1 / 19

Visual Solution to High Performance Computing

Visual Solution to High Performance Computing. Computer and Automation Research Institute Laboratory of Parallel and Distributed Systems http :// www.lpds.sztaki.hu/pgrade. The Big Issue. Parallelization ?. Sequential program code C, C++ Fortran. Parallel program code ?. Debugging ?.

jadzia
Download Presentation

Visual Solution to High Performance Computing

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Visual Solutionto High Performance Computing Computer and Automation Research Institute Laboratory of Parallel and Distributed Systemshttp://www.lpds.sztaki.hu/pgrade

  2. The Big Issue Parallelization? Sequentialprogram code C, C++ Fortran Parallelprogram code ? Debugging? Performance? Execution?

  3. Distributed supercomputing with P-GRADE • Parallel Grid Run-time and Application DevelopmentEnvironment (P-Grade) • The first highly integrated parallel application development system for Grid and clusters • Provides: • Parallel, supercomputing programming • Fast and efficient development • Observation and visualization • Fault and performance analysis • ON CLUSTERS • ON SUPERCOMPUTERS • IN THE GRID

  4. DESIGN: Three hierarchical layers for easy parallelisation Application window Process window Text window

  5. DESIGN: Built-in Communication Templates for fast design

  6. DEBUGGING: Hierarchical control and views to eliminite programming errors

  7. Support for systematic debugging to handle non-deterministic behaviour of parallel applications Automatic dead-lock detection Replay technique with collective breakpoints Active control: generation of Execution Trees Testing parallel programs by temporal logic assertions DEBUGGING: Macrostep-by-macrostep…

  8. MONITORING: statistics and event traces for performance evaluation • Collection of both statistics and event traces • Application monitoring and visualization in the Grid • Evaluation of long-runningprograms based on semi-on-line trace collection • Support for debugger in P-GRADE by execution visualisation

  9. PERFORMANCE VISUALIZATION: Visualization of Event Traces User controlled focus onprocessors,processes and messages

  10. P-GRADE: Stages of Software Development and Execution Design, debugging Performance- analyzis Execution Grid & Cluster & Supercomputer

  11. 25 x 10 x 25 x 5 x Application I: Ultra-short range weather forecast (Hungarian Meteorology Service) Forecasting dangerous weather situations (storms, fog, etc.),crucial task in the protection of life and property Processed information: surface level measurements, high-altitude measurements, radar, satellite, lightning, results of previous computed models Result • Requirements: • Execution time < 10 min • Higher resolution

  12. Satellite raw image Receiving image & Processing of satellite images Interpolation to basic GRID Transformation Processing: Altitude of clouds

  13. Job submission TRACE & Results Input P-GRADE in meteorology demonstrated at Euro-Par 2003 conference HungarianMeteorologicalService P-GRADE GUI DB P-GRADE - RS CONDOR-PVM Parallel execution and Monitoring

  14. Monitoring of Workflow Input files Secure data transfer Job Monitoring of Job Workflow support (in the Grid)Illustrated using the meteorological application

  15. APPLICATION II: Urban traffic simulation(University of Westminster)

  16. P-GRADE GUI P-GRADE program Submitted to Budapest as a Condor job 1 P-GRADE Program Runs at UoW cluster P-GRADE program Runs at SZTAKI cluster 4 2 3 P-GRADE program migrates to London as a Condor job SZTAKI & BUTE Clusters overloaded CHECKPOINTING Checkpointing and migration of P-GRADEprograms between clusters London-UoW Budapest, MTA SZTAKI SZTAKI & BUTE

  17. Monitoring & visualisation - job migration in the Grid - Slow-down of simulator job due tooverloaded cluster Migrationof job betweenclusters in theGRID

  18. Summary: Advantages of P-GRADE • Effective and efficient support for each stage of the parallel program development • Fast parallelization of existing algorithms • Reusability of sequential code • Hiding of low level communication functions • Integratedgraphical concept • Predefined communication templates • Support for hierarchical design • Even non-professional programmers can use it(without a steep learning curve) • Portability (supercomputers, PC clusters, Grid)

  19. Parallel Grid Run-time and Application DevelopmentEnvironment

More Related