Difference between revisions of "NA-MIC/Projects/NA-MIC Kit/Grid Computing"

From NAMIC Wiki
Jump to: navigation, search
Line 9: Line 9:
  
 
* Installed and updated grid infrastructure components: namic-srb submit machine, implemented configuration for Condor/Globus/GSI to allow NA-MIC users access to 64 node cluster.
 
* Installed and updated grid infrastructure components: namic-srb submit machine, implemented configuration for Condor/Globus/GSI to allow NA-MIC users access to 64 node cluster.
* Defined  [[Data Execution Model for Slicer3|Slicer3:Execution_Model]] - The purpose of this is to facilitate a "run-everywhere" philosophy for algorithm writers. If NAMIC adopts a standard for algorithm "self-description" that is followed when command line executables are written, Slicer, the grid, clusters, etc... should be able to use the executables directly in their environment.
+
* Defined  [[Slicer3:Execution_Model|Data Execution Model for Slicer3]] - The purpose of this is to facilitate a "run-everywhere" philosophy for algorithm writers. If NAMIC adopts a standard for algorithm "self-description" that is followed when command line executables are written, Slicer, the grid, clusters, etc... should be able to use the executables directly in their environment.
 
* Defined API for the Grid Interface - based on the execution model, this API enables the running of algorithms in a distributed grid environment
 
* Defined API for the Grid Interface - based on the execution model, this API enables the running of algorithms in a distributed grid environment
  

Revision as of 19:15, 26 April 2007

Home < NA-MIC < Projects < NA-MIC Kit < Grid Computing
Back to NA-MIC_Collaborations

Objective:

  • Enable Slicer3 to execute work in a distributed grid environment
  • Enable NA-MIC algorithms to be tested in a distributed grid environment

Progress:

  • Installed and updated grid infrastructure components: namic-srb submit machine, implemented configuration for Condor/Globus/GSI to allow NA-MIC users access to 64 node cluster.
  • Defined Data Execution Model for Slicer3 - The purpose of this is to facilitate a "run-everywhere" philosophy for algorithm writers. If NAMIC adopts a standard for algorithm "self-description" that is followed when command line executables are written, Slicer, the grid, clusters, etc... should be able to use the executables directly in their environment.
  • Defined API for the Grid Interface - based on the execution model, this API enables the running of algorithms in a distributed grid environment

Key Investigators:

  • UCSD BIRN-CC: Jeffrey Grethe, Neil Jones
  • GE: Dan Belzek, Jim Miller
  • Isomics: Steve Pieper

Links: