Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Data parallelism”

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 847 records · Page 47
All sourcesNASA NTRSDOE OSTI
NASA NTRS1983

Apparent electrostatic ion cyclotron waves in the diffuse aurora

Emissions that have properties consistent with electrostatic ion cyclotron (EIC) waves have been observed at low altitude in the diffuse aurora by a sounding rocket payload. Peaks were observed in the power spectrum of the electric field near the hydrogen and oxygen ion cyclotron frequencies. Doppler shift and polarization analyses have been performed using EIC wave parameters derived from linear theory. Both analyses indicated that these emissions had properties consistent with those expected for H(+) and O(+) EIC waves. The two analyses indicated that both emission bands were due to waves propagating eastward parallel to the poleward boundary of the diffuse aurora. The large local cold plasma density and resulting Landau damping require that the source be local. Magnetometer data indicated the presence of a downward parallel current density of 5 microamps/sq m. Sufficient free energy for the waves was available from this current, although the waves were observed frequently at altitudes where the ion-neutral collision frequency exceeded the oxygen cyclotron frequency.

Bering, E. A.↗
DOE OSTI2024

Distributed Augmentation, Hypersweeps, and Branch Decomposition of Contour Trees for Scientific Exploration

Contour trees describe the topology of level sets in scalar fields and are widely used in topological data analysis and visualization. A main challenge of utilizing contour trees for large-scale scientific data is their computation at scale using highperformance computing. To address this challenge, recent work has introduced distributed hierarchical contour trees for distributed computation and storage of contour trees. However, effective use of these distributed structures in analysis and visualization requires subsequent computation of geometric properties and branch decomposition to support contour extraction and exploration. In this work, we introduce distributed algorithms for augmentation, hypersweeps, and branch decomposition that enable parallel computation of geometric properties, and support the use of distributed contour trees as query structures for scientific exploration. Finally, we evaluate the parallel performance of these algorithms and apply them to identify and extract important contours for scientific visualization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

The Persistent Challenge of Data Locality in the Post-Exascale Era

The era of exascale computing, exemplified by systems like Frontier achieving exaflop-level performance, marks a milestone. However, the quest for sheer compute power leads to strong imbalance in system design. Hence, scaling advancements in memory, network bandwidth, and storage are also necessary and pose challenges, with a crucial need to address data locality issues. This article underscores the fundamental importance of data locality as a key abstraction for optimizing application performance. Despite notable software solutions, the growing complexity of parallelism and memory hierarchy demands performance-portable data locality solutions across diverse computing platforms. Additionally, the article revisits data locality aspects, covering hardware considerations, application perspectives, software stack abstractions, and tool support. It concludes with insights into data locality challenges and opportunities, emphasizing the ongoing significance of collaborative research for progress in this critical issue.

Unat, Didem [Koc University, Istanbul (Turkey)] (O↗
DOE OSTI2020

Large Scale Tensor Factorization via Parallel Sketches

Tensor factorization methods have recently gained increased popularity. A key feature that renders tensors attractive is the ability to directly model multi-relational data. In this work, we propose ParaSketch, a parallel tensor factorization algorithm that enables massive parallelism, to deal with large tensors. The idea is to compress the large tensor into multiple small tensors, decompose each small tensor in parallel, and combine the results to reconstruct the desired latent factors. Prior art in this direction entails potentially very high complexity in the (Gaussian) compression and final combining stages. Adopting sketching matrices for compression, the proposed method enjoys a dramatic reduction in compression complexity, and features a much lighter combining step. Moreover, theoretical analysis shows that the compressed tensors inherit latent identifiability under mild conditions, hence establishing correctness of the overall approach. Numerical experiments corroborate the theory and demonstrate the effectiveness of the proposed algorithm.

block term decomposition↗
DOE OSTI2020

Understanding performance variability in standard and pipelined parallel Krylov solvers

In this work, we collect data from runs of Krylov subspace methods and pipelined Krylov algorithms in an effort to understand and model the impact of machine noise and other sources of variability on performance. We find large variability of Krylov iterations between compute nodes for standard methods that is reduced in pipelined algorithms, directly supporting conjecture, as well as large variation between statistical distributions of runtimes across iterations. Based on these results, we improve upon a previously introduced nondeterministic performance model by allowing iterations to fluctuate over time. We present our data from runs of various Krylov algorithms across multiple platforms as well as our updated non-stationary model that provides good agreement with observations. We also suggest how it can be used as a predictive tool.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1982

Improved Parallel-Access Alinement Network

Network channels elements of data array from memory ports to processor ports using a hardware-generated binary control work. Depending on control work selected, data may be shifted in increments or transposed in each of three levels to reach appropriate processing ports. A similar arrangement with reversed wiring is used to return data from processing ports to respective memory modules. Selection gate used in network incorporates two AND gates feeding an OR gate. In some logic families the OR gate may be fabricated as a "wired OR".

Barnes, G. H.↗
NASA NTRS1998

A Theoretical and Observational Study of Large and Small-Scale Dynamics in the Mesosphere and Lower Thermosphere in Support of TIMED

The long-term objectives of this IDS component of the TIMED mission are to define, through a combination of modeling and data analysis efforts, the influences of large- and small-scale waves (tidal, planetary, and gravity waves) on the circulation, structure, composition, and variability of the mesosphere and lower thermosphere. Particular emphasis is aimed at the TIMED core science objectives of defining the structure and energetics of the TIMED core region, approx. 60 to 180 km. To do so, however, it is also essential to understand the dynamical influences and contributions because of their considerable direct and indirect influences on structure and energetics. To accomplish these goals, we anticipate two parallel modeling efforts and a significant data analysis effort following TIMED launch. The modeling efforts will address both: the residual circulation response to mean and variable wave forcing of the MLT through development of a spherical model addressing balanced flow dynamics and transience and a more comprehensive effort addressing gravity wave propagation, interactions, nonlinearity, and spectral evolution and transports in canonical and realistic environments. The data analysis effort is envisioned to involve application of ground-based measurements and TIMED data analyses to a quantification of gravity wave forcing and effects at one or more sites with comprehensive measurement suites and extension of the inferred forcing globally, based on distributed ground-based measurements. Research results and publications resulting from the research are included.

Fritts, David C.↗
DOE OSTI2021

PLANC: Parallel Low-rank Approximation with Nonnegativity Constraints

In this work, we consider the problem of low-rank approximation of massive dense nonnegative tensor data, for example, to discover latent patterns in video and imaging applications. As the size of data sets grows, single workstations are hitting bottlenecks in both computation time and available memory. We propose a distributed-memory parallel computing solution to handle massive data sets, loading the input data across the memories of multiple nodes, and performing efficient and scalable parallel algorithms to compute the low-rank approximation. We present a software package called Parallel Low-rank Approximation with Nonnegativity Constraints, which implements our solution and allows for extension in terms of data (dense or sparse, matrices or tensors of any order), algorithm (e.g., from multiplicative updating techniques to alternating direction method of multipliers), and architecture (we exploit GPUs to accelerate the computation in this work). We describe our parallel distributions and algorithms, which are careful to avoid unnecessary communication and computation, show how to extend the software to include new algorithms and/or constraints, and report efficiency and scalability results for both synthetic and real-world data sets.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1996

Air Traffic Complexity Measurement Environment (ACME): Software User's Guide

A user's guide for the Air Traffic Complexity Measurement Environment (ACME) software is presented. The ACME consists of two major components, a complexity analysis tool and user interface. The Complexity Analysis Tool (CAT) analyzes complexity off-line, producing data files which may be examined interactively via the Complexity Data Analysis Tool (CDAT). The Complexity Analysis Tool is composed of three independently executing processes that communicate via PVM (Parallel Virtual Machine) and Unix sockets. The Runtime Data Management and Control process (RUNDMC) extracts flight plan and track information from a SAR input file, and sends the information to GARP (Generate Aircraft Routes Process) and CAT (Complexity Analysis Task). GARP in turn generates aircraft trajectories, which are utilized by CAT to calculate sector complexity. CAT writes flight plan, track and complexity data to an output file, which can be examined interactively. The Complexity Data Analysis Tool (CDAT) provides an interactive graphic environment for examining the complexity data produced by the Complexity Analysis Tool (CAT). CDAT can also play back track data extracted from System Analysis Recording (SAR) tapes. The CDAT user interface consists of a primary window, a controls window, and miscellaneous pop-ups. Aircraft track and position data is displayed in the main viewing area of the primary window. The controls window contains miscellaneous control and display items. Complexity data is displayed in pop-up windows. CDAT plays back sector complexity and aircraft track and position data as a function of time. Controls are provided to start and stop playback, adjust the playback rate, and reposition the display to a specified time.

Source record↗
DOE OSTI2025

HPDR: High-Performance Portable Scientific Data Reduction Framework

The rapid growth in scientific data generation is outpacing advancements in computing systems necessary for efficient storage, transfer, and analysis, particularly in the context of exascale computing. With the deployment of first-generation exascale computing systems and next-generation experimental facilities, this gap is widening and necessitates effective data reduction techniques to manage enormous data volumes. Over the past decade, various data reduction methods, including lossless compression, error-controlled lossy compression, and data refactoring, have been developed to accelerate I/O in scientific workflows. Despite significant reductions in data volume, these methods introduce considerable computational overhead, which can become the new bottleneck in data processing. To mitigate this, GPU-accelerated data reduction algorithms have been introduced. However, challenges remain in their integration into exascale workflows, including limited portability across different GPU architectures, substantial memory transfer overhead, and reduced scalability on dense multi-GPU systems. To address these challenges, we propose HPDR, a high-performance and portable data reduction framework. HPDR is designed to enable the execution of state-of-the-art reduction algorithms across diverse processor architectures while reducing memory transfer overhead to 2.3 % of the original, resulting in up to 3.5× faster throughput compared to existing solutions. It also achieves up to 96% of the theoretical speedup in multi-GPU settings. In addition, evaluations on accelerating I/O operations at scale up to 1,024 nodes of the Frontier supercomputer demonstrate that HPDR can achieve up to 103 TB/s reduction throughput, providing up to 4× acceleration in parallel I/O performance compared to existing data reduction routines. This work highlights the potential of HPDR to significantly enhance data reduction efficiency in exascale computing environments.

Chen, Jieyang [University of Oregon]↗
NASA NTRS1988

National full-scale aerodynamic complex integrated systems test data system

The data acquisition system of the 80 by 120 foot wind tunnel of the National Full-Scale Aerodynamic Facility (NFAC) is described. How the various satellite data stations are connected to the data acquisition system is shown. As an illustrative example, a strain gage signal is traced from one of the satellite data locations to its final destination in the data system where the signal is processed, observed in real time on various parallel graphic displays, and stored on magnetic disks for postrun data reduction.

Jung, Oscar↗
DOE OSTI2022

Parthenon—a performance portable block-structured adaptive mesh refinement framework

On the path to exascale the landscape of computer device architectures and corresponding programming models has become much more diverse. While various low-level performance portable programming models are available, support at the application level lacks behind. To address this issue, we present the performance portable block-structured adaptive mesh refinement (AMR) framework Parthenon, derived from the well-tested and widely used Athena++ astrophysical magnetohydrodynamics code, but generalized to serve as the foundation for a variety of downstream multi-physics codes. Parthenon adopts the Kokkos programming model, and provides various levels of abstractions from multidimensional variables, to packages defining and separating components, to launching of parallel compute kernels. Parthenon allocates all data in device memory to reduce data movement, supports the logical packing of variables and mesh blocks to reduce kernel launch overhead, and employs one-sided, asynchronous MPI calls to reduce communication overhead in multi-node simulations. Using a hydrodynamics miniapp, we demonstrate weak and strong scaling on various architectures including AMD and NVIDIA GPUs, Intel and AMD x86 CPUs, IBM Power9 CPUs, as well as Fujitsu A64FX CPUs. At the largest scale on Frontier (the first TOP500 exascale machine), the miniapp reaches a total of 1.7 × 10 13 zone-cycles/s on 9216 nodes (73,728 logical GPUs) at [Formula: see text] weak scaling parallel efficiency (starting from a single node). In combination with being an open, collaborative project, this makes Parthenon an ideal framework to target exascale simulations in which the downstream developers can focus on their specific application rather than on the complexity of handling massively-parallel, device-accelerated AMR.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A Block-Based Triangle Counting Algorithm on Heterogeneous Environments

Triangle counting is a fundamental building block in graph algorithms. In this article, we propose a block-based triangle counting algorithm to reduce data movement during both sequential and parallel execution. Our block-based formulation makes the algorithm naturally suitable for heterogeneous architectures. The problem of partitioning the adjacency matrix of a graph is well-studied. Our task decomposition goes one step further: it partitions the set of triangles in the graph. By streaming these small tasks to compute resources, we can solve problems that do not fit on a device. We demonstrate the effectiveness of our approach by providing an implementation on a compute node with multiple sockets, cores and GPUs. The current state-of-the-art in triangle enumeration processes the Friendster graph in 2.1 seconds, not including data copy time between CPU and GPU. Using that metric, our approach is 20 percent faster. When copy times are included, our algorithm takes 3.2 seconds. This is 5.6 times faster than the fastest published CPU-only time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

A Block-Based Triangle Counting Algorithm on Heterogeneous Environments

Triangle counting is a fundamental building block in graph algorithms. In this paper, we propose a block-based triangle counting algorithm to reduce data movement during both sequential and parallel execution. Our block-based formulation makes the algorithm naturally suitable for heterogeneous architectures. The problem of partitioning the adjacency matrix of a graph is well-studied. Our task decomposition goes one step further: it partitions the set of triangles in the graph. By streaming these small tasks to compute resources, we can solve problems that do not fit on a device. We demonstrate the effectiveness of our approach by providing an implementation on a compute node with multiple sockets, cores and GPUs. The current state-of-the-art in triangle enumeration processes the Friendster graph in 2.1 seconds, not including data copy time between CPU and GPU. Using that metric, our approach is 20 percent faster. When copy times are included, our algorithm takes 3.2 seconds. This is 5.6 times faster than the fastest published CPU-only time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Towards Lightweight Data Integration Using Multi-Workflow Provenance and Data Observability

Modern large-scale scientific discovery requires multidisciplinary collaboration across diverse computing facilities, including High Performance Computing (HPC) machines and the Edge-to-Cloud continuum. Integrated data analysis plays a crucial role in scientific discovery, especially in the current AI era, by enabling Responsible AI development, FAIR, Reproducibility, and User Steering. However, the heterogeneous nature of science poses challenges such as dealing with multiple supporting tools, cross-facility environments, and efficient HPC execution. Building on data observability, adapter system design, and provenance, we propose MIDA: an approach for lightweight runtime Multi-workflow Integrated Data Analysis. MIDA defines data observability strategies and adaptability methods for various parallel systems and machine learning tools. With observability, it intercepts the dataflows in the background without requiring instrumentation while integrating domain, provenance, and telemetry data at runtime into a unified database ready for user steering queries. We conduct experiments showing end-to-end multi-workflow analysis integrating data from Dask and MLFlow in a real distributed deep learning use case for materials science that runs on multiple environments with up to 276 GPUs in parallel. We show near-zero overhead running up to 100,000 tasks on 1,680 CPU cores on the Summit supercomputer.

Santos Souza, Renan↗
NASA NTRS2001

Automation of Data Traffic Control on DSM Architecture

The design of distributed shared memory (DSM) computers liberates users from the duty to distribute data across processors and allows for the incremental development of parallel programs using, for example, OpenMP or Java threads. DSM architecture greatly simplifies the development of parallel programs having good performance on a few processors. However, to achieve a good program scalability on DSM computers requires that the user understand data flow in the application and use various techniques to avoid data traffic congestions. In this paper we discuss a number of such techniques, including data blocking, data placement, data transposition and page size control and evaluate their efficiency on the NAS (NASA Advanced Supercomputing) Parallel Benchmarks. We also present a tool which automates the detection of constructs causing data congestions in Fortran array oriented codes and advises the user on code transformations for improving data traffic in the application.

Frumkin, Michael↗
DOE OSTI2026

Pion and kaon PDFs from lattice QCD via large momentum effective theory and short-distance factorization

In this paper, we present a first-principles lattice-QCD calculation of the unpolarized quark PDF for the pion and the kaon. The lattice data rely on matrix elements calculated for boosted mesons coupled to non-local operators containing a Wilson line. The calculations on this lattice ensemble correspond to two degenerate light, a strange, and a charm quark (𝑁 𝑓 = 2 + 1 + 1), using maximally twisted mass fermions with a clover term. The lattice volume is 32 3 × 64, with a lattice spacing of 0.0934 fm, and a pion mass of 260 MeV. Matrix elements are calculated for hadron boosts of |𝑃 3 | = 0, 0.41, 0.83, 1.25, 1.66, and 2.07 GeV. To match lattice QCD results to their light-cone counterparts, we employ two complementary frameworks: the large-momentum effective theory (LaMET) and the short-distance factorization (SDF). Using these approaches in parallel, we also test the lattice data to identify methodology-driven systematics. Results are presented for the standard quark PDFs, as well as the valence sector. Beyond obtaining the PDFs, we also explore the possibility of extracting information on SU(3) flavor-symmetry-breaking effects. For LaMET, we also parametrize the momentum dependence to obtain the infinite-momentum PDFs. Since the present calculation is performed on a single ensemble at a pion mass of 260 MeV and fixed lattice spacing, the uncertainties reported are statistical only, and systematic uncertainties remain to be addressed in future multi-ensemble studies.

Miller, Joshua [Temple University, Philadelphia, P↗