Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “parallel performance”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Performance Analysis of Traditional and Data-Parallel Primitive Implementations of Visualization and Analysis Kernels

Measurements of absolute runtime are useful as a summary of performance when studying parallel visualization and analysis methods on computational platforms of increasing concurrency and complexity. We can obtain even more insights by measuring and examining more detailed measures from hardware performance counters, such as the number of instructions executed by an algorithm implemented in a particular way, the amount of data moved to/from memory, memory hierarchy utilization levels via cache hit/miss ratios, and so forth. This work focuses on performance analysis on modern multi-core platforms of three different visualization and analysis kernels that are implemented in different ways: one is "traditional", using combinations of C++ and VTK, and the other uses a data-parallel approach using VTK-m. Our performance study consists of measurement and reporting of several different hardware performance counters on two different multi-core CPU platforms. The results reveal interesting performance differences between these two different approaches for implementing these kernels, results that would not be apparent using runtime as the only metric.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1986

Miniature metastable ionization detectors for exobiology flight experiments

The Metastable Ionization Detector (MID) is three orders of magnitude more sensitive than the thermal conductivity detectors used on previous flight instruments. The miniature MID provides scientists with a much smaller and highly sensitive detector for flight gas chromatographs. A miniature MID featuring an unconventional triaxial electrode configuration was developed and used routinely in the laboratory. Although much smaller and lighter than the commercial MID, its performance characteristics parallel those of the traditional design. The detector is compatible with the modulated voltage circuitry, also developed here, and thus can perform over an expanded response range of more than 7 orders magnitude. A micro volume version of a miniature MID, with an internal volume of less than 8 microliter, was recently designed is now being tested. The micro volume MID uses carrier gas flow rates of approx. 2cc/min thus eliminating the need for makeup gas when capillary columns are used.

Woeller, F. H.↗
NASA NTRS2000

Identification of genes regulated during mechanical load-induced cardiac hypertrophy

Cardiac hypertrophy is associated with both adaptive and adverse changes in gene expression. To identify genes regulated by pressure overload, we performed suppressive subtractive hybridization between cDNA from the hearts of aortic-banded (7-day) and sham-operated mice. In parallel, we performed a subtraction between an adult and a neonatal heart, for the purpose of comparing different forms of cardiac hypertrophy. Sequencing more than 100 clones led to the identification of an array of functionally known (70%) and unknown genes (30%) that are upregulated during cardiac growth. At least nine of those genes were preferentially expressed in both the neonatal and pressure over-load hearts alike. Using Northern blot analysis to investigate whether some of the identified genes were upregulated in the load-independent calcineurin-induced cardiac hypertrophy mouse model, revealed its incomplete similarity with the former models of cardiac growth. Copyright 2000 Academic Press.

NASA Discipline Cardiopulmonary↗
NASA NTRS1993

Fast structural design and analysis via hybrid domain decomposition on massively parallel processors

A hybrid domain decomposition framework for static, transient and eigen finite element analyses of structural mechanics problems is presented. Its basic ingredients include physical substructuring and /or automatic mesh partitioning, mapping algorithms, 'gluing' approximations for fast design modifications and evaluations, and fast direct and preconditioned iterative solvers for local and interface subproblems. The overall methodology is illustrated with the structural design of a solar viewing payload that is scheduled to fly in March 1993. This payload has been entirely designed and validated by a group of undergraduate students at the University of Colorado using the proposed hybrid domain decomposition approach on a massively parallel processor. Performance results are reported on the CRAY Y-MP/8 and the iPSC-860/64 Touchstone systems, which represent both extreme parallel architectures. The hybrid domain decomposition methodology is shown to outperform leading solution algorithms and to exhibit an excellent parallel scalability.

Farhat, Charbel↗
NASA NTRS2002

Effects of Ordering Strategies and Programming Paradigms on Sparse Matrix Computations

The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. For systems that are ill-conditioned, it is often necessary to use a preconditioning technique. In this paper, we investigate the effects of various ordering and partitioning strategies on the performance of parallel CG and ILU(O) preconditioned CG (PCG) using different programming paradigms and architectures. Results show that for this class of applications: ordering significantly improves overall performance on both distributed and distributed shared-memory systems, that cache reuse may be more important than reducing communication, that it is possible to achieve message-passing performance using shared-memory constructs through careful data ordering and distribution, and that a hybrid MPI+OpenMP paradigm increases programming complexity with little performance gains. A implementation of CG on the Cray MTA does not require special ordering or partitioning to obtain high efficiency and scalability, giving it a distinct advantage for adaptive applications; however, it shows limited scalability for PCG due to a lack of thread level parallelism.

Oliker, Leonid↗
NASA NTRS1989

Development of parallel algorithms for electrical power management in space applications

The application of parallel techniques for electrical power system analysis is discussed. The Newton-Raphson method of load flow analysis was used along with the decomposition-coordination technique to perform load flow analysis. The decomposition-coordination technique enables tasks to be performed in parallel by partitioning the electrical power system into independent local problems. Each independent local problem represents a portion of the total electrical power system on which a loan flow analysis can be performed. The load flow analysis is performed on these partitioned elements by using the Newton-Raphson load flow method. These independent local problems will produce results for voltage and power which can then be passed to the coordinator portion of the solution procedure. The coordinator problem uses the results of the local problems to determine if any correction is needed on the local problems. The coordinator problem is also solved by an iterative method much like the local problem. The iterative method for the coordination problem will also be the Newton-Raphson method. Therefore, each iteration at the coordination level will result in new values for the local problems. The local problems will have to be solved again along with the coordinator problem until some convergence conditions are met.

Berry, Frederick C.↗
DOE OSTI2020

Scalability of high-performance PDE solvers

Performance tests and analyses are critical to effective high-performance computing software development and are central components in the design and implementation of computational algorithms for achieving faster simulations on existing and future computing architectures for large-scale application problems. In this article, we explore performance and space-time trade-offs for important compute-intensive kernels of large-scale numerical solvers for partial differential equations (PDEs) that govern a wide range of physical applications. We consider a sequence of PDE-motivated bake-off problems designed to establish best practices for efficient high-order simulations across a variety of codes and platforms. We measure peak performance (degrees of freedom per second) on a fixed number of nodes and identify effective code optimization strategies for each architecture. In addition to peak performance, we identify the minimum time to solution at 80% parallel efficiency. The performance analysis is based on spectral and p-type finite elements but is equally applicable to a broad spectrum of numerical PDE discretizations, including finite difference, finite volume, and h-type finite elements.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Effect of Extended Aging and Oxidation on Linear Poly(propylenimine)-Mesoporous Silica Composites for CO 2 Capture from Simulated Air and Flue Gas Streams

Physical aging or degradation of amine-containing polymers and supported amine adsorbents is a critical issue that could limit practical application of such materials for CO 2 capture. However, to date, there is a scarcity of studies that evaluate the long-term stability of amine-based sorbents without the exclusive use of accelerated aging tests. Here, we demonstrate that extended aging (~2 years) of linear poly(propylenimine) (LPPI) confined in mesoporous silica (SBA-15) supports does not drastically impact the CO 2 adsorption performance under simulated flue gas (10% CO 2 ) and direct air capture (DAC, 400 ppm CO 2 ) conditions, although the behavior of the aged sorbents and polymers in the two CO 2 concentration regimes differs. Sorbents made with aged LPPI had modestly decreased CO 2 uptake performance (<~20% lower) compared to the fresh polymers, with overall good CO 2 cycling performance. The data indicate that only slow degradation occurs under the deployed ambient storage conditions. Even after extended aging, the LPPI-based sorbents preserved their ability to display stable temperature-swing cycling performance. In parallel, the impact of blending LPPI polymers of different number-average molecular weights, M n , is evaluated, seeking to understand its impact on adsorbent performance. We find that the results demonstrate that blends of two M n aged LPPI give similar CO 2 adsorption performance to adsorbents made from a single M n LPPI, suggesting that molecular weight will not negatively impact adsorbent performance in the studied M n range. After an accelerated oxidation experiment, the aged LPPI sorbents retained a larger portion of the samples’ original performance when cycling under simulated flue gas conditions than under DAC conditions. However, in each case, the oxidized sorbents could be cycled repeatedly with consistent uptake performance. Overall, these first of their kind extended aging tests suggest that LPPI-based amine adsorbents offer promise for long term, stable use in carbon capture applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1998

Integrating Cache Performance Modeling and Tuning Support in Parallelization Tools

With the resurgence of distributed shared memory (DSM) systems based on cache-coherent Non Uniform Memory Access (ccNUMA) architectures and increasing disparity between memory and processors speeds, data locality overheads are becoming the greatest bottlenecks in the way of realizing potential high performance of these systems. While parallelization tools and compilers facilitate the users in porting their sequential applications to a DSM system, a lot of time and effort is needed to tune the memory performance of these applications to achieve reasonable speedup. In this paper, we show that integrating cache performance modeling and tuning support within a parallelization environment can alleviate this problem. The Cache Performance Modeling and Prediction Tool (CPMP), employs trace-driven simulation techniques without the overhead of generating and managing detailed address traces. CPMP predicts the cache performance impact of source code level "what-if" modifications in a program to assist a user in the tuning process. CPMP is built on top of a customized version of the Computer Aided Parallelization Tools (CAPTools) environment. Finally, we demonstrate how CPMP can be applied to tune a real Computational Fluid Dynamics (CFD) application.

Waheed, Abdul↗
NASA NTRS1990

Responsive systems - The challenge for the nineties

A concept of responsive computer systems will be introduced. The emerging responsive systems demand fault-tolerant and real-time performance in parallel and distributed computing environments. The design methodologies for fault-tolerant, real time and responsive systems will be presented. Novel techniques of introducing redundancy for improved performance and dependability will be illustrated. The methods of system responsiveness evaluation will be proposed. The issues of determinism, closed and open systems will also be discussed from the perspective of responsive systems design.

Malek, Miroslaw↗
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↗
NASA NTRS1998

Developing Information Power Grid Based Algorithms and Software

This exploratory study initiated our effort to understand performance modeling on parallel systems. The basic goal of performance modeling is to understand and predict the performance of a computer program or set of programs on a computer system. Performance modeling has numerous applications, including evaluation of algorithms, optimization of code implementations, parallel library development, comparison of system architectures, parallel system design, and procurement of new systems. Our work lays the basis for the construction of parallel libraries that allow for the reconstruction of application codes on several distinct architectures so as to assure performance portability. Following our strategy, once the requirements of applications are well understood, one can then construct a library in a layered fashion. The top level of this library will consist of architecture-independent geometric, numerical, and symbolic algorithms that are needed by the sample of applications. These routines should be written in a language that is portable across the targeted architectures.

Dongarra, Jack↗
DOE OSTI2022

Simulating single-particle dynamics in magnetized plasmas: The RMF code

The RMF (Rotating Magnetic Field) code is designed to calculate the motion of a charged particle in a given electromagnetic field. It integrates Hamilton’s equations in cylindrical coordinates using an adaptive predictor-corrector double-precision variable-coefficient ordinary differential equation solver for speed and accuracy. RMF has multiple capabilities for the field. Particle motion is initialized by specifying the position and velocity vectors. Here, the six-dimensional state vector and derived quantities are saved as functions of time. A post-processing graphics code, XDRAW, is used on the stored output to plot up to 12 windows of any two quantities using different colors to denote successive time intervals. Multiple cases of RMF may be run in parallel and perform data mining on the results. Recent features are a synthetic diagnostic for simulating the observations of charge-exchange-neutral energy distributions and RF grids to explore a Fermi acceleration parallel to static magnetic fields.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
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 NTRS1978

An investigation for the development of an integrated optical data preprocessor

The successful fabrication and demonstration of an integrated optical circuit designed to perform a parallel processing operation by utilizing holographic subtraction to simultaneously compare N analog signal voltages with N predetermined reference voltages is summarized. The device alleviates transmission, storage and processing loads of satellite data systems by performing, at the sensor site, some preprocessing of data taken by remote sensors. Major accomplishments in the fabrication of integrated optics components include: (1) fabrication of the first LiNbO3 waveguide geodesic lens; (2) development of techniques for polishing TIR mirrors on LiNbO3 waveguides; (3) fabrication of high efficiency metal-over-photoresist gratings for waveguide beam splitters; (4) demonstration of high S/N holographic subtraction using waveguide holograms; and (5) development of alignment techniques for fabrication of integrated optics circuits. Important developments made in integrated optics are the discovery and suggested use of holographic self-subtraction in LiNbO3, development of a mathematical description of the operating modes of the preprocessor, and the development of theories for diffraction efficiency and beam quality of two dimensional beam defined gratings.

Verber, C. M.↗
NASA NTRS1990

High-performance fault-tolerant VLSI systems using micro rollback

A technique called micro rollback, which allows most of the performance penalty for concurrent error detection to be eliminated, is presented. Detection is performed in parallel with the transmission of information between modules, thus removing the delay for detection from the critical path. Erroneous information may thus reach its destination module several clock cycles before an error indication. Operations performed on this erroneous information are undone using a hardware mechanism for fast rollback of a few cycles. The implementation of a VLSI processor capable of micro rollback is discussed, as well as several critical issues related to its use in a complete system.

Tamir, Yuval↗
NASA NTRS1994

Automated Performance Prediction of Message Passing Parallel Programs

As the trend toward massively parallel processing continues, the need for tools that can predict scalability trends becomes greater. While high level languages Eke HPF have come into greater use, explicit message-passing programs proliferate, and will probably do so for some time, thanks to the onslaught of standards such as MPI. Much work has been done to create simple models that represent important characteristics of parallel programs, such as latency, network contention, and communication volume. But many of these methods still require a substantial manual effort to represent an application in the model's format. The YAPP ("Yet Another Performance Predictor") tool is an attempt to automate the formation of first-order expressions for completion time, with a minimum of programmer assistance. The content of this paper is as follows: First, we explore the implementation details of YAPP, and illustrate with examples some of the reasons that automatic prediction is difficult. In the following sections, we present the results of four applications, using execution traces on the Intel i860, analyze the error in YAPP's predictions, explain the limitations of our implementation, and mention possible future additions. In particular, we illustrate techniques used to identify pipeline communication patterns, and demonstrate how compiler analysis and regression are combined to automate the prediction process.

Block, Robert J.↗
DOE OSTI2024

h5bench: A unified benchmark suite for evaluating HDF5 I/O performance on pre‐exascale platforms

Summary Parallel I/O is a critical technique for moving data between compute and storage subsystems of supercomputers. With massive amounts of data produced or consumed by compute nodes, high‐performant parallel I/O is essential. I/O benchmarks play an important role in this process; however, there is a scarcity of I/O benchmarks representative of current workloads on HPC systems. Toward creating representative I/O kernels from real‐world applications, we have created h5bench , a set of I/O kernels that exercise hierarchical data format version 5 (HDF5) I/O on parallel file systems in numerous dimensions. Our focus on HDF5 is due to the parallel I/O library's heavy usage in various scientific applications running on supercomputing systems. The various tests benchmarked in the h5bench suite include I/O operations (read and write), data locality (arrays of basic data types and arrays of structures), array dimensionality (one‐dimensional arrays, two‐dimensional meshes, three‐dimensional cubes), I/O modes (synchronous and asynchronous). In this paper, we present the observed performance of h5bench executed along several of these dimensions on existing supercomputers (Cori and Summit) and pre‐exascale platforms (Perlmutter, Theta, and Polaris). h5bench measurements can be used to identify performance bottlenecks and their root causes and evaluate I/O optimizations. As the I/O patterns of h5bench are diverse and capture the I/O behaviors of various HPC applications, this study will be helpful to the broader supercomputing and I/O community.

97 MATHEMATICS AND COMPUTING↗