Search NASA⌕ Search

SEARCH · Search NASA

Results for “runtime”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,153 records · Page 64

Center for Plasma Edge Simulation (CPES) (Rutgers University Final Report)

The CPES scientific simulations run at scale on leadership class machines, collaborate at runtime and produce and exchange large data sizes, which present multiple I/O and data management challenges. During the CPES project, the Rutgers team worked with the rest of the CPES team to address these challenges at different levels, and specifically (1) at the data transport and communication level through the DART (Decoupled and Asynchronous Remote Data Transfers) framework, and (2) at the data management and services level through the DataSpaces and ActiveSpaces frameworks. These frameworks and their impact are briefly described.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

FOX: A Fault-Oblivious Extreme-Scale Execution Environment Boston University Final Report Project Number: DE-SC0005365

Exascale computing systems will provide a thousand-fold increase in parallelism and a proportional increase in failure rate relative to today's machines. Systems software for exascale machines must provide the infrastructure to support existing applications while simultaneously enabling efficient execution of new programming models that naturally express dynamic, adaptive, irregular computation; coupled simulations; and massive data analysis in a highly unreliable hardware environment with billions of threads of execution. The FOX project explored systems software and runtime support for a new approach to the data and work distribution for fault oblivious application execution. Our major OS work at Boston University focused on developing a new light-weight operating systems model that provides an appropriate context for both multi-core and multi-node application development. This work is discussed in section 1. Early on in the FOX project BU developed infrastructure for prototyping dynamic HPC environments in which the sets of nodes that an application is run on can be dynamically grown or shrunk. This work was an extension of the Kittyhawk project and is discussed in section 2. Section 3 documents the publications and software repositories that we have produced. To put our work in context of the complete FOX project contribution we include in section 4 an extended version of a paper that documents the complete work of the FOX team.

97 MATHEMATICS AND COMPUTING↗

Performance Refactoring of Instrumentation, Measurement, and Analysis Technologies for Petascale Computing: the PRIMA Project

The growing number of cores provided by today’s high-end computing systems present substantial challenges to application developers in their pursuit of parallel efficiency. To find the most effective optimization strategy, application developers need insight into the runtime behavior of their code. The University of Oregon (UO) and the Julich Supercomputing Centre of Forschungszentrum Julich (FZJ) developed the performance analysis tools TAU and Scalasca, respectively, which allow high-performance computing (HPC) users to collect and analyze relevant performance data – even at very large scales. TAU and Scalasca are considered among the most advanced parallel performance systems available, and are used extensively across HPC centers in the U.S., Germany, and around the world.

97 MATHEMATICS AND COMPUTING↗

The Wind Forecast Improvement Project (WFIP). A Public/Private Partnership for Improving Short Term Wind Energy Forecasts and Quantifying the Benefits of Utility Operations -- the Northern Study Area

This report contains the results from research aimed at improving short-range (0-6 hour) hub-height wind forecasts in the NOAA weather forecast models through additional data assimilation and model physics improvements for use in wind energy forecasting. Additional meteorological observing platforms including wind profilers, sodars, and surface stations were deployed for this study by NOAA and DOE, and additional meteorological data at or near wind turbine hub height were provided by South Dakota State University and WindLogics/NextEra Energy Resources over a large geographical area in the U.S. Northern Plains for assimilation into NOAA research weather forecast models. The resulting improvements in wind energy forecasts based on the research weather forecast models (with the additional data assimilation and model physics improvements) were examined in many different ways and compared with wind energy forecasts based on the current operational weather forecast models to quantify the forecast improvements important to power grid system operators and wind plant owners/operators participating in energy markets. Two operational weather forecast models (OP_RUC, OP_RAP) and two research weather forecast models (ESRL_RAP, HRRR) were used as the base wind forecasts for generating several different wind power forecasts for the NextEra Energy wind plants in the study area. Power forecasts were generated from the wind forecasts in a variety of ways, from very simple to quite sophisticated, as they might be used by a wide range of both general users and commercial wind energy forecast vendors. The error characteristics of each of these types of forecasts were examined and quantified using bulk error statistics for both the local wind plant and the system aggregate forecasts. The wind power forecast accuracy was also evaluated separately for high-impact wind energy ramp events. The overall bulk error statistics calculated over the first six hours of the forecasts at both the individual wind plant and at the system-wide aggregate level over the one year study period showed that the research weather model-based power forecasts (all types) had lower overall error rates than the current operational weather model-based power forecasts, both at the individual wind plant level and at the system aggregate level. The bulk error statistics of the various model-based power forecasts were also calculated by season and model runtime/forecast hour as power system operations are more sensitive to wind energy forecast errors during certain times of year and certain times of day. The results showed that there were significant differences in seasonal forecast errors between the various model-based power forecasts. The results from the analysis of the various wind power forecast errors by model runtime and forecast hour showed that the forecast errors were largest during the times of day that have increased significance to power system operators (the overnight hours and the morning/evening boundary layer transition periods), but the research weather model-based power forecasts showed improvement over the operational weather model-based power forecasts at these times.

17 WIND ENERGY↗

Pervasive Restart In MOOSE-based Applications

Multiphysics applications are inherently complicated. Solving for multiple, interacting physical phenomena involves the solution of multiple equations, and each equation has its own data dependencies. Feeding the correct data to these equations at exactly the right time requires extensive effort in software design. In an ideal world, multiphysics applications always run to completion and produce correct answers. Unfortunately, in reality, there can be many reasons why a simulation might fail: power outage, system failure, exceeding a runtime allotment on a supercomputer, failure of the solver to converge, etc. A failure after many hours spent computing can be a significant setback for a project. Therefore, the ability to “continue” a solve from the point of failure, rather than starting again from scratch, is an essential component of any high-quality simulation tool. This process of “continuation” is commonly termed “restart” in the computational community. While the concept of restarting an application sounds ideal, the aforementioned complexities and data dependencies present in multiphysics applications make its implementation decidedly non-trivial. A running multiphysics calculation accumulates an enormous amount of “state”: current time, solution history, material properties, status of mechanical contact, etc. This “state” data comes in many different forms, including scalar, tensor, vector, and arbitrary, application-specific data types. To be able to restart an application, you must be able to both store and retrieve this data, effectively recreating the state of the application before the failure. When utilizing the Multiphysics Object Oriented Simulation Environment (MOOSE) framework developed at Idaho National Laboratory, this state data is stored both internally within the framework itself (such as solution vectors and the current time) and within the applications that use the framework. In order to implement restart in MOOSE-based applications, the total state of the system (both within the framework and without) must be stored and retrieved. To this end, the MOOSE team has implemented a “pervasive” restart capability which allows any object within MOOSE (or within a MOOSE-based application) to be declared as “state” data, and handles the storage and retrieval of said data.

97 MATHEMATICS AND COMPUTING↗

Performance Refactoring of Instrumentation, Measurement, and Analysis Technologies for Petascale Computing. The PRIMA Project

The growing number of cores provided by today’s high-­end computing systems present substantial challenges to application developers in their pursuit of parallel efficiency. To find the most effective optimization strategy, application developers need insight into the runtime behavior of their code. The University of Oregon (UO) and the Juelich Supercomputing Centre of Forschungszentrum Juelich (FZJ) develop the performance analysis tools TAU and Scalasca, respectively, which allow high-­performance computing (HPC) users to collect and analyze relevant performance data – even at very large scales. TAU and Scalasca are considered among the most advanced parallel performance systems available, and are used extensively across HPC centers in the U.S., Germany, and around the world. The TAU and Scalasca groups share a heritage of parallel performance tool research and partnership throughout the past fifteen years. Indeed, the close interactions of the two groups resulted in a cross-­fertilization of tool ideas and technologies that pushed TAU and Scalasca to what they are today. It also produced two performance systems with an increasing degree of functional overlap. While each tool has its specific analysis focus, the tools were implementing measurement infrastructures that were substantially similar. Because each tool provides complementary performance analysis, sharing of measurement results is valuable to provide the user with more facets to understand performance behavior. However, each measurement system was producing performance data in different formats, requiring data interoperability tools to be created. A common measurement and instrumentation system was needed to more closely integrate TAU and Scalasca and to avoid the duplication of development and maintenance effort. The PRIMA (Performance Refactoring of Instrumentation, Measurement, and Analysis) project was proposed over three years ago as a joint international effort between UO and FZJ to accomplish these objectives: (1) refactor TAU and Scalasca performance system components for core code sharing and (2) integrate TAU and Scalasca functionality through data interfaces, formats, and utilities. As presented in this report, the project has completed these goals. In addition to shared technical advances, the groups have worked to engage with users through application performance engineering and tools training. In this regard, the project benefits from the close interactions the teams have with national laboratories in the United States and Germany. We have also sought to enhance our interactions through joint tutorials and outreach. UO has become a member of the Virtual Institute of High-­Productivity Supercomputing (VI-­HPS) established by the Helmholtz Association of German Research Centres as a center of excellence, focusing on HPC tools for diagnosing programming errors and optimizing performance. UO and FZJ have conducted several VI-­HPS training activities together within the past three years.

97 MATHEMATICS AND COMPUTING↗

Report for the ASC CSSE L2 Milestone (4873) - Demonstration of Local Failure Local Recovery Resilient Programming Model.

Recovery from process loss during the execution of a distributed memory parallel application is presently achieved by restarting the program, typically from a checkpoint file. Future computer system trends indicate that the size of data to checkpoint, the lack of improvement in parallel file system performance and the increase in process failure rates will lead to situations where checkpoint restart becomes infeasible. In this report we describe and prototype the use of a new application level resilient computing model that manages persistent storage of local state for each process such that, if a process fails, recovery can be performed locally without requiring access to a global checkpoint file. LFLR provides application developers with an ability to recover locally and continue application execution when a process is lost. This report discusses what features are required from the hardware, OS and runtime layers, and what approaches application developers might use in the design of future codes, including a demonstration of LFLR-enabled MiniFE code from the Matenvo mini-application suite.

Heroux, Michael Allen↗

A New On-the-Fly Sampling Method for Incoherent Inelastic Thermal Neutron Scattering Data in MCNP6

At thermal energies, the scattering of neutrons in a system is complicated by the comparable velocities of the neutron and target, resulting in competing upscattering and downscattering events. The neutron wavelength is also similar in size to the target's interatomic spacing making the scattering process a quantum mechanical problem. Because of the complicated nature of scattering at low energies, the thermal data files in ACE format used in continuous-energy Monte Carlo codes are quite large { on the order of megabytes for a single temperature and material. In this paper, a new storage and sampling method is introduced that is orders of magnitude less in size and is used to sample scattering parameters at any temperature on-the-fly. In addition to the reduction in storage, the need to pre-generate thermal scattering data tables at fine temperatures has been eliminated. This is advantageous for multiphysics simulations which may involve temperatures not known in advance. A new module was written for MCNP6 that bypasses the current S(α,β) table lookup in favor of the new format. The new on-the-fly sampling method was tested for graphite for two benchmark problems at ten temperatures: 1) an eigenvalue test with a fuel compact of uranium oxycarbide fuel homogenized into a graphite matrix, 2) a surface current test with a \broomstick" problem with a monoenergetic point source. The largest eigenvalue difference was 152pcm for T= 1200K. For the temperatures and incident energies chosen for the broomstick problem, the secondary neutron spectrum showed good agreement with the traditional S(α,β) sampling method. These preliminary results show that sampling thermal scattering data on-the-fly is a viable option to eliminate both the storage burden of keeping thermal data at discrete temperatures and the need to know temperatures before simulation runtime.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

LAMMPS strong scaling performance optimization on Blue Gene/Q

LAMMPS "Large-scale Atomic/Molecular Massively Parallel Simulator" is an open-source molecular dynamics package from Sandia National Laboratories. Significant performance improvements in strong-scaling and time-to-solution for this application on IBM's Blue Gene/Q have been achieved through computational optimizations of the OpenMP versions of the short-range Lennard-Jones term of the CHARMM force field and the long-range Coulombic interaction implemented with the PPPM (particle-particle-particle mesh) algorithm, enhanced by runtime parameter settings controlling thread utilization. Additionally, MPI communication performance improvements were made to the PPPM calculation by re-engineering the parallel 3D FFT to use MPICH collectives instead of point-to-point. Performance testing was done using an 8.4-million atom simulation scaling up to 16 racks on the Mira system at Argonne Leadership Computing Facility (ALCF). Speedups resulting from this effort were in some cases over 2x.

Coffman, Paul↗

Thrifty: An Exascale Architecture for Energy Proportional Computing

The objective of this project is to design different aspects of a novel exascale architecture called Thrifty. Our goal is to focus on the challenges of power/energy efficiency, performance, and resiliency in exascale systems. The project includes work on computer architecture (Josep Torrellas from University of Illinois), compilation (Daniel Quinlan from Lawrence Livermore National Laboratory), runtime and applications (Laura Carrington from University of California San Diego), and circuits (Wilfred Pinfold from Intel Corporation). In this report, we focus on the progress at the University of Illinois during the last year of the grant (September 1, 2013 to August 31, 2014). We also point to the progress in the other collaborating institutions when needed.

97 MATHEMATICS AND COMPUTING↗

Using Discrete Event Simulation for Programming Model Exploration at Extreme-Scale: Macroscale Components for the Structural Simulation Toolkit (SST).

Discrete event simulation provides a powerful mechanism for designing and testing new extreme- scale programming models for high-performance computing. Rather than debug, run, and wait for results on an actual system, design can first iterate through a simulator. This is particularly useful when test beds cannot be used, i.e. to explore hardware or scales that do not yet exist or are inaccessible. Here we detail the macroscale components of the structural simulation toolkit (SST). Instead of depending on trace replay or state machines, the simulator is architected to execute real code on real software stacks. Our particular user-space threading framework allows massive scales to be simulated even on small clusters. The link between the discrete event core and the threading framework allows interesting performance metrics like call graphs to be collected from a simulated run. Performance analysis via simulation can thus become an important phase in extreme-scale programming model and runtime system design via the SST macroscale components.

97 MATHEMATICS AND COMPUTING↗

Rexsss Performance Analysis: Domain Decomposition Algorithm Implementations for Resilient Numerical Partial Differential Equation Solvers

The future of extreme-scale computing is expected to magnify the influence of soft faults as a source of inaccuracy or failure in solutions obtained from distributed parallel computations. The development of resilient computational tools represents an essential recourse for understanding the best methods for absorbing the impacts of soft faults without sacrificing solution accuracy. The Rexsss (Resilient Extreme Scale Scientific Simulations) project pursues the development of fault resilient algorithms for solving partial differential equations (PDEs) on distributed systems. Performance analyses of current algorithm implementations assist in the identification of runtime inefficiencies.

97 MATHEMATICS AND COMPUTING↗

Adding Data Management Services to Parallel File Systems

The objective of this project, called DAMASC for “Data Management in Scientific Computing”, is to coalesce data management with parallel file system management to present a declarative interface to scientists for managing, querying, and analyzing extremely large data sets efficiently and predictably. Managing extremely large data sets is a key challenge of exascale computing. The overhead, energy, and cost of moving massive volumes of data demand designs where computation is close to storage. In current architectures, compute/analysis clusters access data in a physically separate parallel file system and largely leave it scientist to reduce data movement. Over the past decades the high-end computing community has adopted middleware with multiple layers of abstractions and specialized file formats such as NetCDF-4 and HDF5. These abstractions provide a limited set of high-level data processing functions, but have inherent functionality and performance limitations: middleware that provides access to the highly structured contents of scientific data files stored in the (unstructured) file systems can only optimize to the extent that file system interfaces permit; the highly structured formats of these files often impedes native file system performance optimizations. We are developing Damasc, an enhanced high-performance file system with native rich data management services. Damasc will enable efficient queries and updates over files stored in their native byte-stream format while retaining the inherent performance of file system data storage via declarative queries and updates over views of underlying files. Damasc has four key benefits for the development of data-intensive scientific code: (1) applications can use important data-management services, such as declarative queries, views, and provenance tracking, that are currently available only within database systems; (2) the use of these services becomes easier, as they are provided within a familiar file-based ecosystem; (3) common optimizations, e.g., indexing and caching, are readily supported across several file formats, avoiding effort duplication; and (4) performance improves significantly, as data processing is integrated more tightly with data storage. Our key contributions are: SciHadoop which explores changes to MapReduce assumption by taking advantage of semantics of structured data while preserving MapReduce’s failure and resource management; DataMods which extends common abstractions of parallel file systems so they become programmable such that they can be extended to natively support a variety of data models and can be hooked into emerging distributed runtimes such as Stanford’s Legion; and Miso which combines Hadoop and relational data warehousing to minimize time to insight, taking into account the overhead of ingesting data into data warehousing.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Efficient Support for Matrix Computations on Heterogeneous Multi-core and Multi-GPU Architectures

We present a new methodology for utilizing all CPU cores and all GPUs on a heterogeneous multicore and multi-GPU system to support matrix computations e ciently. Our approach is able to achieve the objectives of a high degree of parallelism, minimized synchronization, minimized communication, and load balancing. Our main idea is to treat the heterogeneous system as a distributed-memory machine, and to use a heterogeneous 1-D block cyclic distribution to allocate data to the host system and GPUs to minimize communication. We have designed heterogeneous algorithms with two di erent tile sizes (one for CPU cores and the other for GPUs) to cope with processor heterogeneity. We propose an auto-tuning method to determine the best tile sizes to attain both high performance and load balancing. We have also implemented a new runtime system and applied it to the Cholesky and QR factorizations. Our experiments on a compute node with two Intel Westmere hexa-core CPUs and three Nvidia Fermi GPUs demonstrate good weak scalability, strong scalability, load balance, and e ciency of our approach.

97 MATHEMATICS AND COMPUTING↗

GPU-Accelerated Asynchronous Error Correction for Mixed Precision Iterative Refinement

In hardware-aware high performance computing, block- asynchronous iteration and mixed precision iterative refinement are two techniques that are applied to leverage the computing power of SIMD accelerators like GPUs. Although they use a very different approach for this purpose, they share the basic idea of compensating the convergence behaviour of an inferior numerical algorithm by a more efficient usage of the provided computing power. In this paper, we want to analyze the potential of combining both techniques. Therefore, we implement a mixed precision iterative refinement algorithm using a block-asynchronous iteration as an error correction solver, and compare its performance with a pure implementation of a block-asynchronous iteration and an iterative refinement method using double precision for the error correction solver. For matrices from theUniversity of FloridaMatrix collection,we report the convergence behaviour and provide the total solver runtime using different GPU architectures.

97 MATHEMATICS AND COMPUTING↗

Load Balancing Scientific Applications

The largest supercomputers have millions of independent processors, and concurrency levels are rapidly increasing. For ideal efficiency, developers of the simulations that run on these machines must ensure that computational work is evenly balanced among processors. Assigning work evenly is challenging because many large modern parallel codes simulate behavior of physical systems that evolve over time, and their workloads change over time. Furthermore, the cost of imbalanced load increases with scale because most large-scale scientific simulations today use a Single Program Multiple Data (SPMD) parallel programming model, and an increasing number of processors will wait for the slowest one at the synchronization points. To address load imbalance, many large-scale parallel applications use dynamic load balance algorithms to redistribute work evenly. The research objective of this dissertation is to develop methods to decide when and how to load balance the application, and to balance it effectively and affordably. We measure and evaluate the computational load of the application, and develop strategies to decide when and how to correct the imbalance. Depending on the simulation, a fast, local load balance algorithm may be suitable, or a more sophisticated and expensive algorithm may be required. We developed a model for comparison of load balance algorithms for a specific state of the simulation that enables the selection of a balancing algorithm that will minimize overall runtime.

97 MATHEMATICS AND COMPUTING↗

The Adaptive Multi-scale Simulation Infrastructure

The Adaptive Multi-scale Simulation Infrastructure (AMSI) is a set of libraries and tools developed to support the development, implementation, and execution of general multimodel simulations. Using a minimal set of simulation meta-data AMSI allows for minimally intrusive work to adapt existent single-scale simulations for use in multi-scale simulations. Support for dynamic runtime operations such as single- and multi-scale adaptive properties is a key focus of AMSI. Particular focus has been spent on the development on scale-sensitive load balancing operations to allow single-scale simulations incorporated into a multi-scale simulation using AMSI to use standard load-balancing operations without affecting the integrity of the overall multi-scale simulation.

97 MATHEMATICS AND COMPUTING↗

Towards Accurate Application Characterization for Exascale (APEX)

Sandia National Laboratories has been engaged in hardware and software codesign activities for a number of years, indeed, it might be argued that prototyping of clusters as far back as the CPLANT machines and many large capability resources including ASCI Red and RedStorm were examples of codesigned solutions. As the research supporting our codesign activities has moved closer to investigating on-node runtime behavior a nature hunger has grown for detailed analysis of both hardware and algorithm performance from the perspective of low-level operations. The Application Characterization for Exascale (APEX) LDRD was a project conceived of addressing some of these concerns. Primarily the research was to intended to focus on generating accurate and reproducible low-level performance metrics using tools that could scale to production-class code bases. Along side this research was an advocacy and analysis role associated with evaluating tools for production use, working with leading industry vendors to develop and refine solutions required by our code teams and to directly engage with production code developers to form a context for the application analysis and a bridge to the research community within Sandia. On each of these accounts significant progress has been made, particularly, as this report will cover, in the low-level analysis of operations for important classes of algorithms. This report summarizes the development of a collection of tools under the APEX research program and leaves to other SAND and L2 milestone reports the description of codesign progress with Sandia’s production users/developers.

97 MATHEMATICS AND COMPUTING↗