, the vast diversity of viruses represents a challenge for classification, not only in constructing a viral taxonomy, but also in identifying similarities between a virus’ genotype and its phenotype. However, the diversity of viral sequences can be leveraged to classify their sequences in metagenomic and metatranscriptomic samples, even if they do not have a taxonomy. To identify and quantify viruses in transcriptomic and genomic samples, we developed a dynamic programming algorithm for creating a classification tree out of 715,672 metagenome viruses. To create the classification tree, we clustered proportional similarity scores generated from the k-mer profiles of each of the metagenome viruses to create a database of metagenomic viruses. The resulting Kraken2 database of the metagenomic viruses can be found here: https://www.osti.gov/biblio/1615774 and is compatible with Kraken2. We then integrated the viral classification database with databases created with genomes from NCBI for use with ParaKraken (a parallelized version of Kraken provided in Supplemental Zip 1), a metagenomic/transcriptomic classifier. To illustrate the breadth of our utility for classifying metagenome viruses, we analyzed data from a plant metagenome study identifying genotypic and compartment specific differences between two Populus genotypes in three different compartments. We also identified a significant increase in abundance of eight viral sequences in post mortem brains in a human metatranscriptome study comparing Autism Spectrum Disorder patients and controls. We also show the potential accuracy for classifying viruses by utilizing both the JGI and NCBI viral databases to identify the uniqueness of viral sequences. Finally, we validate the accuracy of viral classification with NCBI databases containing viruses with taxonomy to identify pathogenic viruses in known COVID-19 and cassava brown streak virus infection samples. Our method represents the compulsory first step in better understanding the role of viruses in the microbiome by allowing for a more complete identification of sequences without taxonomy. Better classification of viruses will improve identifying associations between viruses and their hosts as well as viruses and other microbiome members. Despite the lack of taxonomy, this database of metagenomic viruses can be used with any tool that utilizes a taxonomy, such as Kraken, for accurate classification of viruses.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

OPER: Optimality-Guided Embedding Table Parallelization for Large-scale Recommendation Model

With the sharp increasing volume of user data, Deep Learning Recommendation Model (DLRM) becomes an indispensable infrastructure in large technology companies. However, large-scale DLRM on the multi-GPU platform is still inefficient due to unbalanced workload partitioning and intensive inter-GPU communication. To this end, we propose OPER, an OPtimality guided Embedding table placement for large-scale Recommendation model training and inference. OPER explores the potential of mitigating remote memory access latency in DLRM through fine-grained embedding table placement. Specifically, OPER proposes a theoretical modeling that builds up the relationship between EMT placement and the embedding communication latency in both training and inference. OPER proves the NP hardness of finding the optimal embedding table placement and proposes a heuristic algorithm that yields near optimal placement. OPER implements a SHMEM-based embedding table training system and a unified embedding index mapping to support fine-grained embedding table sharding and placement. Comprehensive experiments reveal that OPER achieves on average 3.4× and 5.1× speedup on training and inference respectively over state-of-the-art DLRM frameworks.

Wang, Zheng↗
DOE OSTI2025

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↗
DOE OSTI2024

Accelerated Constrained Sparse Tensor Factorization on Massively Parallel Architectures

This study presents the first constrained sparse tensor factorization (cSTF) framework that optimizes and fully offloads computation to massively parallel GPU architectures, and the first performance characterization of cSTF on GPU architectures. In contrast to prior work on tensor factorization, where the matricized tensor times Khatri-Rao product (MTTKRP) is the primary performance bottleneck, our systematic analysis of the cSTF algorithm on GPUs reveals that adding constraints creates an additional bottleneck in the update operation for many real-world sparse tensors. While executing the update operation on the GPU brings significant speedup over its CPU counterpart, it remains a significant bottleneck. To further accelerate the update operation, we propose cuADMM, a new update algorithm that leverages algorithmic and code optimization strategies to minimize both computation and data movement on GPUs. As a result, our framework delivers significantly improved performance compared to prior state-of-the-art. On 10 real-world sparse tensors, our framework achieves geometric mean speedup of 5.1 × (max 41.59 ×) and 7.01 × (max 58.05 ×) on the NIVIDA A100 and H100 GPUs, respectively, over the state-of-the-art SPLATT library running on a 26-core Intel Ice Lake Xeon CPU.

Soh, Yongseok↗
NASA NTRS2000

Parallel Conjugate Gradient: Effects of Ordering Strategies, Programming Paradigms, and Architectural Platforms

The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. A sparse matrix-vector multiply (SPMV) usually accounts for most of the floating-point operations within a CG iteration. In this paper, we investigate the effects of various ordering and partitioning strategies on the performance of parallel CG and SPMV using different programming paradigms and architectures. Results show that for this class of applications, ordering significantly improves overall performance, that cache reuse may be more important than reducing communication, and that it is possible to achieve message passing performance using shared memory constructs through careful data ordering and distribution. However, a multi-threaded implementation of CG on the Tera MTA does not require special ordering or partitioning to obtain high efficiency and scalability.

Oliker, Leonid↗
NASA NTRS1991

3-D CFD in a day - The laser digitizer project

The computation of airflow over complex configurations requires a complete description of the geometry. This can be obtained from CAD data, from blueprints, or from actual models. In any case, the time required is currently estimated at 4 to 6 months. It is proposed to shorten this time by a factor of 10 to 100 through the use of automated software, a fast, highly parallel computer and a three-dimensional laser digitizer. This device can provide (x,y,z) coordinates of surface points at rates exceeding 14,500/sec. Thus, it is possible to digitize an entire model in a few minutes. The accuracy of measurement on a flat white surface is better than 0.005 inches. Higher accuracy is available at higher cost. This work discusses the challenges which remain to be addressed. In particular, the surface point data need to be converted into a surface description, the surface description needs to be made into a surface grid, and the surface grid used to make a volume grid for the flow solver. Algorithms are kept in place or in mind for all of these problems. Integration of the more mature flow solution and visualization algorithms then allows generation of solution graphics directly from a wind tunnel model.

Merriam, Marshal↗
NASA NTRS2025

Mission-Maps For Outbound Cislunar Transfer Trajectories

This study quantifies the robustness and sensitivity of an outbound cislunar trajectory for a lunar lander in the form of mission-maps, or topological maps that allows either a computer program or mission designer to intuitively optimize the placement of critical outbound correction burns from the derived sensitivity data. The non-linear multi-body dynamics are applied to generate an outbound cislunar reference profile used by a linear covariance analysis (LinCov) tool to compute the expected Δv and trajectory dispersions due to the initial state uncertainty, sensor errors, maneuver execution errors, and disturbance accelerations along the outbound cislunar profile. The rapid performance analysis capabilities of LinCov are complimented with parallel processing techniques to evaluate hundreds and thousands of different translational burn locations, placements, and targeting constraints to identify the combination that minimizes the total Δv usage (nominal plus 3σ Δv) and trajectory dispersions at lunar orbit insertion. This study utilizes a generalized reference targeting algorithm to quickly assess the integrated closed-loop GN&C system performance due to different targeting configurations and constraints. The resulting mission maps provide an intuitive insight to ascertain each trajectory correction maneuver’s (TCM) sensitivity to different burn times along an outbound cislunar trajectory and quickly identify desirable engineering tradeoffs when performing analysis on the number and placement of these burns that nominally zero. Multiple mission maps are generated for a variety of different performance parameters that allow engineers to visually identify optimal solutions for trajectory correction maneuver placements, the number of correction burns, and the targeting constraints for each burn.

GN&C↗
DOE OSTI2024

GPU-enabled extreme-scale turbulence simulations: Fourier pseudo-spectral algorithms at the exascale using OpenMP offloading

Fourier pseudo-spectral methods for nonlinear partial differential equations are of wide interest in many areas of advanced computational science, including direct numerical simulation of three-dimensional (3-D) turbulence governed by the Navier-Stokes equations in fluid dynamics. This paper presents a new capability for simulating turbulence at a new record resolution up to 35 trillion grid points, on the world's first exascale computer, Frontier, comprising AMD MI250x GPUs with HPE's Slingshot interconnect and operated by the US Department of Energy's Oak Ridge Leadership Computing Facility (OLCF). Key programming strategies designed to take maximum advantage of the machine architecture involve performing almost all computations on the GPU which has the same memory capacity as the CPU, performing all-to-all communication among sets of parallel processes directly on the GPU, and targeting GPUs efficiently using OpenMP offloading for intensive number-crunching including 1-D Fast Fourier Transforms (FFT) performed using AMD ROCm library calls. With 99% of computing power on Frontier being on the GPU, leaving the CPU idle leads to a net performance gain via avoiding the overhead of data movement between host and device except when needed for some I/O purposes. Memory footprint including the size of communication buffers for MPI_ALLTOALL is managed carefully to maximize the largest problem size possible for a given node count. Detailed performance data including separate contributions from different categories of operations to the elapsed wall time per step are reported for five grid resolutions, from 2048 3 on a single node to 32768 3 on 4096 or 8192 nodes out of 9408 on the system. Both 1D and 2D domain decompositions which divide a 3D periodic domain into slabs and pencils respectively are implemented. The present code suite (labeled by the acronym GESTS, GPUs for Extreme Scale Turbulence Simulations) achieves a figure of merit (in grid points per second) exceeding goals set in the Center for Accelerated Application Readiness (CAAR) program for Frontier. The performance attained is highly favorable in both weak scaling and strong scaling, with notable departures only for 2048 3 where communication is entirely intra-node, and for 32768 3 , where a challenge due to small message sizes does arise. Communication performance is addressed further using a lightweight test code that performs all-to-all communication in a manner matching the full turbulence simulation code. Performance at large problem sizes is affected by both small message size due to high node counts as well as dragonfly network topology features on the machine, but is consistent with official expectations of sustained performance on Frontier. Overall, although not perfect, the scalability achieved at the extreme problem size of 32768 3 (and up to 8192 nodes — which corresponds to hardware rated at just under 1 exaflop/sec of theoretical peak computational performance) is arguably better than the scalability observed using prior state-of-the-art algorithms on Frontier's predecessor machine (Summit) at OLCF. New science results for the study of intermittency in turbulence enabled by this code and its extensions are to be reported separately in the near future.

3D fast Fourier transform↗