Search NASA⌕ Search

SEARCH · Search NASA

Results for “task 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 505 records · Page 28
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Locality-aware and load-balanced static task scheduling for MapReduce

Task scheduling for MapReduce jobs has been an active area of research with the objective of decreasing the amount of data transferred during the shuffle phase via exploiting data locality. In the literature, generally only the scheduling of reduce tasks is considered with the assumption that scheduling of map tasks is already determined by the input data placement. However, in cloud or HPC deployments of MapReduce, the input data is located in a remote storage and scheduling map tasks gains importance. Here, we propose models for simultaneous scheduling of map and reduce tasks in order to improve data locality and balance the processors’ loads in both map and reduce phases. Our approach is based on graph and hypergraph models which correctly encode the interactions between map and reduce tasks. Partitions produced by these models are decoded to schedule map and reduce tasks. A two-constraint formulation utilized in these models enables balancing processors’ loads in both map and reduce phases. The partitioning objective in the hypergraph models correctly encapsulates the minimization of data transfer when a local combine step is performed prior to shuffle, whereas the partitioning objective in the graph models achieve the same feat when a local combine is not performed. Here, we show the validity of our scheduling on the MapReduce parallelizations of two important kernel operations – sparse matrix–vector multiplication (SpMV) and generalized sparse matrix–matrix multiplication (SpGEMM) – that are widely encountered in big data analytics and scientific computations. Compared to random scheduling, our models lead to tremendous savings in data transfer by reducing data traffic from several hundreds of megabytes to just a few megabytes in the shuffle phase and consequently leading up to 2.6x and 4.2x speedup for SpMV and SpGEMM, respectively.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training

Distributed training increases the number of batches processed per iteration either by scaling-out (adding more nodes) or scaling-up (increasing the batch-size). However, the largest configuration does not necessarily yield the best performance. Horizontal scaling introduces additional communication overhead, while vertical scaling is constrained by computation cost and device memory limits. Thus, simply increasing the batch-size leads to diminishing returns: training time and cost decrease initially but eventually plateaus, creating a knee-point in the time/cost vs. batch-size pareto curve. The optimal batch-size therefore depends on the underlying model, data and available compute resources. Large batches also suffer from worse model quality due to the well-known “generalization gap”. In this paper, we present Tula, an online service that automatically optimizes time, cost, and convergence quality for large-batch training of convolutional models. It combines parallel-systems modeling with statistical performance prediction to identify the optimal batchsize. Tula predicts training time and cost within 7.5−14% error across multiple models, and achieves up to 20× overall speedup and improves test accuracy by ≈9% on average over standard large-batch training on various vision tasks, thus successfully mitigating the generalization gap and accelerating training at the same time.

Tyagi, Sahil [ORNL] (ORCID:0009000783144745)↗
DOE OSTI2024

Alfalfa Virtual Building Service: Software Engineering Best Practices Applied to Runtime Interaction with Building Energy Models

Buildings are active participants in increasingly complex energy systems. Building Energy Modeling (BEM) has a key role to play in planning and de-risking an equitable energy transition, with BEM-backed "virtual buildings" critical path for diverse applications that include workforce training tools, Hardware-in-the-Loop (HIL) experimentation to study equipment performance under a range of conditions, Control-Hardware-in-the-Loop (CHIL) experimentation to de-risk commercial control implementations at equipment through grid orchestration levels, and integration of dynamic load profiles into grid modeling tools for energy system experimentation at the urban scale. Modeling requirements vary across these applications, but many software engineering tasks do not. The Alfalfa Virtual Building Service (AVBS, see https://github.com/NREL/alfalfa/wiki) is an open-source web service that solves these common tasks robustly in one place, providing a foundational platform for power users to bootstrap their own applications. AVBS abstracts the specifics of runtime interaction with OpenStudio, Modelica, and Spawn of EnergyPlus models behind a unified REST API. Additionally, AVBS provides resources for cloud deployment and scaling to 100s of parallel simulations, a growing library of modular Operational Technology (OT) integrations for emulation of real-world interfaces, and scripts to automate the population of communities of virtual buildings from URBANopt, ResStock and ComStock.

building automation↗
DOE OSTI2014

PETSc Users Manual (Rev. 3.4)

This manual describes the use of PETSc for the numerical solution of partial differential equations and related problems on high-performance computers. The Portable, Extensible Toolkit for Scientific Computation (PETSc) is a suite of data structures and routines that provide the building blocks for the implementation of large-scale application codes on parallel (and serial) computers. PETSc uses the MPI standard for all message-passing communication. PETSc includes an expanding suite of parallel linear, nonlinear equation solvers and time integrators that may be used in application codes written in Fortran, C, C++, Python, and MATLAB (sequential). PETSc provides many of the mechanisms needed within parallel application codes, such as parallel matrix and vector assembly routines. The library is organized hierarchically, enabling users to employ the level of abstraction that is most appropriate for a particular problem. By using techniques of object-oriented programming, PETSc provides enormous flexibility for users. PETSc is a sophisticated set of software tools; as such, for some users it initially has a much steeper learning curve than a simple subroutine library. In particular, for individuals without some computer science background, experience programming in C, C++ or Fortran and experience using a debugger such as gdb or dbx, it may require a significant amount of time to take full advantage of the features that enable efficient software use. However, the power of the PETSc design and the algorithms it incorporates may make the efficient implementation of many application codes simpler than “rolling them” yourself; For many tasks a package such as MATLAB is often the best tool; PETSc is not intended for the classes of problems for which effective MATLAB code can be written. PETSc also has a MATLAB interface, so portions of your code can be written in MATLAB to “try out” the PETSc solvers. The resulting code will not be scalable however because currently MATLAB is inherently not scalable; and PETSc should not be used to attempt to provide a “parallel linear solver” in an otherwise sequential code. Certainly all parts of a previously sequential code need not be parallelized but the matrix generation portion must be parallelized to expect any kind of reasonable performance. Do not expect to generate your matrix sequentially and then “use PETSc” to solve the linear system in parallel. Since PETSc is under continued development, small changes in usage and calling sequences of routines will occur. PETSc is supported; see the web site http://www.mcs.anl.gov/petsc for information on contacting support. A http://www.mcs.anl.gov/petsc/publications may be found a list of publications and web sites that feature work involving PETSc. We welcome any reports of corrections for this document.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

PETSc Users Manual (Rev. 3.5)

This manual describes the use of PETSc for the numerical solution of partial differential equations and related problems on high-performance computers. The Portable, Extensible Toolkit for Scientific Computation (PETSc) is a suite of data structures and routines that provide the building blocks for the implementation of large-scale application codes on parallel (and serial) computers. PETSc uses the MPI standard for all message-passing communication. PETSc includes an expanding suite of parallel linear, nonlinear equation solvers and time integrators that may be used in application codes written in Fortran, C, C++, Python, and MATLAB (sequential). PETSc provides many of the mechanisms needed within parallel application codes, such as parallel matrix and vector assembly routines. The library is organized hierarchically, enabling users to employ the level of abstraction that is most appropriate for a particular problem. By using techniques of object-oriented programming, PETSc provides enormous flexibility for users. PETSc is a sophisticated set of software tools; as such, for some users it initially has a much steeper learning curve than a simple subroutine library. In particular, for individuals without some computer science background, experience programming in C, C++ or Fortran and experience using a debugger such as gdb or dbx, it may require a significant amount of time to take full advantage of the features that enable efficient software use. However, the power of the PETSc design and the algorithms it incorporates may make the efficient implementation of many application codes simpler than “rolling them” yourself. ;For many tasks a package such as MATLAB is often the best tool; PETSc is not intended for the classes of problems for which effective MATLAB code can be written. PETSc also has a MATLAB interface, so portions of your code can be written in MATLAB to “try out” the PETSc solvers. The resulting code will not be scalable however because currently MATLAB is inherently not scalable; and PETSc should not be used to attempt to provide a “parallel linear solver” in an otherwise sequential code. Certainly all parts of a previously sequential code need not be parallelized but the matrix generation portion must be parallelized to expect any kind of reasonable performance. Do not expect to generate your matrix sequentially and then “use PETSc” to solve the linear system in parallel. Since PETSc is under continued development, small changes in usage and calling sequences of routines will occur. PETSc is supported; see the web site http://www.mcs.anl.gov/petsc for information on contacting support. A http://www.mcs.anl.gov/petsc/publications may be found a list of publications and web sites that feature work involving PETSc. We welcome any reports of corrections for this document.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

A view into FleCSI [Slides]

FleCSI is largely based around sharing of memory spaces. FleCSI facilitates parallel execution and sharing of memory across memory spaces. Execute() transforms sender-side data structures into receiver-side data structures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

CMS event processing multi-core efficiency status

In 2015, CMS was the first LHC experiment to begin using a multi-threaded framework for doing event processing. This new framework utilizes Intel’s Thread Building Block library to manage concurrency via a task based processing model. During the 2015 LHC run period, CMS only ran reconstruction jobs using multiple threads because only those jobs were sufficiently thread efficient. Recent work now allows simulation and digitization to be thread efficient. In addition, during 2015 the multi-threaded framework could run events in parallel but could only use one thread per event. Work done in 2016 now allows multiple threads to be used while processing one event. In this presentation we will show how these recent changes have improved CMS’s overall threading and memory efficiency and we will discuss work to be done to further increase those efficiencies.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2015

An Update on Improvements to NiCE Support for PROTEUS

The Department of Energy Office of Nuclear Energy's Nuclear Energy Advanced Modeling and Simulation (NEAMS) program has supported the development of the NEAMS Integrated Computational Environment (NiCE), a modeling and simulation workflow environment that provides services and plugins to facilitate tasks such as code execution, model input construction, visualization, and data analysis. This report details the development of workflows for the reactor core neutronics application, PROTEUS. This advanced neutronics application (primarily developed at Argonne National Laboratory) aims to improve nuclear reactor design and analysis by providing an extensible and massively parallel, finite-element solver for current and advanced reactor fuel neutronics modeling. The integration of PROTEUS-specific tools into NiCE is intended to make the advanced capabilities that PROTEUS provides more accessible to the nuclear energy research and development community. This report will detail the work done to improve existing PROTEUS workflow support in NiCE. We will demonstrate and discuss these improvements, including the development of flexible IO services, an improved interface for input generation, and the addition of advanced Fortran development tools natively in the platform.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Large language models for batteries

Large Language Models (LLMs) are advanced artificial intelligence systems capable of solving diverse tasks using language, reasoning, and external tools. Despite their growing deployment in academia and industry, their potential remains underexplored in battery research. This review presents a comprehensive overview of existing and emerging applications of LLMs in batterie field, addressing two critical questions: What can LLMs offer to support battery-related tasks, and how to develop more effective models for this purpose. We begin by outlining the principles of LLMs and criteria for selecting appropriate models and tools for battery research and development. We then explore their roles in text-mining, data interpretation, and the development of intelligent battery systems. In parallel, we discuss technical challenges, such as data standardizing and sharing, model evaluation, and tool integration. Lastly, we propose future research directions with short-, medium-, and long-term goals and highlight more broad perspectives for connecting experts and cross-disciplinary collaborations.

SoC↗
DOE OSTI2020

Scalable Asynchronous Domain Decomposition Solvers

We discuss how parallel implementations of linear iterative solvers generally alternate between phases of data exchange and phases of local computation. Increasingly large problem sizes and more heterogeneous compute architectures make load balancing and the design of low latency network interconnects that are able to satisfy the communication requirements of linear solvers very challenging tasks. In particular, global communication patterns such as inner products become increasingly limiting at scale. We explore the use of asynchronous communication based on one-sided Message Passing Interface primitives in the context of domain decomposition solvers. In particular, a scalable asynchronous two-level Schwarz method is presented. We discuss practical issues encountered in the development of a scalable solver and show experimental results obtained on a state-of-the-art supercomputer system that illustrate the benefits of asynchronous solvers in load balanced as well as load imbalanced scenarios. Using the novel method, we can observe speedups of up to four times over its classical synchronous equivalent.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Stack Trace Analysis Tool (STAT)

STAT is a light weight debugging tool that gathers and merges stack traces from all of the processes in a parallel application. STAT uses the MRNet tree based overlay network to broadcast commands from the tool front-end to the STAT daemons and for the front-end to gather the traces from the STAT daemons. As the traces propagate through the MRNet network tree, they are merged across all tasks to fonn a single call prefix tree. The call prefix tree can be examined to identify tuks with similar function call patterns and to delineate a small set of equivalence classes. A representative task from each of these classes can then be fed into a full feature debugger like TotalView for root cause analysis.

ECP↗
DOE OSTI2017

Stack Trace Ahalysis Tool

STAT is a light weight debugging tool that gathers and merges stack traces from all of the processes in a parallel application. STAT uses the MRNet tree based overlay network to broadcast commands from the tool front-end to the STAT daemons and for the front-end to gather the traces from the STAT daemons. As the traces propagate through the MRNet network tree, they are merged across all tasks to form a similar function call patterns and to delineate a small set of equivalence classes. A representative task from each of these classes can then be fed into a full feature debugger like TolalView for root cause analysis.

Lee, Gregory L.↗
DOE OSTI2019

EGS Collab Earth Modeling: Integrated 3D Model of the Testbed

The EGS Collab project is conducting a series of stimulation and interwell flow tests in an intermediate scale (~10-20 m) testbed located on the 4850 level in the Sanford Underground Research Facility (SURF) in Lead, South Dakota. The testbed consists of eight ~200 ft (~60 m) HQ-diameter (9.6 cm) boreholes that are drilled into the Poorman Formation from the western rib of the West Access Drift. Of the eight boreholes, one borehole is used as an injection/stimulation well, another sub-parallel borehole located about 10 m away from the injection well is used as a production well, and rest of the other boreholes are used as monitoring wells. For 3D visualization of the testbed as well as to provide spatially accurate and consistent parameter data for geomechanical and geophysical process modeling tasks, we are using Leapfrog Software (Seequent Limited). For analysis of fractures and creation of conditioned stochastic discrete fracture network (CS-DFN) model of the testbed, we are using FracMan (Golder Associates Inc.). As of mid-May 2019, the EGS Collab Leapfrog database contains the general layout of the drifts/shafts at the 4850 and 4100 levels; generalized geologic framework model of a domain that spans both the 4850 and 4100 levels; the CS-DFN of the testbed; and layouts of the EGS Collab testbed boreholes, kISMET testbed boreholes, and other existing boreholes at the 4850 level. This information has been obtained from the SURF Vulcan database, detailed laser scan and point surveys of borehole collar locations, directional surveys of borehole trajectories, and mapping of features in the drifts, boreholes, and cores. Similarly, other types of data that have been incorporated into the Leapfrog database include static features of the testbed such as natural discontinuities (e.g., fractures, weeps), location of monitoring instruments, and stimulation notches. Baseline geophysical characterization results (e.g., seismic, ERT, temperature, etc.) are also imported into the Leapfrog database. The location and size of packers, various point-source signals detected during stimulation and flow tests (e.g., temperature anomalies, micro-earthquake events, etc.) are also compiled in the database. All feature locations are reported using the local Homestake Mine coordinate system. In this paper, we present some of the geostructural characteristics as well as the status of the testbed as represented by Leapfrog/FracMan database/visualizations.

15 GEOTHERMAL ENERGY↗
DOE OSTI2016

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↗
DOE OSTI2022

LivermorE Al Projector for Computed Tomography Tasks

With recent computed tomography (CT) efforts using Artificial Intelligence (AI) and Deep Learning (DL)techniques, there is a strong need for differentiable forward projection models that can be integrated into existing DL frameworks. We developed a pytorch-based package library providing differentiable forward and back projection functions and classes to facilitate forward and back propagation of CT operations in the training procedure. This forward projectors support three CT projection geometries: cone, parallel and modular beams. This package can be used with both CPU and GPU with CUDA.

Kim, Hyojin↗
DOE OSTI2019

MPI jobs within MPI jobs: A practical way of enabling task-level fault-tolerance in HPC workflows

While the use of workflows for HPC is growing, MPI interoperability remains a challenge for workflow management systems. The MPI standard and/or its implementations provide a number of ways to build multiple-programs-multiple-data (MPMD) applications. These methods present limitations related to fault tolerance, and are not easy to use. In this paper, we advocate for a novel MPI_Comm_launch function acting as the parallel counterpart of a system(3) call. MPI_Comm_launch allows a child MPI application to be launched inside the resources originally held by processes of a parent MPI application. Two important aspects of MPI_Comm_launch is that it pauses the calling process, and runs the child processes on the parent’s CPU cores, but in an isolated manner with respect to memory. This function makes it easier to build MPMD applications with well-decoupled subtasks. We show how this feature can provide better flexibility and better fault tolerance in ensemble simulations and HPC workflows. Here, we report results showing 2x throughput improvement for application workflows with faults, and scaling results for challenging workloads up to 256 nodes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

A Sparse Distributed Gigascale Resolution Material Point Method

In this paper, we present a four-layer distributed simulation system and its adaptation to the Material Point Method (MPM). The system is built upon a performance portable C++ programming model targeting major High-Performance-Computing (HPC) platforms. A key ingredient of our system is a hierarchical block-tile-cell sparse grid data structure that is distributable to an arbitrary number of Message Passing Interface (MPI) ranks. We additionally propose strategies for efficient dynamic load balance optimization to maximize the efficiency of MPI tasks. Our simulation pipeline can easily switch among backend programming models, including OpenMP and CUDA, and can be effortlessly dispatched onto supercomputers and the cloud. Finally, we construct benchmark experiments and ablation studies on supercomputers and consumer workstations in a local network to evaluate the scalability and load balancing criteria. We demonstrate massively parallel, highly scalable, and gigascale resolution MPM simulations of up to 1.01 billion particles for less than 323.25 seconds per frame with 8 OpenSSH-connected workstations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Personnel Certifications for the Design, Installation and Maintenance of Photovoltaic Systems. Final Technical Report

The North American Board of Certified Energy Practitioners (NABCEP) is the most respected, well-established, and widely recognized national certification organization for professionals in the field of renewable energy. NABCEP’s certifications were created to facilitate consumer protection, improve quality assurance, and help employers judge the skills of existing or potential employees. The certifications also allow individuals to differentiate themselves from others in their field and advance their careers while fostering increased recognition of the profession. Since NABCEP’s founding in 2002, all of its certification exams have been administered in paper-and-pencil format twice per year at 30 exam sites around the United States. The biannual test administration and relatively low number of exam sites make it challenging for many qualified renewable energy professionals to take NABCEP’s certification exams. The rigorous nature of the exam, which leads to many candidates failing the exam on their first and sometimes second attempts, combined with the low number of annual test administrations means that anyone who fails will need to wait another six months for the chance to retake the exam. These factors limited the potential growth of NABCEP’s certification programs and the resultant quality assurance within the renewable energy industry. Thanks to a generous grant by the Department of Energy’s Solar Training and Education for Professional (STEP) program, NABCEP recently began updating its Photovoltaic (PV) Installation Professional Exam and developing three new specialty certifications in PV design, PV installation, and PV commissioning & maintenance. One of the primary objectives of this STEP-funded project was to develop the exams using a computer-based testing (CBT) model to increase the number of exam administrations and available exam sites for NABCEP’s certification exams. To successfully complete this project, NABCEP partnered with Castle Worldwide, Inc. With more than 25 years of experience in test development, test administration, analysis of examinations, and has a staff of 70 experienced personnel, NABCEP was confident that Castle’s team was more than qualified to help NABCEP make the transition to CBT examinations. NABCEP and Castle Worldwide jointly developed a project management plan that included key deliverables, scope management, a work breakdown structure, roles and responsibilities, and a project schedule with milestones. The project schedule was carefully monitored to ensure that activities along the critical path were not delayed and, when deemed necessary, the project was crashed to add resources so that activities could occur in parallel. NABCEP and Castle Worldwide staff met weekly to discuss any potential schedule variances and activities which might delay the closing of the project. NABCEP also recruited 46 subject matter experts (SMEs) to work with Castle’s staff on this project. NABCEP staff, SME’s, and Castle staff worked together to develop the Job Task Analyses that form the basis for the certification exams, create new examination forms, conduct passing score studies, and complete a psychometrical analysis of potential exam items. NABCEP’s SMEs utilized Castle’s item development platform during face-to-face meetings, webinars, and remote item authoring to write, review, and approve exam items. Castle also used their software to psychometrically analyze existing exam items to confirm the reliability and validity of the NABCEP’s certification exams. On January 3rd, 2018, NABCEP’s began offering its PV Installation Professional certification exam via CBT. The exam was available at Castle’s nearly 600 exam sites in the United States. A large number of sites will help to ensure better access for solar professionals in rural and remote areas, which drives down the implicit costs of taking the certification exams. Thanks to the STEP grant and the robust partnership between NABCEP and Castle Worldwide, Inc., personnel certifications will be much more accessible and affordable for renewable energy professionals.

14 SOLAR ENERGY↗