Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “performance portable”

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 703 records · Page 39

Translational research in the MPICH project

The MPICH project is an example of translational research in computer science before that term was well known or even coined. The project began in 1992 as an effort to develop a portable, high-performance implementation of the emerging Message-Passing Interface (MPI) Standard. It has enabled the widespread adoption of MPI as a way to write scalable parallel applications on systems of all sizes including upcoming exascale supercomputers. In this paper, we describe how the translational research process was used in MPICH, how that led to its success, the challenges encountered and lessons learned, and how the process could be applied to other similar projects.

97 MATHEMATICS AND COMPUTING↗

MPICH

MPICH is a high-performance and widely portable implementation of the MPI-4 standard from the Argonne National Laboratory. This release has all MPI 4 functions and features required by the standard with the exception of support for the user-defined data representations for I/O.

ECP↗

Compiled MPI: Cost-Effective Exascale Applications Development

The complexity of petascale and exascale machines makes it increasingly difficult to develop applications that can take advantage of them. Future systems are expected to feature billion-way parallelism, complex heterogeneous compute nodes and poor availability of memory (Peter Kogge, 2008). This new challenge for application development is motivating a significant amount of research and development on new programming models and runtime systems designed to simplify large-scale application development. Unfortunately, DoE has significant multi-decadal investment in a large family of mission-critical scientific applications. Scaling these applications to exascale machines will require a significant investment that will dwarf the costs of hardware procurement. A key reason for the difficulty in transitioning today's applications to exascale hardware is their reliance on explicit programming techniques, such as the Message Passing Interface (MPI) programming model to enable parallelism. MPI provides a portable and high performance message-passing system that enables scalable performance on a wide variety of platforms. However, it also forces developers to lock the details of parallelization together with application logic, making it very difficult to adapt the application to significant changes in the underlying system. Further, MPI's explicit interface makes it difficult to separate the application's synchronization and communication structure, reducing the amount of support that can be provided by compiler and run-time tools. This is in contrast to the recent research on more implicit parallel programming models such as Chapel, OpenMP and OpenCL, which promise to provide significantly more flexibility at the cost of reimplementing significant portions of the application. We are developing CoMPI, a novel compiler-driven approach to enable existing MPI applications to scale to exascale systems with minimal modifications that can be made incrementally over the application's lifetime. It includes: (1) New set of source code annotations, inserted either manually or automatically, that will clarify the application's use of MPI to the compiler infrastructure, enabling greater accuracy where needed; (2) A compiler transformation framework that leverages these annotations to transform the original MPI source code to improve its performance and scalability; (3) Novel MPI runtime implementation techniques that will provide a rich set of functionality extensions to be used by applications that have been transformed by our compiler; and (4) A novel compiler analysis that leverages simple user annotations to automatically extract the application's communication structure and synthesize most complex code annotations.

97 MATHEMATICS AND COMPUTING↗

PETSc Users Manual Revision 3.7

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.

97 MATHEMATICS AND COMPUTING↗

PETSc Users Manual Revision 3.8

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.

97 MATHEMATICS AND COMPUTING↗

PETSc Users Manual: Revision 3.10

This manual describes the use of PETSc for the numerical solution of partial differential equa-tions and related problems on high-performance computers. The Portable, Extensible Toolkit forScientific Computation (PETSc) is a suite of data structures and routines that provide the buildingblocks for the implementation of large-scale application codes on parallel (and serial) computers.PETSc uses the MPI standard for all message-passing communication.

97 MATHEMATICS AND COMPUTING↗

PETSc Users Manual (Rev. 3.11)

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.

97 MATHEMATICS AND COMPUTING↗

PETSc Users Manual (Rev. 3.13)

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 solvers, nonlinear solvers, and time integrators that may be used in application codes written in Fortran, C, C++, and Python. 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++, python, 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.

97 MATHEMATICS AND COMPUTING↗

GASNet-EX Memory Kinds: Support for Device Memory in PGAS Programming Models

There is an emerging need for adaptive, lightweight communication in irregular HPC applications at exascale, where GPU accelerators provide the majority of available compute cycles. To address this need, Lawrence Berkeley National Lab is developing a programming system to support distributed-memory HPC application development using the Partitioned Global Address Space (PGAS) model. This work includes two major components: UPC++ and GASNet-EX. UPC++ is a C++ template library providing Remote Memory Access (RMA) and Remote Procedure Call (RPC) communication interfaces. GASNet-EX is a portable, high-performance communication middleware library, used by the implementations of UPC++ and many other PGAS programming models. We describe recent advances in GASNet-EX to efficiently implement zero-copy Remote Memory Access (RMA) communication to and from memory on accelerator devices such as GPUs. We demonstrate performance improvements via benchmark results from UPC++ (on Summit) and the Legion programming system (on DGX-1), both using GASNet-EX for communication.

Hargrove, Paul H↗

Characterizing the performance of a POPS miniaturized optical particle counter when operated on a quadcopter drone

We first validate the performance of the Portable Optical Particle Spectrometer (POPS), a small light-weight and high sensitivity optical particle counter, against a reference scanning mobility particle sizer (SMPS) for a month-long deployment in an environment dominated by biomass burning aerosols. Subsequently, we examine any biases introduced by operating the POPS on a quadcopter drone, a DJI Matrice 200 V2. We report the root mean square difference (RMSD) and mean absolute difference (MAD) in particle number concentrations (PNCs) when mounted on the UAV and operating on the ground and when hovering at 10 m. When wind speeds are low (less than 2.6 m s –1 ), we find only modest differences in the RMSDs and MADs of 5 % and 3 % when operating at 10 m altitude. When wind speeds are between 2.6 and 7.7 m s –1 the RMSDs and MADs increase to 26.2 % and 19.1 %, respectively, when operating at 10m altitude. No statistical difference in PNCs was detected when operating on the UAV in either ascent or descent. We also find size distributions of aerosols in the accumulation mode (defined by diameter, d, where 0.1 ≤ d ≤ 1 µm) are relatively consistent between measurements at the surface and measurements at 10 m altitude, while differences in the coarse mode (here defined by d > 1 µm) are universally larger. Our results suggest that the impact of the UAV rotors on the POPS PNCs are small at low wind speeds, but when operating under a higher wind speed of up to 7.6 m s –1 , larger discrepancies occur. In addition, it appears that the POPS measures sub-micron aerosol particles more accurately than super-micron aerosol particles when airborne on the UAV. These measurements lay the foundations for determining the magnitude of potential errors that might be introduced into measured aerosol particle size distributions and concentrations owing to the turbulence created by the rotors on the UAV.

47 OTHER INSTRUMENTATION↗

Time dissemination: An update

A brief description of some of the improvements in the generation and dissemination of precise time and time interval at the U.S. Naval Observation are described. Details on some of the newer hardware developed for this purpose are presented. Data from tests of two of the more significant items, a small portable clock with performance approaching that of larger units and a GPS Time Transfer Unit capable of time transfer to an accuracy of less than 100 nanoseconds, are also given.

Putkovich, K.↗

Development of a miniaturized gas chromatograph-mass spectrometer with a microbore capillary column and an array detector

A review is presented of the demonstration of a miniaturized focal plane mass spectrograph using a microbore capillary column with an array detector to measure multiple mass spectra from narrow and closely eluted gas chromatograph peaks. It is shown that the system possesses high sensitivity and a high speed of spectral mass measurements. The combination of the capillary column with the miniaturized mass spectrograph is uniquely suited for the development of a field-portable, high-performance system.

Sinha, Mahadeva P.↗

Building the electronic industry's roadmaps

JTEC panelists found a strong consistency among the electronics firms they visited: all the firms had clear visions or roadmaps for their research and development activities and had committed resources to ensure that they achieve targeted results. The overarching vision driving Japan's electronics industry is that of achieving market success through developing appealing, high-quality, low-cost consumer goods - ahead of the competition. Specifics of the vision include improving performance, quality, and portability of consumer electronics products. Such visions help Japanese companies define in detail the roadmaps they will follow to develop new and improved electronic packaging technologies.

Boulton, William R.↗

On Designing Lightweight Threads for Substrate Software

Existing user-level thread packages employ a 'black box' design approach, where the implementation of the threads is hidden from the user. While this approach is often sufficient for application-level programmers, it hides critical design decisions that system-level programmers must be able to change in order to provide efficient service for high-level systems. By applying the principles of Open Implementation Analysis and Design, we construct a new user-level threads package that supports common thread abstractions and a well-defined meta-interface for altering the behavior of these abstractions. As a result, system-level programmers will have the advantages of using high-level thread abstractions without having to sacrifice performance, flexibility or portability.

Haines, Matthew↗

Load Balancing Sequences of Unstructured Adaptive Grids

Mesh adaption is a powerful tool for efficient unstructured grid computations but causes load imbalance on multiprocessor systems. To address this problem, we have developed PLUM, an automatic portable framework for performing adaptive large-scale numerical computations in a message-passing environment. This paper makes several important additions to our previous work. First, a new remapping cost model is presented and empirically validated on an SP2. Next, our load balancing strategy is applied to sequences of dynamically adapted unstructured grids. Results indicate that our framework is effective on many processors for both steady and unsteady problems with several levels of adaption. Additionally, we demonstrate that a coarse starting mesh produces high quality load balancing, at a fraction of the cost required for a fine initial mesh. Finally, we show that the data remapping overhead can be significantly reduced by applying our heuristic processor reassignment algorithm.

Biswas, Rupak↗

Processors, Pipelines, and Protocols for Advanced Modeling Networks

Predictive capabilities arise from our understanding of natural processes and our ability to construct models that accurately reproduce these processes. Although our modeling state-of-the-art is primarily limited by existing computational capabilities, other technical areas will soon present obstacles to the development and deployment of future predictive capabilities. Advancement of our modeling capabilities will require not only faster processors, but new processing algorithms, high-speed data pipelines, and a common software engineering framework that allows networking of diverse models that represent the many components of Earth's climate and weather system. Development and integration of these new capabilities will pose serious challenges to the Information Systems (IS) technology community. Designers of future IS infrastructures must deal with issues that include performance, reliability, interoperability, portability of data and software, and ultimately, the full integration of various ES model systems into a unified ES modeling network.

Coughlan, Joseph↗

Taking evolutionary circuit design from experimentation to implementation: some useful techniques and a silicon demonstration

Current techniques in evolutionary synthesis of analogue and digital circuits designed at transistor level have focused on achieving the desired functional response, without paying sufficient attention to issues needed for a practical implementation of the resulting solution. No silicon fabrication of circuits with topologies designed by evolution has been done before, leaving open questions on the feasibility of the evolutionary circuit design approach, as well as on how high-performance, robust, or portable such designs could be when implemented in hardware. It is argued that moving from evolutionary 'design-for experimentation' to 'design-for-implementation' requires, beyond inclusion in the fitness function of measures indicative of circuit evaluation factors such as power consumption and robustness to temperature variations, the addition of certain evaluation techniques that are not common in conventional design. Several such techniques that were found to be useful in evolving designs for implementation are presented; some are general, and some are particular to the problem domain of transistor-level logic design, used here as a target application. The example used here is a multifunction NAND/NOR logic gate circuit, for which evolution obtained a creative circuit topology more compact than what has been achieved by multiplexing a NAND and a NOR gate. The circuit was fabricated in a 0.5 mum CMOS technology and silicon tests showed good correspondence with the simulations.

digital circuits designs↗