Athena is the common framework used by the ATLAS experiment for simulation,reconstruction,and analysis,By design,Athena supports multiple persistence services,and insulates users from technology-specific persistence d...Athena is the common framework used by the ATLAS experiment for simulation,reconstruction,and analysis,By design,Athena supports multiple persistence services,and insulates users from technology-specific persistence details.Athena users and even most Athena package developers should neither know nor care whether data come from the grid or from local filesystems.nor whether data reside in object databases,in ROOT or ZEBRA files,or in ASCII files.In this paper we describe how Athena applications may transparently take advantage of emerging services provided by grid software today-how data generated by Athea jobs are registered in grid replica catalogs and other collection management services,and the means by which input data are identified and located in a grid-aware collection management environment.We outline an evolutionary path toward incorporation of grid-based virtual data services,whereby locating data may be replaced by locating a recipe according to which that dta may be generated.Several implementation scenarios,ranging from lowlevel grid catalog services(e.g.,from Globus)through higher-level services such as the Grid Data Management Pilot (under development as part of the European DataGrid porject,in collaboration,with the Particle Physics Data Grid)to more conventional database services,and a common architecture to support these various scenarios,are also described.展开更多
In high-energy physics,terabyte and soon petabyte-scale data collections are emerging as critical community resources.A new class of "Data Grid" infrastructure is required to support distributed access to an...In high-energy physics,terabyte and soon petabyte-scale data collections are emerging as critical community resources.A new class of "Data Grid" infrastructure is required to support distributed access to and analysis of these datasets by potentially thousands of users.Data Grid technology is being deployed in numerous experiments through collaborationssuch as the EU DataGrid,the Grid Physics Network,and the Particel Physics Data Grid[1],The Globus Toolkit is a widely used set of services designed to support the creation of these Grid infrastrunctures and applications,In this paper we survey the Globus technologies that will play a major role in the development and deployment for these Grids.展开更多
The 18 months since CHEP'2000 have seen significant advances in Grid computing,both within and outside high energy physics,While in early 2000,Grid Computing was a novel concept that most CHEP attendees were being...The 18 months since CHEP'2000 have seen significant advances in Grid computing,both within and outside high energy physics,While in early 2000,Grid Computing was a novel concept that most CHEP attendees were being exposed to for the first time,we now see considerable consensus on Grid architecture,a solid and widely adopeted technology base,major funding initiatives,a wide variety of projects developing applications and technologies,and major deployment projects aimed at creating robust Grid infrastructures,I provide a summary of major developments and trends,focusing on the Globus open source Grid software project and the GriPhyN data grid project.展开更多
We have prototyped and analyzed design of a novel approach for the high throughput computing-a core element for the emerging HENP computational grid.Independent event processing in HENP is well suted for computing in ...We have prototyped and analyzed design of a novel approach for the high throughput computing-a core element for the emerging HENP computational grid.Independent event processing in HENP is well suted for computing in parallel.The prototype facilitateds use of inexpensive mass-market components by poviding fault tolerant resilienece (instead of the expensive total system reliablity) via highly scalable management components. The ability to handle both hardware and software failures on a large dedicated HENP facility limits the need for user intervention.A robust data management is especially important in HENP computing since large data-flows occur before and /or atfer each processing task.The architecture of our active object object coordination schema implements a multi-level hierarchical agent model,It provides fault tolerance by splitting a large overall task into independent atomic processes,performed by lower level agents synchronizing each other via a local database.Necessary control function performed by higher level agents interact with the same database thus managing distributed data production.The system has been tested in production environment for simulations in the STAR experiment at RHIC.Our architectural prototype controlled processes on more than a hundred processors at a time and has run for extended periods of time.Twenty terabytes of simulated data hava been produced.The generic nature of our two level architectural solution fault tolerance in distributed environment has been demonstrated by ist successful test for the grid file replication services between BNL and LBNL.展开更多
The occurrence of heterogeneous flow structures in gas-particle flows seriously affects the gas-solid contacting and transport processes in high-velocity gas-fluidized beds. Particles do not disperse uniformly in the ...The occurrence of heterogeneous flow structures in gas-particle flows seriously affects the gas-solid contacting and transport processes in high-velocity gas-fluidized beds. Particles do not disperse uniformly in the flow but pass through the bed in a swarm of clusters. The so-called 揷ore-annulus?structure in the radial direction and 揝?shaped axial distribution of solids concentration characterize the typical flow structure in the system. A computational study, using the discrete particle approach based on molecular dynamics techniques, has been carried out to explore the mechanisms underlying formation of the clusters and the core-annulus structure. Based on energy budget analysis including work done by the drag force, kinetic energy, rotational energy, potential energy, and energy dissipation due to particle-particle and particle-wall collisions, the role of gas-solid interaction and inelastic collisions between the particles are elucidated. It is concluded that the competition between gas-solid interaction and particle-particle interaction determines the pattern formation in high-velocity gas-solid flows: if the gas-solid interaction (under elevated pressure) dominates, most of particle energy obtained by drag from the gas phase is partitioned such that particle potential energy is raised, leading to a uniform flow structure. Otherwise, a heterogeneous pattern exists, which could be induced by both particle-particle collisions and gas-solid interaction. Although both factors could cause the flow instability, the non-linear drag force is demonstrated to be the necessary condition to trigger heterogeneous flow structure formation. As gas velocity increases and goes beyond a critical value, the fluid-particle interaction suppresses particle collisional dissipation, and as a consequence a more homogeneous flow regime is formed.展开更多
文摘Athena is the common framework used by the ATLAS experiment for simulation,reconstruction,and analysis,By design,Athena supports multiple persistence services,and insulates users from technology-specific persistence details.Athena users and even most Athena package developers should neither know nor care whether data come from the grid or from local filesystems.nor whether data reside in object databases,in ROOT or ZEBRA files,or in ASCII files.In this paper we describe how Athena applications may transparently take advantage of emerging services provided by grid software today-how data generated by Athea jobs are registered in grid replica catalogs and other collection management services,and the means by which input data are identified and located in a grid-aware collection management environment.We outline an evolutionary path toward incorporation of grid-based virtual data services,whereby locating data may be replaced by locating a recipe according to which that dta may be generated.Several implementation scenarios,ranging from lowlevel grid catalog services(e.g.,from Globus)through higher-level services such as the Grid Data Management Pilot (under development as part of the European DataGrid porject,in collaboration,with the Particle Physics Data Grid)to more conventional database services,and a common architecture to support these various scenarios,are also described.
文摘In high-energy physics,terabyte and soon petabyte-scale data collections are emerging as critical community resources.A new class of "Data Grid" infrastructure is required to support distributed access to and analysis of these datasets by potentially thousands of users.Data Grid technology is being deployed in numerous experiments through collaborationssuch as the EU DataGrid,the Grid Physics Network,and the Particel Physics Data Grid[1],The Globus Toolkit is a widely used set of services designed to support the creation of these Grid infrastrunctures and applications,In this paper we survey the Globus technologies that will play a major role in the development and deployment for these Grids.
文摘The 18 months since CHEP'2000 have seen significant advances in Grid computing,both within and outside high energy physics,While in early 2000,Grid Computing was a novel concept that most CHEP attendees were being exposed to for the first time,we now see considerable consensus on Grid architecture,a solid and widely adopeted technology base,major funding initiatives,a wide variety of projects developing applications and technologies,and major deployment projects aimed at creating robust Grid infrastructures,I provide a summary of major developments and trends,focusing on the Globus open source Grid software project and the GriPhyN data grid project.
文摘We have prototyped and analyzed design of a novel approach for the high throughput computing-a core element for the emerging HENP computational grid.Independent event processing in HENP is well suted for computing in parallel.The prototype facilitateds use of inexpensive mass-market components by poviding fault tolerant resilienece (instead of the expensive total system reliablity) via highly scalable management components. The ability to handle both hardware and software failures on a large dedicated HENP facility limits the need for user intervention.A robust data management is especially important in HENP computing since large data-flows occur before and /or atfer each processing task.The architecture of our active object object coordination schema implements a multi-level hierarchical agent model,It provides fault tolerance by splitting a large overall task into independent atomic processes,performed by lower level agents synchronizing each other via a local database.Necessary control function performed by higher level agents interact with the same database thus managing distributed data production.The system has been tested in production environment for simulations in the STAR experiment at RHIC.Our architectural prototype controlled processes on more than a hundred processors at a time and has run for extended periods of time.Twenty terabytes of simulated data hava been produced.The generic nature of our two level architectural solution fault tolerance in distributed environment has been demonstrated by ist successful test for the grid file replication services between BNL and LBNL.
文摘The occurrence of heterogeneous flow structures in gas-particle flows seriously affects the gas-solid contacting and transport processes in high-velocity gas-fluidized beds. Particles do not disperse uniformly in the flow but pass through the bed in a swarm of clusters. The so-called 揷ore-annulus?structure in the radial direction and 揝?shaped axial distribution of solids concentration characterize the typical flow structure in the system. A computational study, using the discrete particle approach based on molecular dynamics techniques, has been carried out to explore the mechanisms underlying formation of the clusters and the core-annulus structure. Based on energy budget analysis including work done by the drag force, kinetic energy, rotational energy, potential energy, and energy dissipation due to particle-particle and particle-wall collisions, the role of gas-solid interaction and inelastic collisions between the particles are elucidated. It is concluded that the competition between gas-solid interaction and particle-particle interaction determines the pattern formation in high-velocity gas-solid flows: if the gas-solid interaction (under elevated pressure) dominates, most of particle energy obtained by drag from the gas phase is partitioned such that particle potential energy is raised, leading to a uniform flow structure. Otherwise, a heterogeneous pattern exists, which could be induced by both particle-particle collisions and gas-solid interaction. Although both factors could cause the flow instability, the non-linear drag force is demonstrated to be the necessary condition to trigger heterogeneous flow structure formation. As gas velocity increases and goes beyond a critical value, the fluid-particle interaction suppresses particle collisional dissipation, and as a consequence a more homogeneous flow regime is formed.