The TOFOR Neutron Spectrometer For High-Performance Measurements of D Plasma Fuel Ion Properties

2008 ◽  
Author(s):  
M. Gatu Johnson ◽  
L. Giacomelli ◽  
A. Hjalmarsson ◽  
M. Weiszflog ◽  
E. Andersson Sundén ◽  
...  
Keyword(s):  
High Performance ◽  
Performance Measurements ◽  
Neutron Spectrometer

scholarly journals JAliEn: the new ALICE high-performance and high-scalability Grid framework

2019 ◽  
Vol 214 ◽  
pp. 03037
Author(s):  
M. Martinez Pedreira ◽  
C. Grigoras ◽  
V. Yurchenko
Keyword(s):  
Data Processing ◽  
High Performance ◽  
Data Access ◽  
Performance Measurements ◽  
Alice Experiment ◽  
Grid Middleware ◽  
Software Upgrades ◽  
Order Of Magnitude ◽  
And Performance ◽  
And Storage

The ALICE experiment will undergo extensive hardware and software upgrades for the LHC Run3. This translates in significant increase of the CPU and storage resources required for data processing, and at the same time the data access rates will grow linearly with the amount of resources. JAliEn (Java ALICE Environment) is the new Grid middleware designed to scale-out horizontally to fulfil the computing needs of the upgrade, and at the same time to modernize all parts of the distributed system software. This paper will present the architecture of the JAliEn framework, the technologies used and performance measurements. This work will also describe the next generation solution that will replace our main database backend, the AliEn File Catalogue. The catalogue is an integral part of the system, containing the metadata of all files written to the distributed Grid storage and also provides powerful search and data manipulation tools. As for JAliEn, the focus has been put onto horizontal scalability, with the aim to handle near exascale data volumes and order of magnitude more workload than the currently used Grid middleware. Lastly, this contribution will present how JAliEn manages the increased complexity of the tasks associated with the new ALICE data processing and analysis framework (ALFA) and multi-core environments.

scholarly journals Kemari: A Portable High Performance Fortran System for Distributed Memory Parallel Processors

1997 ◽  
Vol 6 (1) ◽  
pp. 41-58 ◽  
Author(s):  
T. Kamachi ◽  
A. MÜller ◽  
R. RÜhl ◽  
Y. Seo ◽  
K. Suehiro ◽  
...  
Keyword(s):  
Message Passing ◽  
High Performance ◽  
Message Passing Interface ◽  
Data Distribution ◽  
Programming Environment ◽  
Performance Measurements ◽  
High Performance Fortran ◽  
Additional Control ◽  
Compilation Process ◽  
Structured Problems

We have developed a compilation system which extends High Performance Fortran (HPF) in various aspects. We support the parallelization of well-structured problems with loop distribution and alignment directives similar to HPF's data distribution directives. Such directives give both additional control to the user and simplify the compilation process. For the support of unstructured problems, we provide directives for dynamic data distribution through user-defined mappings. The compiler also allows integration of message-passing interface (MPI) primitives. The system is part of a complete programming environment which also comprises a parallel debugger and a performance monitor and analyzer. After an overview of the compiler, we describe the language extensions and related compilation mechanisms in detail. Performance measurements demonstrate the compiler's applicability to a variety of application classes.

Parallel CFD-DEM for Fluid-Particle Systems

Volume 3 ◽  
2004 ◽  
Author(s):  
Xiang Zhao ◽  
Jun Wang ◽  
Sijun Zhang
Keyword(s):  
Parallel Algorithm ◽  
High Performance ◽  
Particle Systems ◽  
Solid Particles ◽  
Fluid Particle ◽  
Particle Flow ◽  
Performance Measurements ◽  
Discrete Flow ◽  
Computational Fluid Dynamics Cfd ◽  
Computationally Intensive

This paper presents numerical methods and parallel algorithms for modeling the fluid-particle flow in gas fluidization of multi-sized particles. This work involves combined Computational Fluid Dynamics (CFD) and Discrete Element Method (DEM) to describe continuum flow of fluids and discrete flow of solid particles, respectively. Such simulations are extremely computationally intensive. To meet the challenge and produce high-performance, state-of-the-art computational tools capable of simulating the industrial fluid-particle systems, the parallel computing techniques are used with special emphasis of domain decomposition, dynamic load balancing and parallel algorithm. A study of the implementation of a parallel algorithm is also presented, together with performance measurements on PC cluster machines. The results obtained validate not only the parallel algorithm, but also the potential role of such computer systems in industrial fluid-particle flow simulations.

Circumferentially Non-Uniform Flow in the Rear Stage of a Multistage Compressor

2015 ◽  
Author(s):  
Simon Stummann ◽  
Peter Jeschke ◽  
Timo Metzler
Keyword(s):  
High Performance ◽  
Uniform Flow ◽  
Performance Measurements ◽  
Wake Interference ◽  
Unsteady Wake ◽  
Numerical Effort ◽  
Wake Interaction ◽  
Compressor Performance ◽  
Multistage Compressor ◽  
Main Effects

Full annulus midspan URANS simulations are performed to examine wake interaction for rows with different blade counts. The amount of non-uniform flow is studied particularly in the rear stages of a 3.5 stage compressor with a different blade count at all rows. A high-performance cluster was used for the required full annulus URANS simulations. Due to the high numerical effort, three representative operating points are investigated in quasi-3D. The simulations are performed at a midspan stream tube which take into consideration the contracting duct of the compressor. The results indicate two main effects: wake-wake interference and wake-airfoil interaction. Both effects are related to the particular clocking position, which affect each other accordingly. At the aerodynamic design point, non-uniform flow at the rear stage has a significant impact. Intensified unsteady wake-airfoil interaction near the surge line causes circumferential unequal flow separation. Close to choke, the shock strength depends on the Mach number, hence jet and wake inflow affects different losses. The frequently used assumption of periodic flow disregards the deviations shown. Based on the numerical results, the accuracy of performance measurements is presented. Non-uniform flow causes inaccuracy of more than one percentage point for stage and compressor performance measurements, which is more than commonly requested. In summary, interaction of rows with dissimilar blade count leads to non-uniform flow in rear stages that needs to be considered in performance measurements.

SOME METACOMPUTING EXPERIENCES FOR SCIENTIFIC APPLICATIONS

1999 ◽  
Vol 09 (02) ◽  
pp. 243-252 ◽  
Author(s):  
O. LARSSON ◽  
M. FEIG ◽  
L. JOHNSSON
Keyword(s):  
Molecular Dynamics ◽  
Thin Layer ◽  
High Performance ◽  
Large Scale ◽  
Distributed Memory ◽  
Parallel Applications ◽  
Globus Toolkit ◽  
Performance Measurements ◽  
Correct Execution ◽  
Application Codes

We demonstrate good metacomputing efficiency and portability for three typical large-scale parallel applications; one molecular dynamics code and two electromagnetics codes. The codes were developed for distributed memory parallel platforms using Fortran77 or Fortran90 with MPI. The performance measurements were made for a testbed of two IBM SPs connected through the vBNS. No change of the application codes were required for correct execution of the codes on the testbed using the Globus Toolkit for the required metacomputing services. However, we observe that for good performance, it may be necessary for MPI codes to make use of overlapped computation and communication. For such MPI codes, a communications library designed for hierarchical or clustered communication can yield very good metacomputing efficiencies when high-performance networks, such as the vBNS or the Abilene networks, such as the vBNS or the Abilene networks, are used for platform connectivity. We demonstrate this by inserting a thin layer between the MPI application and the MPI libraries, providing some clustering of communications between platforms.

scholarly journals VFC: The Vienna Fortran Compiler

1999 ◽  
Vol 7 (1) ◽  
pp. 67-81 ◽  
Author(s):  
Siegfried Benkner
Keyword(s):  
Message Passing ◽  
High Performance ◽  
Data Distribution ◽  
Data Locality ◽  
Performance Measurements ◽  
Fortran Compiler ◽  
Work Distribution ◽  
Local Access ◽  
High Level ◽  
Access Patterns

High Performance Fortran (HPF) offers an attractive high‐level language interface for programming scalable parallel architectures providing the user with directives for the specification of data distribution and delegating to the compiler the task of generating an explicitly parallel program. Available HPF compilers can handle regular codes quite efficiently, but dramatic performance losses may be encountered for applications which are based on highly irregular, dynamically changing data structures and access patterns. In this paper we introduce the Vienna Fortran Compiler (VFC), a new source‐to‐source parallelization system for HPF+, an optimized version of HPF, which addresses the requirements of irregular applications. In addition to extended data distribution and work distribution mechanisms, HPF+ provides the user with language features for specifying certain information that decisively influence a program’s performance. This comprises data locality assertions, non‐local access specifications and the possibility of reusing runtime‐generated communication schedules of irregular loops. Performance measurements of kernels from advanced applications demonstrate that with a high‐level data parallel language such as HPF+ a performance close to hand‐written message‐passing programs can be achieved even for highly irregular codes.

scholarly journals 3-D Edge-Oriented Electrocatalytic NiCo2S4 Nanoflakes on Vertical Graphene for Li-S Batteries

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Wenyue Li ◽  
Shiqi Li ◽  
Ayrton A. Bernussi ◽  
Zhaoyang Fan
Keyword(s):  
Active Sites ◽  
High Performance ◽  
Carbon Nanofiber ◽  
Coulombic Efficiency ◽  
Small Mass ◽  
Performance Measurements ◽  
Free Standing ◽  
Shuttle Effect ◽  
Catalytic Function ◽  
Polysulfide Shuttle

Polysulfide shuttle effect, causing extremely low Coulombic efficiency and cycling stability, is one of the toughest challenges hindering the development of practical lithium sulfur batteries (LSBs). Introducing catalytic nanostructures to stabilize the otherwise soluble polysulfides and promote their conversion to solids has been proved to be an effective strategy in attacking this problem, but the heavy mass of catalysts often results in a low specific energy of the whole electrode. Herein, by designing and synthesizing a free-standing edge-oriented NiCo2S4/vertical graphene functionalized carbon nanofiber (NCS/EOG/CNF) thin film as a catalytic overlayer incorporated in the sulfur cathode, the polysulfide shuttle effect is largely alleviated, revealed by the enhanced electrochemical performance measurements and the catalytic function demonstration. Different from other reports, the NiCo2S4 nanosheets synthesized here have a 3-D edge-oriented structure with fully exposed edges and easily accessible in-plane surfaces, thus providing a high density of active sites even with a small mass. The EOG/CNF scaffold further renders the high conductivity in the catalytic structure. Combined, this novel structure, with high sulfur loading and high sulfur fraction, leads to high-performance sulfur cathodes toward a practical LSB technology.

scholarly journals An Inexpensive, High-Precision, Modular Spherical Treadmill Setup Optimized for Drosophila Experiments

2021 ◽  
Vol 15 ◽  
Author(s):  
Frank Loesche ◽  
Michael B. Reiser
Keyword(s):  
High Performance ◽  
Neural Control ◽  
Motor Behavior ◽  
Genetic Model ◽  
Low Cost ◽  
Sensory Stimulation ◽  
Integrated System ◽  
Local Network ◽  
Model Organisms ◽  
Performance Measurements

To pursue a more mechanistic understanding of the neural control of behavior, many neuroethologists study animal behavior in controlled laboratory environments. One popular approach is to measure the movements of restrained animals while presenting controlled sensory stimulation. This approach is especially powerful when applied to genetic model organisms, such as Drosophila melanogaster, where modern genetic tools enable unprecedented access to the nervous system for activity monitoring or targeted manipulation. While there is a long history of measuring the behavior of body- and head-fixed insects walking on an air-supported ball, the methods typically require complex setups with many custom components. Here we present a compact, simplified setup for these experiments that achieves high-performance at low cost. The simplified setup integrates existing hardware and software solutions with new component designs. We replaced expensive optomechanical and custom machined components with off-the-shelf and 3D-printed parts, and built the system around a low-cost camera that achieves 180 Hz imaging and an inexpensive tablet computer to present view-angle-corrected stimuli updated through a local network. We quantify the performance of the integrated system and characterize the visually guided behavior of flies in response to a range of visual stimuli. In this paper, we thoroughly document the improved system; the accompanying repository incorporates CAD files, parts lists, source code, and detailed instructions. We detail a complete ~$300 system, including a cold-anesthesia tethering stage, that is ideal for hands-on teaching laboratories. This represents a nearly 50-fold cost reduction as compared to a typical system used in research laboratories, yet is fully featured and yields excellent performance. We report the current state of this system, which started with a 1-day teaching lab for which we built seven parallel setups and continues toward a setup in our lab for larger-scale analysis of visual-motor behavior in flies. Because of the simplicity, compactness, and low cost of this system, we believe that high-performance measurements of tethered insect behavior should now be widely accessible and suitable for integration into many systems. This access enables broad opportunities for comparative work across labs, species, and behavioral paradigms.

Sign in / Sign up

Export Citation Format

Share Document