National Supercomputing Center Research Articles

Adsorption behavior of Fe atoms on a naphthalocyanine monolayer on Ag(111) surface**Project supported by the National Natural Science Foundation of China (Grant Nos. 61390501, 51325204, and 11204361), the National Basic Research Program of China (Grant Nos. 2011CB808401 and 2011CB921702), the National Key Scientific Instrument and Equipment Development Project of China (Grant No. 2013YQ1203451), the National Supercomputing Center in Tianjin, China,

Adsorption behavior of Fe atoms on a metal-free naphthalocyanine (H2Nc) monolayer on Ag(111) surface at room temperature has been investigated using scanning tunneling microscopy combined with density functional theory (DFT) based calculations. We found that the Fe atoms were adsorbed on the centers of H2Nc molecules and formed Fe–H2Nc complexes at low coverage. DFT calculations show that Fe sited in the center of the molecule is the most stable configuration, in good agreement with the experimental observations. After an Fe–H2Nc complex monolayer was formed, the extra Fe atoms self-assembled to Fe clusters of uniform size and adsorbed dispersively at the interstitial positions of Fe–H2Nc complex monolayer. Therefore, the H2Nc monolayer grown on Ag(111) could be a good template to grow dispersed magnetic metal atoms and clusters at room temperature for further investigation of their magnetism-related properties.

Vector Meson Mass in Finite Density and Temperature Lattice QCD* *Supported by the National Science Foundation of China (NSFC) under Grant Nos. 11335001, 11105153, 11405178. It is also supported in part by the DFG and the NSFC (No. 11261130311) through funds provided to the Sino-Germen CRC 110 “Symmetries and the Emergence of Structure in QCD”. The numerical calculations were performed

Vector meson mass values are studied at finite chemical potential and temperature in lattice QCD with lattice size of 24 × 122 × 6 using two flavors of staggered quarks. The investigation focuses on the change of the vector meson mass in the critical region close to Tc with two different types of chemical potentials switched on: the isoscalar chemical potential μs and its isovector counterpart μv. It is found that the vector meson mass increases in the QGP phase with both chemical potentials and decreases with μs in the confinement phase.

Measurement Processes and Destructive Testing of Fiber Concrete Foundation Slab Pattern

The main theme of this article is a measurement processes description and the results of experimental destructive test of the fiber concrete foundation slab pattern. The purpose of this research was to make a behavior analysis of the fiber concrete foundation slab pattern focused on the interaction between foundation slab and the subsoil. This experiment was realized on model of real construction, especially - the National Supercomputing Center IT4 Innovations - significant construction built in campus of VŠB - Technical University of Ostrava.

High efficient parallel numerical surface wave model based on an irregular quasi-rectangular domain decomposition scheme

To achieve high parallel efficiency for the global MASNUM surface wave model, the algorithm of an irregular quasi-rectangular domain decomposition and related serializing of calculating points and data exchanging schemes are developed and conducted, based on the environment of Message Passing Interface (MPI). The new parallel version of the surface wave model is tested for parallel computing on the platform of the Sunway BlueLight supercomputer in the National Supercomputing Center in Jinan. The testing involves four horizontal resolutions, which are 1°×1°, (1/2)°×(1/2)°, (1/4)°×(1/4)°, and (1/8)°×(1/8)°. These tests are performed without data Input/Output (IO) and the maximum amount of processors used in these tests reaches to 131072. The testing results show that the computing speeds of the model with different resolutions are all increased with the increasing of numbers of processors. When the number of processors is four times that of the base processor number, the parallel efficiencies of all resolutions are greater than 80%. When the number of processors is eight times that of the base processor number, the parallel efficiency of tests with resolutions of 1°×1°, (1/2)°×(1/2)° and (1/4)°×(1/4)° is greater than 80%, and it is 62% for the test with a resolution of (1/8)°×(1/8)° using 131072 processors, which is the nearly all processors of Sunway BlueLight. When the processor’s number is 24 times that of the base processor number, the parallel efficiencies for tests with resolutions of 1°×1°, (1/2)°×(1/2)°, and (1/4)° ×(1/4)° are 72%, 62%, and 38%, respectively. The speedup and parallel efficiency indicate that the irregular quasi-rectangular domain decomposition and serialization schemes lead to high parallel efficiency and good scalability for a global numerical wave model.

Early experiences in developing and managing the neuroscience gateway.

The last few decades have seen the emergence of computational neuroscience as a mature field where researchers are interested in modeling complex and large neuronal systems and require access to high performance computing machines and associated cyber infrastructure to manage computational workflow and data. The neuronal simulation tools, used in this research field, are also implemented for parallel computers and suitable for high performance computing machines. But using these tools on complex high performance computing machines remains a challenge because of issues with acquiring computer time on these machines located at national supercomputer centers, dealing with complex user interface of these machines, dealing with data management and retrieval. The Neuroscience Gateway is being developed to alleviate and/or hide these barriers to entry for computational neuroscientists. It hides or eliminates, from the point of view of the users, all the administrative and technical barriers and makes parallel neuronal simulation tools easily available and accessible on complex high performance computing machines. It handles the running of jobs and data management and retrieval. This paper shares the early experiences in bringing up this gateway and describes the software architecture it is based on, how it is implemented, and how users can use this for computational neuroscience research using high performance computing at the back end. We also look at parallel scaling of some publicly available neuronal models and analyze the recent usage data of the neuroscience gateway.

Experimental Testing of Fiberconcrete Foundation Slab Model

Experimental measurements described in this paper are a continuation of research focused on interaction of foundation concrete structures and subsoil. This problematic has been researching on the Faculty of Civil Engineering VSB - Technical University of Ostrava for long time. Is it one of the main research directions at the Department of Constructions. In 2013, the research was focused on the analysis of fiberconcrete foundation structures. Especially, It was tested a foundation slab model of the National Supercomputing Center IT4 Innovations. This significant construction is realized in campus of VŠB - Technical University of Ostrava right now. It was a big opportunity to compare a model test results with measurements from real construction.

Development of Temperature and Stress during Foundation Slab Concreting of National Supercomputer Centre IT4

In the paper the method of experimental temperature and stress measurement of reinforced concrete foundation slab during construction of the National Supercomputing Centre in Ostrava, Czech Republic is described. Measured results are compared with numerical analysis and time dependent development of concrete strength. Decreasing the tensile stress in concrete by use of the sliding joint was verified.

EXPERIMENTAL MEASUREMENT IN THE FOUNDATION SLAB OF NATIONAL SUPERCOMPUTER CENTRE

In the paper is described the method of experimental temperature and strain measurement of reinforced concrete foundation slab during building-up of National Supercomputing Centre in Ostrava. This is a continuous measurement during the construction of this special structure.

Numerical simulations of the dark universe: State of the art and the next decade

ABSTRACT We present a review of the current state of the art of cosmological dark matter simulations, with particular emphasis on the implications for dark matter detection efforts and studies of dark energy. This review is intended both for particle physicists, who may find the cosmological simulation literature opaque or confusing, and for astro-physicists, who may not be familiar with the role of simulations for observational and experimental probes of dark matter and dark energy. Our work is complementary to the contribution by Baldi in this issue, which focuses on the treatment of dark energy and cosmic acceleration in dedicated N-body simulations. Truly massive dark matter-only simulations are being conducted on national supercomputing centers, employing from several billion to over half a trillion particles to simulate the formation and evolution of cosmologically representative volumes (cosmic scale) or to zoom in on individual halos (cluster and galactic scale). These simulations cost millions of core-hours, require tens to hundreds of terabytes of memory, and use up to petabytes of disk storage. Predictions from such simulations touch on almost every aspect of dark matter and dark energy studies, and we give a comprehensive overview of this connection. We also discuss the limitations of the cold and collisionless DM-only approach, and describe in some detail efforts to include different particle physics as well as baryonic physics in cosmological galaxy formation simulations, including a discussion of recent results highlighting how the distribution of dark matter in halos may be altered. We end with an outlook for the next decade, presenting our view of how the field can be expected to progress.

Computational Performance of the High-Resolution Atmospheric Model FAMIL

AbstractThis paper describes the model speed and model In/Out (I/O) efficiency of the high-resolution atmospheric general circulation model FAMIL (Finite-volume Atmospheric Model of IAP/LASG) at the National Supercomputer Center in Tianjin, China, on its Tianhe-1A supercomputer platform. A series of three-model-day simulations were carried out with standard Aqua Planet Experiment (APE) designed within FAMIL to obtain the time stamp for the calculation of model speed, simulation cost, and model I/O efficiency. The results of the simulation demonstrate that FAMIL has remarkable scalability below 3456 and 6144 cores, and the lowest simulation costs are 1536 and 3456 cores for 12.5 km and 6.25 km resolutions, respectively. Furthermore, FAMIL has excellent I/O scalability and an efficiency of more than 80% on 6 I/Os and more than 99% on 1536 I/Os.

The TianHe-1A Supercomputer: Its Hardware and Software

This paper presents an overview of TianHe-1A (TH-1A) supercomputer, which is built by National University of Defense Technology of China (NUDT). TH-1A adopts a hybrid architecture by integrating CPUs and GPUs, and its interconnect network is a proprietary high-speed communication network. The theoretical peak performance of TH-1A is 4700 TFlops, and its LINPACK test result is 2566 TFlops. It was ranked the No. 1 on the TOP500 List released in November, 2010. TH-1A is now deployed in National Supercomputer Center in Tianjin and provides high performance computing services. TH-1A has played an important role in many applications, such as oil exploration, weather forecast, bio-medical research.

Grid Activities of the Swiss National Supercomputing Centre CSCS

Grid Computing is addressing the new paradigm of collaborative science, where discoveries are being sought in large national and international collaborations. Grids provide a means to share resources between different scientific communities. The aim is not only to enable collaborations through resource sharing, but also to make optimal use of each participating resource, trying to maximize the overall resource capacity to the benefit of science. Researchers throughout Switzerland have already engaged in several Grid-related projects of national and international scope. The Swiss National Supercomputing Centre CSCS is involved in many of these projects. This article describes some of the projects and their aims, and gives a brief overview on the next steps that may be taken to prepare Switzerland for the future in Grid technology.

Local supercomputing training in the computational sciences using remote national centers

Local training for high performance computing using remote national supercomputing centers is quite different from training at the centers themselves or using local machines. The local site computing and communication resources are a fraction of those available at the national centers. However, training at the local site has the potential of training more computational science and engineering students in high performance computing by including those who are unable to travel to the national center for training. The experience gained from supercomputing courses and workshops in the last 17 years at the University of Illinois at Chicago is described. These courses serve as the kernel in the program for training computational science and engineering students. Many training techniques are illustrated, such as key local user’s guides and starter problems that would be portable to other local sites. Training techniques are continually evolving to keep up with rapid changes in supercomputing. An essential feature of this program is the use of real supercomputer time on several supercomputer platforms at national centers with emphasis in solving large scale problems.

Use of the World Wide Web in astronomy teaching

I discuss the burgeoning World Wide Web and how it can be used to aid astronomy teaching.I supply a list of a variety of useful Web sites.The World Wide Web was invented 5 years ago at CERN, which is now translated as the European Laboratory for Particle Physics, as a way of aiding access to information from remote sites. The invention of graphic interfaces, notably Mosaic by a group at the National Supercomputer Center in Illinois and then Netscape Navigator as a private development by many of the original Mosaic people, led to an explosion in use of the Web. Millions of people around the world are now able to access information from over 100,000 Web sites.There is much astronomical information on the Web, though that information make up only a small fraction of all the information available through this medium.

Achieving Scalable Parallel Molecular Dynamics Using Dynamic Spatial Domain Decomposition Techniques

To achieve scalable parallel performance in molecular dynamics simulations, we have modeled and implemented several dynamic spatial domain decomposition algorithms. The modeling is based upon the bulk synchronous parallel architecture model (BSP), which describes supersteps of computation, communication, and synchronization. Using this model, we have developed prototypes that explore the differing costs of several spatial decomposition algorithms and then use this data to drive implementation of our molecular dynamics simulator,Sigma. The parallel implementation is not bound to the limitations of the BSP model, allowing us to extend the spatial decomposition algorithm. For an initial decomposition, we use one of the successful decomposition strategies from the BSP study and then subsequently use performance data to adjust the decomposition, dynamically improving the load balance. The motivating reason to use historical performance data is that the computation to predict a better decomposition increases in cost with the quality of prediction, while the measurement of past work often has hardware support, requiring only a slight amount of work to modify the decomposition for future simulation steps. In this paper, we present our adaptive spatial decomposition algorithms, the results of modeling them with the BSP, the enhanced spatial decomposition algorithm, and its performance results on computers available locally and at the national supercomputer centers.

Workload characterization using the CRAY hardware performance monitor

This paper describes some preliminary results about a workload characterization study at a national supercomputer center. This study is part of a larger project to develop an analytic methodology for the construction of arepresentative benchmark set. Our study reports on 292,254 user jobs during the period from June 1992 to July 1993 and represents about one-half of the wall clock time available on the four-processor CRAY Y-MP at the National Center for Supercomputing Applications during this time. The performance statistics we gathered in some sensedefine the workload because of the large fraction of the available time that was recorded. These statistics will allow us to “reverse engineer” a set of benchmarks that analytically represents the workload at this site.

The national research and education network: The early evolution of nren

A national multi‐gigabit‐per‐second research and education network known as the National Research and Education Network is to be established by 1996, according to the High‐Performance Computing Act of 1991 (P.L. 102–194) passed in December 1991. Commonly known as the NREN and referred to as the “information highway,” this electronic network is expected to provide scientific, educational, and economic benefits for the United States and to serve as the basis for an all‐encompassing National Information Infrastructure available to all citizens. The idea of the NREN began in the late 1960s in the Department of Defense and its Defense Advanced Research Projects Agency (DARPA) with the development of ARPANet, the first packet‐switching network. This evolved into the Internet, or Interim NREN, after the National Science Foundation (NSF) linked its national supercomputing centers with the NSFNet. The NSFNet is to be the technological backbone for the NREN, which will continue the networking begun by the Internet. Initially, the NREN is intended to interconnect researchers and resources of research institutions, educational institutions, industry, and government in every state.

National supercomputer centre urged for US

National supercomputer centre urged for US

A static and dynamic workload characterization study of the San Diego Supercomputer center Cray X-MP

The San Diego Supercomputer Center is one of four NSF sponsored national supercomputer centers. Up until January of 1990, its workhorse was a Cray X-MP, which served 2700 researchers from 170 institutions, spanning 44 states. In order to better understand how this supercomputer was utilized by its diverse community of users, we undertook a workload characterization study of the Cray X-MP. The goals of our study were twofold. First, we wished to characterize the workload at both the functional and resource levels. The functional level represents the user point of view: what types of programs users are running on the system. The resource level represents the system point of view: how the systems resources (CPU, memory, I/O bandwidth) are being used. Second, we wanted to see how the workload changed over an average weekday. Thus, we conducted a static characterization to understand its global attributes over the entire measurement period, as well as a dynamic workload characterization to understand the time behavior of the workload over a weekday cycle.

NSF Establishes First Four National Supercomputer Centers

NSF Establishes First Four National Supercomputer Centers