Results for “thread parallelism” — Page 17

NASA NTRS2002

Growth of Defect-Free 3C-Sic on 4H- and 6H-SIC Mesas Using Step-Free Surface Heteroepitaxy

A new growth process, herein named step-free surface heteroepitaxy, has achieved 3C-SiC films completely free of double positioning boundaries and stacking faults on 4H-SiC and 6H-SiC substrate mesas. The process is based upon the initial 2-dimensional nucleation and lateral expansion of a single island of 3C-SiC on a 4H- or 6H-SiC mesa surface that is completely free of bilayer surface steps. Our experimental results indicate that substrate-epilayer in-plane lattice mismatch (Delta/a = 0.0854% for 3C/4H) is at least partially relieved parallel to the interface in the initial bilayers of the heterofilm, producing an at least partially relaxed 3C-SiC film without dislocations that undesirably thread through the thickness of the epilayer. This result should enable realization of improved 3C-SiC devices.

Neudeck, Philip G.↗

NASA NTRS2001

Growth of Defect-Free 3C-SiC on 4H- and 6H-SiC Mesas Using Step-Free Surface Heteroepitaxy

A new growth process, herein named step-free surface heteroepitaxy, has achieved 3CSiC films completely free of double positioning boundaries and stacking faults on 4H-SiC and 6H-SiC substrate mesas. The process is based upon the initial 2-dimensional nucleation and lateral expansion of a single island of 3C-SiC on a 4H- or 6H-SiC mesa surface that is completely free of bilayer surface steps. Our experimental results indicate that substrate-epilayer in-plane lattice mismatch (delta a/a = 0.0854% for 3C/4H) is at least partially relieved parallel to the interface in the initial bilayers of the heterofilm, producing an at least partially relaxed 3C-SiC film without dislocations that undesirably thread through the thickness of the epilayer. This result should enable realization of improved 3C-SiC devices.

Neudeck, Philip G.↗

DOE OSTI2019

PRIMA-X - Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing

The PRIMA-X (Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing) project is the successor of the DOE PRIMA (Performance Refactoring of Instrumentation, Measurement, and Analysis Technologies for Petascale Computing) project, which addressed the challenge of creating a core measurement infrastructure that would serve as a common platform for both integrating leading parallel performance systems (notably TAU and Scalasca) and developing next-generation scalable performance tools. The PRIMA-X project shifts the focus away from refactorization of robust performance tools towards a re-targeting of the parallel performance measurement and analysis architecture for extreme scales. The massive concurrency, asynchronous execution dynamics, hardware heterogeneity, and multi-objective prerequisites (performance, power, resilience) that identify exascale systems introduce fundamental constraints on the ability to carry forward existing performance methodologies. In particular, there must be a deemphasis of per-thread observation techniques to significantly reduce the otherwise unsustainable flood of redundant performance data. Instead, it will be necessary to assimilate multi-level resource observations into macroscopic performance views, from which resilient performance metrics can be attributed to the computational features of the application. This requires a scalable framework for node-level and system-wide monitoring and runtime analyses of dynamic performance information. Also, the interest in optimizing parallelism parameters with respect to performance and energy drives the integration of tool capabilities in the exascale environment further. Initially, PRIMA-X was a collaborative project between the University of Oregon (lead institution) and the German Research School for Simulation Sciences (GRS). Because Prof. Wolf, the PI at GRS, accepted a position as full professor at Technische Universitaet Darmstadt (TU Darmstadt) starting February 1st, 2015, the work of GRS was continued at TU Darmstadt. This report covers the work at TU Darmstadt after the transition. The first main accomplishment of TU Darmstadt is the development of different techniques to aggregate performance data on the level of threads. TU Darmstadt evaluated different schemes designed at GRS during the first phase of this project and integrated them into Score-P, a widely used performance measurement framework for HPC applications. The second main accomplishment is a substantial increase of Score-P’s scalability, achieved by improving its internal representation of the underlying system. Third, we extended our performance-modeling tool Extra-P to automatically create models with more than one input parameter (e.g., process count and input size), which was previously impossible. These models allow the performance behavior of an application to be extrapolated to larger machines. Specific applications of the new multi-parameter capability realized in this project include modeling the isoefficiency function of task-based applications and a novel co-design methodology. Further extensions of Extra-P comprise online modeling functionality, automatic refinement of the model search space, and segmented performance modeling. Further contributions include new locality metrics for both shared- and distributed-memory applications, a new way of measuring the impact of inter-application inference on the execution time of an application, and finally an automatic method that selects appropriate OpenMP constructs for the parallelization of sequential code and classifies the affected variables based on their sharing semantics.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2015

POLARIZATION STRUCTURE OF FILAMENTARY CLOUDS

Filaments are considered to be basic structures, and molecular clouds consist of filaments. Filaments are often observed as extending in the direction perpendicular to the interstellar magnetic field. The structure of filaments has been studied based on a magnetohydrostatic equilibrium model. Here we simulate the expected polarization pattern for isothermal magnetohydrostatic filaments. The filament exhibits a polarization pattern in which the magnetic field is apparently perpendicular to the filament when observed from the direction perpendicular to the magnetic field. When the line of sight is parallel to the global magnetic field, the observed polarization pattern is dependent on the center-to-surface density ratio for the filament and the concentration of the gas mass toward the central magnetic flux tube. Filaments with low center-to-surface density ratios have an insignificant degree of polarization when observed from the direction parallel to the global magnetic field. However, models with a large center-to-surface density ratio have polarization patterns that indicate that the filament is perpendicularly threaded by the magnetic field. When mass is heavily concentrated at the central magnetic flux tube, which can be realized by the ambipolar diffusion process, the polarization pattern is similar to that expected for a low center-to-surface density contrast.

79 ASTRONOMY AND ASTROPHYSICS↗

NASA NTRS1998

Observations of Ion Signatures of Magnetic Reconnection for Northward IMF

Magnetic merging at Earth's magnetopause produces distinct mixtures of ions and electrons as well as signatures in their distribution functions. High resolution measurements allow for the separation of the different distributions and quantification of their characteristics. This provides details on the temporal and spatial nature of the merging site and the resulting history of the merged fields. The event of May 29, 1996 resulted in remote observations of the effects of reconnection on both magnetosheath and magnetosphere populations for a period of approximately three hours. Three-dimensional ion distributions obtained by the Thermal Ion Dynamics Experiment on the Polar spacecraft show that field lines threading the spacecraft's location in the northern cusp region contained a mix of D-shaped ions from the magnetosheath and accelerated magnetospheric ions both moving parallel to the local magnetic field. This mix of ions resulted from transmission of magnetosheath ions across the magnetopause at speeds greater than the de-Hoffman-Teller speed and the reflection of cold, slow-moving plasmasphere-like ions at the magnetopause. These observations are used to conclude that these field lines were connected to the ionosphere in the northern hemisphere and, southward of the spacecraft, the interplanetary magnetic field and crossed the magnetopause in the equatorial region southward of the spacecraft.

Chandler, Michael O.↗

DOE OSTI2016

PRIMA-X Final Report

The PRIMA-X (Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing) project is the successor of the DOE PRIMA (Performance Refactoring of Instrumentation, Measurement, and Analysis Technologies for Petascale Computing) project, which addressed the challenge of creating a core measurement infrastructure that would serve as a common platform for both integrating leading parallel performance systems (notably TAU and Scalasca) and developing next-generation scalable performance tools. The PRIMA-X project shifts the focus away from refactorization of robust performance tools towards a re-targeting of the parallel performance measurement and analysis architecture for extreme scales. The massive concurrency, asynchronous execution dynamics, hardware heterogeneity, and multi-objective prerequisites (performance, power, resilience) that identify exascale systems introduce fundamental constraints on the ability to carry forward existing performance methodologies. In particular, there must be a deemphasis of per-thread observation techniques to significantly reduce the otherwise unsustainable flood of redundant performance data. Instead, it will be necessary to assimilate multi-level resource observations into macroscopic performance views, from which resilient performance metrics can be attributed to the computational features of the application. This requires a scalable framework for node-level and system-wide monitoring and runtime analyses of dynamic performance information. Also, the interest in optimizing parallelism parameters with respect to performance and energy drives the integration of tool capabilities in the exascale environment further. Initially, PRIMA-X was a collaborative project between the University of Oregon (lead institution) and the German Research School for Simulation Sciences (GRS). Because Prof. Wolf, the PI at GRS, accepted a position as full professor at Technische Universität Darmstadt (TU Darmstadt) starting February 1st, 2015, the project ended at GRS on January 31st, 2015. This report reflects the work accomplished at GRS until then. The work of GRS is expected to be continued at TU Darmstadt. The first main accomplishment of GRS is the design of different thread-level aggregation techniques. We created a prototype capable of aggregating the thread-level information in performance profiles using these techniques. The next step will be the integration of the most promising techniques into the Score-P measurement system and their evaluation. The second main accomplishment is a substantial increase of Score-P’s scalability, achieved by improving the design of the system-tree representation in Score-P’s profile format. We developed a new representation and a distributed algorithm to create the scalable system tree representation. Finally, we developed a lightweight approach to MPI wait-state profiling. Former algorithms either needed piggy-backing, which can cause significant runtime overhead, or tracing, which comes with its own set of scaling challenges. Our approach works with local data only and, thus, is scalable and has very little overhead.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

VTK-m User's Guide (V.1.6)

High-performance computing relies on ever finer threading. Advances in processor technology include ever greater numbers of cores, hyperthreading, accelerators with integrated blocks of cores, and special vectorized instructions, all of which require more software parallelism to achieve peak performance. Traditional visualization solutions cannot support this extreme level of concurrency. Extreme scale systems require a new programming model and a fundamental change in how we design algorithms. To address these issues we created VTK-m: the visualization toolkit for multi-/many-core architectures.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

VTK-m User's' Guide (V.1.7)

High-performance computing relies on ever finer threading. Advances in processor technology include ever greater numbers of cores, hyperthreading, accelerators with integrated blocks of cores, and special vectorized instructions, all of which require more software parallelism to achieve peak performance. Traditional visualization solutions cannot support this extreme level of concurrency. Extreme scale systems require a new programming model and a fundamental change in how we design algorithms. To address these issues we created VTK-m: the visualization toolkit for multi-/many-core architectures. VTK-m supports a number of algorithms and the ability to design further algorithms through a top-down design with an emphasis on extreme parallelism. VTK-m also provides support for finding and building links across topologies, making it possible to perform operations that determine manifold surfaces, interpolate generated values, and find adjacencies. Although VTK-m provides a simplified high-level interface for programming, its template-based code removes the overhead of abstraction. VTK-m simplifies the development of parallel scientific visualization algorithms by providing a framework of supporting functionality that allows developers to focus on visualization operations. Consider the listings in Figure 1.1 that compares the size of the implementation for the Marching Cubes algorithm in VTK-m with the equivalent reference implementation in the CUDA software development kit. Because VTK-m internally manages the parallel distribution of work and data, the VTK-m implementation is shorter and easier to maintain. Additionally, VTK-m provides data abstractions not provided by other libraries that make code written in VTK-m more versatile.This book includes contributions from the VTK-m community including the VTK-m development team and the user community.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

The VTK-m Users' Guide (V.1.9)

High-performance computing relies on ever finer threading. Advances in processor technology include ever greater numbers of cores, hyperthreading, accelerators with integrated blocks of cores, and special vectorized instructions, all of which require more software parallelism to achieve peak performance. Traditional visualization solutions cannot support this extreme level of concurrency. Extreme scale systems require a new programming model and a fundamental change in how we design algorithms. To address these issues we created VTK-m: the visualization toolkit for multi-/many-core architectures. VTK-m supports a number of algorithms and the ability to design further algorithms through a top-down design with an emphasis on extreme parallelism. VTK-m also provides support for finding and building links across topologies, making it possible to perform operations that determine manifold surfaces, interpolate generated values, and find adjacencies. Although VTK-m provides a simplified high-level interface for programming, its template-based code removes the overhead of abstraction. VTK-m simplifies the development of parallel scientific visualization algorithms by providing a framework of supporting functionality that allows developers to focus on visualization operations. Consider the listings in Figure 1.1 that compares the size of the implementation for the Marching Cubes algorithm in VTK-m with the equivalent reference implementation in the CUDA software development kit. Because VTK-m internally manages the parallel distribution of work and data, the VTK-m implementation is shorter and easier to maintain. Additionally, VTK-m provides data abstractions not provided by other libraries that make code written in VTK-m more versatile.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

The VTK-m Users' Guide (V.2.0)

High-performance computing relies on ever finer threading. Advances in processor technology include ever greater numbers of cores, hyperthreading, accelerators with integrated blocks of cores, and special vectorized instructions, all of which require more software parallelism to achieve peak performance. Traditional visualization solutions cannot support this extreme level of concurrency. Extreme scale systems require a new programming model and a fundamental change in how we design algorithms. To address these issues we created VTK-m: the visualization toolkit for multi-/many-core architectures. VTK-m supports a number of algorithms and the ability to design further algorithms through a top-down design with an emphasis on extreme parallelism. VTK-m also provides support for finding and building links across topologies, making it possible to perform operations that determine manifold surfaces, interpolate generated values, and find adjacencies. Although VTK-m provides a simplified high-level interface for programming, its template-based code removes the overhead of abstraction. VTK-m simplifies the development of parallel scientific visualization algorithms by providing a framework of supporting functionality that allows developers to focus on visualization operations. Consider the listings in Figure 1.1 that compares the size of the implementation for the Marching Cubes algorithm in VTK-m with the equivalent reference implementation in the CUDA software development kit. Because VTK-m internally manages the parallel distribution of work and data, the VTK-m implementation is shorter and easier to maintain. Additionally, VTK-m provides data abstractions not provided by other libraries that make code written in VTK-m more versatile.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

The VTK-m User's Guide (V. 2.2)

High-performance computing relies on ever finer threading. Advances in processor technology include ever greater numbers of cores, hyperthreading, accelerators with integrated blocks of cores, and special vectorized instructions, all of which require more software parallelism to achieve peak performance. Traditional visualization solutions cannot support this extreme level of concurrency. Extreme scale systems require a new programming model and a fundamental change in how we design algorithms. To address these issues we created VTK-m: the visualization toolkit for multi-/many-core architectures. VTK-m supports a number of algorithms and the ability to design further algorithms through a top-down design with an emphasis on extreme parallelism. VTK-m also provides support for finding and building links across topologies, making it possible to perform operations that determine manifold surfaces, interpolate generated values, and find adjacencies. Although VTK-m provides a simplified high-level interface for programming, its template-based code removes the overhead of abstraction.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

The Viskores User's Guide (V.1.0)

High-performance computing relies on ever finer threading. Advances in processor technology include ever greater numbers of cores, hyperthreading, accelerators with integrated blocks of cores, and special vectorized instructions, all of which require more software parallelism to achieve peak performance. Traditional visualization solutions cannot support this extreme level of concurrency. Extreme scale systems require a new programming model and a fundamental change in how we design algorithms. To address these issues we created Viskores: the visualization toolkit for multi-/many-core architectures. Viskores supports a number of algorithms and the ability to design further algorithms through a top-down design with an emphasis on extreme parallelism. Viskores also provides support for finding and building links across topologies, making it possible to perform operations that determine manifold surfaces, interpolate generated values, and find adjacencies. Although Viskores provides a simplified high-level interface for programming, its template-based code removes the overhead of abstraction.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

The Viskores User's Guide, Release 1.1

High-performance computing relies on ever finer threading. Advances in processor technology include ever greater numbers of cores, hyperthreading, accelerators with integrated blocks of cores, and special vectorized instructions, all of which require more software parallelism to achieve peak performance. Traditional visualization solutions cannot support this extreme level of concurrency. Extreme scale systems require a new programming model and a fundamental change in how we design algorithms. To address these issues we created Viskores: the visualization toolkit for multi/many-core architectures. Viskores supports a number of algorithms and the ability to design further algorithms through a top-down design with an emphasis on extreme parallelism. Viskores also provides support for finding and building links across topologies, making it possible to perform operations that determine manifold surfaces, interpolate generated values, and find adjacencies. Although Viskores provides a simplified high-level interface for programming, its template-based code removes the overhead of abstraction.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2014

Parallel Monte Carlo Methods for Heterogeneous Hardware Computer Systems Using GPUs and Coprocessors: Recent Development of ARCHER Code - Paper 54

Traditional methods of accelerating Monte Carlo (MC) calculations typically use CPUs as the computing unit. The parallelism is based upon multithreading on a multi-core processor, and message passing interface (MPI) across many processors and nodes. In recent years, the hardware accelerators have been introduced by the high performance computing industry as an alternative approach to achieve massive parallelism. Hardware accelerators have the advantage of high Floating-point Operations Per Second (FLOPS) and high energy efficiency. Examples include graphics processing units (GPUs) and coprocessors. Compute-intensive programs can be off-loaded to them to be concurrently executed by hundreds or thousands of active threads. Existing production MC codes, however, cannot be directly compiled or executed on the new platforms. It is therefore necessary to rewrite or redevelop the code using the hardware accelerator specific programming models and APIs. Several studies have been conducted on using GPUs to accelerate MC calculations in reactor analysis and medical physics. In this paper, we present the recent progress at Rensselaer Polytechnic Institute (RPI) in developing a new parallel MC code called ARCHER (Accelerated Radiation-transport Computations in Heterogeneous Environments) for coupled photon-electron transport simulations. The code is designed as a test bed to evaluate the efficacy of heterogeneous computing systems for low-cost MC-based radiation dosimetric calculations. The code has three variants corresponding to three parallel hardware platforms: ARCHER-CPU (multi-core CPU), ARCHER-GPU (Nvidia GPU) and ARCHER-COP (Intel Xeon Phi coprocessor). The code has been used for several applications, including CT imaging dosimetry, radiotherapy dosimetry and radiation shielding design. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗

DOE OSTI2023

Previously uncharacterized rectangular bacterial structures in the dolphin mouth

Much remains to be explored regarding the diversity of uncultured, host-associated microbes. Here, we describe rectangular bacterial structures (RBSs) in the mouths of bottlenose dolphins. DNA staining revealed multiple paired bands within RBSs, suggesting the presence of cells dividing along the longitudinal axis. Cryogenic transmission electron microscopy and tomography showed parallel membrane-bound segments that are likely cells, encapsulated by an S-layer-like periodic surface covering. RBSs displayed unusual pilus-like appendages with bundles of threads splayed at the tips. We present multiple lines of evidence, including genomic DNA sequencing of micromanipulated RBSs, 16S rRNA gene sequencing, and fluorescence in situ hybridization, suggesting that RBSs are bacterial and distinct from the genera Simonsiella and Conchiformibius (family Neisseriaceae), with which they share similar morphology and division patterning. Our findings highlight the diversity of novel microbial forms and lifestyles that await characterization using tools complementary to genomics such as microscopy.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS1986

An optical imaging and polarimetric study of the Lynds 723 and Barnard 335 molecular outflow regions

Optical polarization measurements are reported for a sample of stars viewed through the periphery of two dense molecular clouds, Barnard 335 and Lynds 723. These observations suggest that the direction of the magnetic field threading these clouds lies along position angle 111 + or - 4 deg for B335 and 90 + or - 8 deg for L723. In each case, the deduced field direction is approximately parallel to the direction defined by a collimated bipolar molecular outflow driven by a highly obscured FIR source. R, I, and H-alpha CCD images of these regions reveal knots of optical emission apparently associated with the molecular outflows. In the case of L723, two emission features are found within the blueshifted wing of the molecular outflow; along with the FIR source, these knots define a position angle nearly identical to that of the molecular flow. For B335, the observed emission knot lies in the redshifted wing of the molecular outflow along a position angle approximately equal to that of the flow.

Vrba, F. J.↗

NASA NTRS1991

Mechanical strain isolator mount

Certain devices such as optical instruments must preserve their alignmental integrity while being subjected to mechanical strain. A mechanical strain isolator mount is provided to preserve the alignmental integrity of an alignment sensitive instrument. An alignment sensitive instrument is mounted on a rectangular base. Flexural legs are connected at their proximal ends to the rectangular base. Flexural legs are also spaced parallel to the sides. Mounting pads are connected to the legs at the distal end and the mechanical strain isolator mount is attached to the substrate by means of threaded bolts. When a mounting pad and its respective leg is subjected to lateral strain in either the X or Y direction via the substrate, the respective leg relieves the strain by bending in the direction of the strain. An axial strain on a mounting pad in the Z direction is relieved by a rotational motion of the legs in the direction of the strain. When the substrate is stress free, the flexural legs return to their original condition and thus preserve the original alignment integrity of the alignment sensitive instrument.

James, Gordon E.↗

NASA NTRS2002

Gilgamesh: A Multithreaded Processor-In-Memory Architecture for Petaflops Computing

Processor-in-Memory (PIM) architectures avoid the von Neumann bottleneck in conventional machines by integrating high-density DRAM and CMOS logic on the same chip. Parallel systems based on this new technology are expected to provide higher scalability, adaptability, robustness, fault tolerance and lower power consumption than current MPPs or commodity clusters. In this paper we describe the design of Gilgamesh, a PIM-based massively parallel architecture, and elements of its execution model. Gilgamesh extends existing PIM capabilities by incorporating advanced mechanisms for virtualizing tasks and data and providing adaptive resource management for load balancing and latency tolerance. The Gilgamesh execution model is based on macroservers, a middleware layer which supports object-based runtime management of data and threads allowing explicit and dynamic control of locality and load balancing. The paper concludes with a discussion of related research activities and an outlook to future work.

management locality load balance↗