Typical Scientific Applications Research Articles

The performance of General Purpose Powder Diffractometer at CSNS

The first time of flight diffractometer at the China Spallation Neutron Source (CSNS), General Purpose Powder Diffractometer (GPPD), has entered the user program in 2018. GPPD is a flexible and versatile instrument to study the crystallographic and magnetic structures of polycrystalline materials. After more than 3 years of debugging and operation, the high performance of the diffractometer has been achieved for a good instrumental resolution 0.15% and a wide d-space detection range 0.05–50.48 Å together with the desirable signal-to-noise ratio characteristics, enabling a large number of user experiments and achievements. The typical scientific applications of GPPD demonstrate its outstanding potential for unraveling the precise structure of crystals.

Testing the robustness of DYNAMITE triaxial Schwarzschild modelling: The effects of correcting the orbit mirroring

In the past 15 yr, the triaxial Schwarzschild orbit-superposition code developed by van den Bosch and van de Ven in Leiden has been widely applied to study the dynamics of galaxies. Recently, a bug was reported in the orbit calculation of this code, specifically in the mirroring procedure that is used to speed up the computation. We have fixed the incorrect mirroring in the DYNAMITE code, which is the publicly-released successor of the Leiden triaxial Schwarzschild code. In this study, we provide a thorough quantification of how this bug has affected the results of dynamical analyses performed with this code. We compare results obtained with the original and corrected versions of DYNAMITE, and discuss the differences in the phase-space distribution of a single orbit and in the global stellar orbit distribution, in the mass estimate of the central black hole in the highly triaxial galaxy PGC 46832, and in the measurement of intrinsic shape and enclosed mass for more than 50 galaxies. Focusing on the typical scientific applications of the Schwarzschild method, in all our tests we find that differences are negligible with respect to the statistical and systematic uncertainties. We conclude that previous results with the Leiden triaxial Schwarzschild code are not significantly affected by the incorrect mirroring.

SplineLib: A modern multi-purpose C++ spline library

This paper provides the description of a novel, multi-purpose spline library. In accordance with the increasingly diverse modes of usage of splines, it is multi-purpose in the sense that it supports geometry representation, finite element analysis, and optimization. The library features reading and writing for various file formats and a wide range of spline manipulation algorithms. Further, a new efficient and objective-oriented algorithm for B-spline basis function evaluation is included. All features are available by a spline-type independent interface. The library is written in modern C++ with CMake as build system. This enables it for usage in typical scientific applications. It is provided as open-source library.

An efficient dataflow accelerator for scientific applications

Dataflow architecture has been proved to be promising in high-performance computing. Traditional dataflow architectures are not efficient enough in typical scientific applications such as stencil and FFT due to low utilization of function units. Based on the blocking and parallelism features of scientific applications, we design SPU, an efficient dataflow architecture for scientific applications. In SPU, dataflow graphs translated from the loop body in scientific applications are mapped to the Processing Element(PE) Array. Iterations enter the dataflow graph in pipeline during execution meanwhile three levels of parallelism are exploited to improve the utilization of function units in dataflow architectures: inner-graph parallelism, pipelining parallelism and inter graph parallelism. The experimental results show that the average energy efficiency of SPU achieves 25.97GFlops/W in 40 nm technology and the utilization of floating point function units in SPU is 2.82x that of typical dataflow architecture on average for typical scientific applications.

Composing resilience techniques: ABFT, periodic and incremental checkpointing

Algorithm Based Fault Tolerant (ABFT) approaches promise unparalleled scalability and performance in failure-prone environments. Thanks to recent advances in the understanding of the involved mechanisms, a growing number of important algorithms (including all widely used factorizations) have been proven ABFT-capable. In the context of larger applications, these algorithms provide a temporal section of the execution, where the data is protected by its own intrinsic properties, and can therefore be algorithmically recomputed without the need of checkpoints. However, while typical scientific applications spend a significant fraction of their execution time in library calls that can be ABFT-protected, they interleave sections that are difficult or even impossible to protect with ABFT. As a consequence, the only practical fault-tolerance approach for these applications is checkpoint/restart. In this paper we propose a model to investigate the efficiency of a composite protocol, that alternates between ABFT and checkpoint/restart for the effective protection of an iterative application composed of ABFT- aware and ABFT-unaware sections. We also consider an incremental checkpointing composite approach in which the algorithmic knowledge is leveraged by a novel optimal dynamic program- ming to compute checkpoint dates. We validate these models using a simulator. The model and simulator show that the composite approach drastically increases the performance delivered by an execution platform, especially at scale, by providing the means to increase the interval between checkpoints while simultaneously decreasing the volume of each checkpoint.

Achieving high job execution reliability using underutilized resources in a computational economy

In distributed shared resource environments, such as grids or recent clouds, one of the major challenges is how to meet users’ QoS requirements and rationally distribute resources at the same time. Computational economy has long been studied as an effective solution to address such resource-allocation problems. However, price alone has limitations in controlling supply-and-demand in computational markets. In particular, even though less reliable desktop PCs are the dominant resource in computation grids, they are often underutilized, regardless of their price, because they do not exhibit qualities required by typical scientific and business applications. To address this problem, we propose Highly Available Job Execution Service (HA-JES) that fosters the balanced resource consumption by dynamically virtualizing resources to meet QoS requirements from users. In particular, in HA-JES, jobs are replicated in a market-driven efficient way; underutilized and therefore cheap resources are exploited to build a virtualized high quality resource and hence facilitate balanced resource usage. Our evaluation results show that HA-JES benefits all actors in the market in terms of resource utilization, market capacity, and market stability.

A JAVA application framework for scientific software development

SUMMARYThis paper presents AIBench (SING group, Ourense, Spain), a JAVA desktop application framework mainly focused on scientific software development, with the goal of improving the productivity of research groups. Following the MVC design pattern, the programmer is able to develop applications using only three types of concepts: operations, data‐typesand views. The framework provides the rest of the functionality present in typical scientific applications, including user parameter requests, logging facilities, multithreading execution, experiment repeatability and graphic user interface generation, among others. The proposed framework is implemented following a plugin‐based architecture, which also allows assembling new applications by the reuse of modules from past development projects. Copyright © 2011 John Wiley & Sons, Ltd.

Composable cost estimation and monitoring for computational applications in cloud computing environments

With the offer from cloud computing providers, scientists have the opportunity to utilize pay-as-you-go resources together with their own and shared resources. However, scientists need to decide which parts of their applications should be executed in cloud computing systems in order to balance the trade-off between cost, time and resource requirements. In this paper, we present a service for estimating, monitoring and analyzing costs associated with scientific applications in the cloud. Cost models associated with different application execution models are proposed and these cost models can be composed to determine costs of different scenarios. We present techniques to estimate costs for service dependency and to monitor costs associated with typical scientific applications. Experiments with real-world applications are performed to illustrate the usefulness of our techniques. Our service could eventually be integrated into cloud resource management and execution services to support on-the-fly resource scheduling.

AIBench: A rapid application development framework for translational research in biomedicine

Applied research in both biomedical discovery and translational medicine today often requires the rapid development of fully featured applications containing both advanced and specific functionalities, for real use in practice. In this context, new tools are demanded that allow for efficient generation, deployment and reutilization of such biomedical applications as well as their associated functionalities. In this context this paper presents AIBench, an open-source Java desktop application framework for scientific software development with the goal of providing support to both fundamental and applied research in the domain of translational biomedicine. AIBench incorporates a powerful plug-in engine, a flexible scripting platform and takes advantage of Java annotations, reflection and various design principles in order to make it easy to use, lightweight and non-intrusive. By following a basic input–processing–output life cycle, it is possible to fully develop multiplatform applications using only three types of concepts: operations, data-types and views. The framework automatically provides functionalities that are present in a typical scientific application including user parameter definition, logging facilities, multi-threading execution, experiment repeatability and user interface workflow management, among others. The proposed framework architecture defines a reusable component model which also allows assembling new applications by the reuse of libraries from past projects or third-party software.

Fei Teng 64 Stream Processing System: Architecture, Compiler, and Programming

The stream architecture is a novel microprocessor architecture with wide application potential. It is critical to study how to use the stream architecture to accelerate scientific computing programs. However, existing stream processors and stream programming languages are not designed for scientific computing. To address this issue, we design and implement a 64-bit stream processor, Fei Teng 64 (FT64), which has a peak performance of 16 Gflops. FT64 supports two kinds of communications, message passing and stream communications, based on which, an interconnection architecture is designed for a FT64-based high-performance computer. This high-performance computer contains multiple modules, with each module containing eight FT64s. We also design a novel stream programming language, stream Fortran 95 (SF95), together with the compiler SF95 compiler, so as to facilitate the development of scientific applications. We test nine typical scientific application kernels on our FT64 platform to evaluate this design. The results demonstrate the effectiveness and efficiency of FT64 and its compiler for scientific computing.

Matrix-based streamization approach for improving locality and parallelism on FT64 stream processor

FT64 is the first 64-bit stream processor designed for scientific computing. It is critical to exploit optimizing streamization approaches for scientific applications on FT64 due to the inefficiency of direct streamization approach. In this paper, we propose a novel matrix-based streamization approach for improving locality and parallelism of scientific applications on FT64. First, a Data&Computation Matrix is built to abstract the relationship between loops and arrays of the original programs, and it is helpful for formulating the streamization problem. Second, three key techniques for optimizing streamization approach are proposed based on the transformations of the matrix, i.e., coarse-grained program transformations, fine-grained program transformations, and stream organization optimizations. Finally, we apply our approach to ten typical scientific application kernels on FT64. The experimental results show that the matrix-based streamization approach achieves an average speedup of 2.76 over the direct streamization approach, and performs equally to or better than the corresponding Fortran programs on Itanium 2 except CG. It is certain that the matrix-based streamization approach is a promising and practical solution to efficiently exploit the tremendous potential of FT64.

A 64-bit stream processor architecture for scientific applications

Stream architecture is a novel microprocessor architecture with wide application potential. But as for whether it can be used efficiently in scientific computing, many issues await further study. This paper first gives the design and implementation of a 64-bit stream processor, FT64 (Fei Teng 64), for scientific computing. The carrying out of 64-bit extension design and scientific computing oriented optimization are described in such aspects as instruction set architecture, stream controller, micro controller, ALU cluster, memory hierarchy and interconnection interface here. Second, two kinds of communications as message passing and stream communications are put forward. An interconnection based on the communications is designed for FT64-based high performance computers. Third, a novel stream programming language, SF95 (Stream FORTRAN95), and its compiler, SF95Compiler (Stream FORTRAN95 Compiler), are developed to facilitate the development of scientific applications. Finally, nine typical scientific application kernels are tested and the results show the efficiency of stream architecture for scientific computing.

Evaluating IA-32 web servers through simics: a practical experience

Nowadays, the use of multiprocessor systems is not just limited to typical scientific applications, but these systems are increasingly being used for executing commercial applications, such as databases and web servers. Therefore, it becomes essential to study the behavior of multiprocessor architectures under commercial workloads. To accomplish this, we need simulators able to model not only the CPU, memory and interconnection network but also other aspects that are critical in the execution of commercial workloads, such as I/O subsystem and operating system. In this paper, we present our first experiences using Simics, a simulator which allows full-system simulation of multiprocessor architectures covering all the topics previously mentioned. Using Simics we carry out a detailed performance study of a static web content server, showing how changes in some architectural parameters, such as number of processors and cache size, affect final performance. The results we have obtained corroborate the intuition of increasing performance of a dual-processor web server opposite to a single-processor one, and at the same time, allow us to check out Simics limitations. Finally, we compare these results with those that are obtained on real machines.

Porting of Scientific Applications to Grid Computing on GridWay

The expansion and adoption of Grid technologies is prevented by the lack of a standard programming paradigm to port existing applications among different environments. The Distributed Resource Management Application API has been proposed to aid the rapid development and distribution of these applications across different Distributed Resource Management Systems. In this paper we describe an implementation of the DRMAA standard on a Globus-based testbed, and show its suitability to express typical scientific applications, like High-Throughput and Master-Worker applications. The DRMAA routines are supported by the functionality offered by the GridWay2framework, which provides the runtime mechanisms needed for transparently executing jobs on a dynamic Grid environment based on Globus. As cases of study, we consider the implementation with DRMAA of a bioinformatics application, a genetic algorithm and the NAS Grid Benchmarks.

特異点グラフを用いた数値シミュレーション結果の分類

We present a visualization technique which a large scale detects the structure at all scales removing from the user the responsibility of extracting information implicit in the data, and presenting the structure explicitly for analysis and retrieval. In typical scientific applications, data is represented at the nodes of a mesh of elements and interpolated linearly across the interior of the elements. A critical point exists in the gradient field of the Scalar filed. It is possible at few cost to express the Scalar field using the graph which connected the critical point.In past, we proposed a technique for calculating isosurfaces efficiently using an extrema skeleton, which consists of elements and connects all extrema points [1].In this algorithm, extrema points in a scalar field are first extracted. A graph is then generated in which the extrema points are taken as nodes. And our work can be regarded as an extension of our original technique, because our new skeleton connects saddle points in addition to extrema points.To confirm the effectiveness of our technique, we extract features skeletons of CFD results for forecasting weather and determine linear correlation between multiple scalar variables such as wind velocity, temperature, and humidity.

Division and square root: choosing the right implementation

Floating-point support has become a mandatory feature of new microprocessors due to the prevalence of business, technical, and recreational applications that use these operations. Spreadsheets, CAD tools, and games, for instance, typically feature floating-point-intensive code. Over the past few years, the leading architectures have incorporated several generations of floating-point units (FPUs). However, while addition and multiplication implementations have become increasingly efficient, support for division and square root has remained uneven. The design community has reached no consensus on the type of algorithm to use for these two functions, and quality and performance of the implementations vary widely. This situation originates in skepticism about the importance of division and square root and an insufficient understanding of the design alternatives. Quantifying what constitutes good performance is challenging. One rule thumb, for example, states that the latency of division should be three times that of multiplication; this figure is based on division frequencies in a selection of typical scientific applications. Even if we accept this doctrine at face value, implementing division-and square root-involves much more than relative latencies. We must also consider area, throughput, complexity, and the interaction with other operations. This article explores the various trade-offs involved and illuminates the consequences of different design choices, thus enabling designers to make informed decisions.

Graphical object-oriented programming with LabVIEW

Programming with graphical languages implements a completely new type of man-machine interface. Conventional text-based programming is an inherently linear process that forces engineers and scientists to think and express their ideas in terms constrained by the programming language. The ability to visualise graphically a process or algorithm allows them, however, to express their ideas in a more intuitive, natural way. This is true, particularly for parallel processes. LabVIEW is such an icon-based graphical programming system that provides a powerful alternative for scientific and engineering programming - it offers the significant productivity gains of a graphical environment with no sacrifice in performance or flexibility. Typical scientific applications include process control, automation, instrumentation, motion control, simulation, and a number of other technical disciplines.

Mesh-connected parallel computer PAX for scientific applications

Nearest-neighbor-mesh connection plus global broadcasting/control bus characterizes the architecture of the processor array PAX, that was constructed for and is now operating in many typical scientific applications. Not only these inter-processor connections, but also an MIMD structure of the machine were found effective in the particle transport problems, that require asynchronous operation. The paper describes the bases of architecture of two recent versions of the PAX computer, their hardware and software systems, and, based on the implementation of scientific applications, the effectiveness of the PAX type architecture is presented.

Active permanent magnet suspensions for scientific instruments

The active permanent magnet suspension (APMS) is presented and reviewed as a suitable means for laboratory and industrial realisation of non-contacting devices. Static and dynamic properties of axial and radial APMS rotary systems are discussed. A gas friction detector and a molecular beam chopper are described as typical scientific instrument applications.