SLinCA@Home 项目介绍

碧城仙

来源：http://en.wikipedia.org/wiki/SLinCA@Home
任务：SLinCA@Home 项目官方 Wiki，待翻译后补充至本站 Wiki 页面 http://www.equn.com/wiki/SLinCA%40Home 内。

有愿意帮助翻译的，请直接回帖（可以先占座，说明翻译那一部分，再翻译或编辑）

WiZarD811

申请翻译Current status标签

Current status
目前状态

Now SLinCA@Home works under alpha-test status, which is related to gradual upgrades of server and client parts.
目前SLinCA@Home运行在alpha测试阶段，服务器端和客户端在测试中逐渐升级。

By informal statistics at BOINCstats site (as of 16 March, 2011) over 2,000 volunteers in 39 countries have participated in the project, making it the second most popular BOINC project in Ukraine (after Magnetism@Home project, which is not active now).[1] About 700 active users contribute about 0.5-1.5 teraFLOPS[2] of computational power, which would rank SLinCA@Home among the top 20 on the TOP500 list of supercomputers ... as of June, 2005.[3] :)
根据Boincstats的非官方统计（截止至2011年3月16日），来自39个国家的超过两千名志愿者已经参与到SLinCA@Home中，使其成为乌克兰第二受欢迎的BOINC项目（仅次于目前已不开放的Magnetism@Home）。大约700名活跃志愿者贡献出了0.5-1.5 teraFLOPS计算力，把SLinCA@Home推上了世界超算五百强前二十名的宝座（不过此处引用的数据竟然是05年6月的水平）。

Currently, one application (SLinCA) is running at global public IMP Desktop Grid (DG) infrastructure (SLinCA@Home), and three others (MultiScaleIVideoP, CPDynSG, LAMMPS over DCI) are under tests now at local private IMP Desktop Grid (DG) infrastructure.
目前，只有SLinCA运行在全球的，公开的EDGeS平台上，MultiScaleIVideoP, CPDynSG, LAMMPS over DCI等三个程序运行在IMP（乌克兰金属物理研究所）的本地网络上。

碧城仙

Introduction 介绍

SLinCA@Home is based at G.V.Kurdyumov Institute for Metal Physics (IMP) of the National Academy of Sciences of Ukraine (NASU), Kyiv, Ukraine. It runs on the Berkeley Open Infrastructure for Network Computing (BOINC) software platform, SZTAKI Desktop Grid platform, and Distributed Computing API (DC-API) by SZTAKI. SLinCA@Home hosts several scientific applications dedicated to search of scale-invariant dependencies in experimental data and results of computer simulations.

SLinCA@Home是乌克兰国家科学院（National Academy of Sciences of Ukraine - NASU）乌克兰金属物理研究所（G.V. Kurdyumov Institute for Metal Physics）主持的。它能在BOINC平台、SZTAKI Desktop Grid平台，SZTAKI开发的分布式计算API（DC-API）上运行。SLinCA@Home具有多种科学应用，它们致力于寻找实验数据与计算机模拟结果之间的依赖关系。

碧城仙

History 历史

SLinCA@Home project was previously launched in January, 2009 as part of EDGeS project in Seventh Framework Programme of the European Union for the funding of research and technological development in Europe. During 2009-2010 it used the power of local IMP Desktop Grid (DG), but from December 2010 it uses the power of volunteer-driven distributed computing in solving the computationally intensive problems related with a search of scale-invariant dependencies in experimentally obtained and simulated scientific data. Now it is operated by group of scientists from IMP NASU in the tight cooperation with partners from IDGF and Distributed Computing team 'Ukraine'. From June 2010 SLinCA@Home works under framework of DEGISCO FP7 EU project.

SLinCA@Home项目是2009年1月推出的，是欧盟第七框架计划（Seventh Framework Programme of the European Union）中EDGeS项目资助的研究和技术开发的一部分。在2009年到2010年中，它使用本地IMP Desktop Grid (DG)的计算能力，而从2010年12月开始，它使用志愿者推动的分布式计算来解决计算密集型问题，发掘从尺度不变的实验获得数据与模拟的科学数据之间的依赖关系。现在，它由一群来自IMP NASU的科学家，以及IDGF和Ukraine分布式计算团队的合同伙伴共同主持。从2010年6月开始，SLinCA@Home在欧盟第七框架计划DEGISCO项目（DEGISCO FP7 EU project）框架下运作。

碧城仙

Scientific Applications 科学应用程序

SLinCA@Home project has been created to perform searches for previously unknown scale-invariant dependencies using data from the public data of experiments and simulations in the following scientific applications.

SLinCA@Home项目被用来挖掘未知的尺度不变所使用的数据——包括公众实验和科学应用程序模拟所得的数据——之间的依赖关系。

碧城仙

Scaling Laws in Cluster Aggregation (SLinCA)

SLinCA (Scaling Laws in Cluster Aggregation) application was the first application ported to DG infrastructure by the Lab of Physics of Deformation Processes of IMP of the NASU. Its aim is to find scale invariant laws in kinetic scenarios of monomer aggregation in clusters of different kinds in different scientific domains.

SLinCA (Scaling Laws in Cluster Aggregation)是第一个通过乌克兰国家科学院金属物理研究所物理变形过程实验室（Lab of Physics of Deformation Processes of IMP of the NASU）移植到DG架构模式的应用程序。SLinCA的目的是挖掘在不同科学领域内尺度不变法则下聚合反应的动力学规律。

碧城仙

The processes of agent aggregation in clusters are investigated in many branches of science: defect aggregation in materials science, population dynamics in biology, city growth and evolution in sociology, etc. There are experimental data confirming their evolving structure, which is hierarchical on many scales. The available theories give many scenarios of cluster aggregation, formation of hierarchical structures, and their scaling properties. But it takes the powerful computational resources for hierarchical processing of the huge databases of experimental data. The typical simulation of one cluster aggregation process with 10^6 monomers takes approximately 1–7 days on a single modern CPU, depending on the number of Monte Carlo steps (MCS). Deploying SLinCA on a Grid computing infrastructure, utilising hundreds of machines at the same time, allows harnessing sufficient computational power to undertake the simulations on a larger scale and in a much shorter timeframe. Running the simulations and analysing the results on the Grid provides the required excessive computational power.

集群中个体聚合的过程，存在于许多科学分支中：材料科学中的缔合缺陷、生物学中的人口动态、社会学中的城市发展和演进等等。有许多实验数据从不同尺度层次上正验证着它们的演化结构。目前适用的理论希望给集群聚合区分了多种场景，形成了不同的层次结构和他们的尺度特性。但是这需要有强大的计算资源来分层处理存储着实验数据的大型数据库。如果在一个单核的现代CPU上，对一个集群聚合的过程开展典型的模拟，依照蒙特卡罗步长（MCS）来计量，这个过程需要1-7天。SLinCA部署在一个网格计算设施上，同时利用成百上千台计算机，形成足够的计算能力，在短时间内即可执行大规模的模拟。网格为后续运行模拟和分析结果提供所需的强大计算能力。

碧城仙

The typical technical parameters for running the DG-enabled version of SLinCA application at global public IMP Desktop Grid (DG) infrastructure (SLinCA@Home):

· The current conditions for 1 workunit per 1 CPU core (2.4 GHz): runtime ~2–4 hours; RAM<60 MB; HDD<40 MB.
· Checkpointing: N/A (under tests now).
· Chronometry of workunit progress: nonlinear.

在全球公众IMP Desktop Grid（DG）结构上运行SLinCA应用程序的DG可用版本的典型技术参数如下：

· 在一个2.4 GHz的单核CPU上运行一个任务单元：运行时间约2-4个小时；内存占用小于60 MB；磁盘占用小于40 MB。
· 检查点：未知（目前仍在测试中）。
· 任务单元的计算过程：非线性。

碧城仙

Scientific Results 科技成果

The previous scientific results of SLinCA application were obtained on EGEE computing resources at CETA-CIEMAT and at XtremWeb-HEP LAL test infrastructures were obtained and reported in 2009 during the poster session at 4th EDGeS training event and 3rd AlmereGrid Workshop, Almere, Netherlands (29–30 March 2009).

以前，SLinCA应用程序借助位于CETA-CIEMAT的EGEE和XtremWeb-HEP LAL测试架构提供的计算资源，取得了一些科技成果，2009年3月29日-30日，在荷兰阿尔梅勒（Almere, Netherlands）第四届EDGeS培训活动（4th EDGeS training event）、第三届AlmereGrid研讨会（3rd AlmereGrid Workshop）会议上发表。

碧城仙

Future Plans 未来计划

The current version of SLinCA-application will be upgraded to stable checkpointing, some new functionality, and support of NVIDIA GPU-computing to perform the analysis faster (by estimations from 50 to 200% faster).

SLinCA应用程序的当前版本，即将升级：稳定检查点、提供一些新的功能，并且支持NVIDIA GPU运算来加快分析速度（预计有50%到200%的速度提升）。

lch=gta

Optical microscopy is usually used for structural characterization of materials in narrow ranges of magnification, small region of interest (ROI), and in static regime. But many crucial processes of damage initiation and propagation take place dynamically in the wide observable time domain from 10−3 s to 103 s and on the many scales from 10−6 m (solitary defects places) to 10−2 m (correlated linked network of defects). Multiscale Image and Video Processing (MultiscaleIVideoP) is designed to process the recorded evolution of material under mechanical deformation in loading machine. The calculations include many parameters of physical process (process rate, magnification, illumination conditions, hardware filters, etc.) and image processing parameters (size distribution, anisotropy, localization, scaling parameters, etc.), hence the calculations are very slow. That is why the extreme need of more powerful computational resources appears. Deploying this application on a Grid computing infrastructure, utilising hundreds of machines at the same time, allows harnessing sufficient computational power to perform image and video processing on a larger scale and in a much shorter timeframe.

The typical technical parameters for running the DG-enabled version of MultiScaleIVideoP application at local private IMP Desktop Grid (DG) infrastructure:

    Current conditions for 1 workunit per 1 CPU core (2.4 GHz): time to run ~20–30 minutes; RAM<200 MB; HDD<500 MB.
    Checkpointing: N/A (under tests now).
    Chronometry of workunit progress: linear.

光学显微术通常被用于放大倍率范围较小，感兴趣区较小并且静态（？）的材料结构检查。但是在可观察的千分之一秒至一千秒时域和一微米（常见于独立的瑕疵）至一厘米（常为多个互相关联的瑕疵）空间尺度上，材料会开始受到破坏而且这种破坏过程会不断地发展。Multiscale Image and Video Processing (MultiscaleIVideoP)旨在处理物体在载物台上发生的机械形变的相关记录。此类计算涉及到机械变化中相当多的参数，包括速率，放大倍率，照明条件，滤镜等；还涉及一系列图像处理参数，如尺寸分布，各向异性，定位，刻度参数等，所以计算将十分缓慢。这就是我们急迫需要大量计算资源的原因。将此应用放到分布式的计算网络中，利用成百上千的计算机，我们就可以驾驭足够强大的计算能力来在大尺度上处理图像和视频，同时将处理时间控制的较短。

在全球公众IMP Desktop Grid（DG）结构上运行SLinCA应用程序的DG可用版本的典型技术参数如下：

· 当前条件下，在一个2.4 GHz的单核CPU上运行一个任务单元：运行时间约20-30分钟；内存占用小于200 MB；磁盘占用小于500 MB。
· 检查点：未知（目前仍在测试中）。
· 任务单元的计算过程：线性。

lch=gta

The previous scientific results of MultiScaleIVideoP application were obtained on EGEE computing resources at CETA-CIEMAT and at XtremWeb-HEP LAL test infrastructures were obtained and reported in 2009 during the poster session at 4th EDGeS training event and 3rd AlmereGrid Workshop, Almere, Netherlands (29–30 March 2009).[5]

In January, 2011 the further scientific results for experiments with cyclic constrained tension of Al foils under video monitoring were obtained and reported.[6]

以前，MultiScaleIVideoP程序在EGEE的计算网络上运行并生成了结果。测试设施已经在CETA-CIEMAT和XtremWeb-HEP LAL（法国的一个线性加速器）建立，而且在2009年的第四届EDGeS训练项目和于荷兰阿尔梅勒举办的第三届AlmereGrid Workshop（2009年3月29-30日）的图片讨论会上参与了报告讨论。
2011年一月，我们生成并发布了关于视频监控下铝箔循环约束张力实验的进一步的科学研究成果。

refla

回复 11# lch=gta

很久不见你了

lch=gta

回复  lch=gta

很久不见你了
refla 发表于 2011-6-19 14:25

    呵呵，其实我一直在潜水，账号也没登，这几天放假了就上来做点事

refla

回复 14# lch=gta

回来就好