1. Small-Scale Raster Map Projection Transformation Using a Virtual System to Interactively Share Computing Resources and Data U.S. Department of the Interior U.S. Geological Survey Michael P. Finn Briefing to CyberGIS Technical Points of Contact Best Practices Series 19 July 2012

2. Collaborators/ Co-Authors Yan Liu – University of Illinois at Urbana-Champaign (UIUC), CyberInfrastructure and Geospatial Information (CIGI) Laboratory David M. Mattli – USGS, Center of Excellence for Geospatial Information Science (CEGIS) Babak Behzad – UIUC, Department of Computer Science Kristina H. Yamamoto – USGS, CEGIS Anand Padmanabhan – UIUC, CIGI Laboratory Qingfeng (Gene) Guan – University of Nebraska -- Lincoln, School of Natural Resources Eric Shook – UIUC, CIGI Laboratory

3. Outline Overview/ Objectives Motivation for HPC-Research pRasterBlaster – a primer and the early days Current Implementation/ Program Components Performance Status

4. Overview HPC  Return to the Mainframe? Parallel computing for raster (map projection, other) – Raster was born to be parallelized CEGIS parallel computing as part of National Science Foundation CyberGIS Grant

5. Objectives Develop a rapid raster projection transformation and Web service using HPC technology -- pRasterBlaster Provide a software package that better handles known problems for wide use in the modeling community

6. Motivation for HPC-Research Raster processing too slow for large datasets mapIMG Example: Re-projecting a 1GB raster dataset can take 45-60 minutes Solution: Solve problems using multiple processors Create user-centric Web 2.0 interface that hides non- important, complex HPC implementation details

7. pRasterBlaster Primer mapIMG in HPC Environment Map Projection/ Reprojection for Raster Datasets Rigorous Geometry Handling and Novel Resampling – Resampling Options for categorical data and population counts (also standard continuous data resampling methods)

8. pRasterBlaster (the Early Days) Very Similar to mapIMG (V. 03) Row-Wise Decomposition I/O Occurred Directly in Program Inner Loop Disadvantages – Resampling Requires a lot of I/O – Changing I/O Implementation Difficult – Difficulty with Multiple Processors Writing to a Shared file

9. Parallel Program Use Multiple Processors to Decrease Run Time Evaluation – Wall Time Vs. Speedup Amdahl’s Law: Calculate Maximum Speedup – Communications Overhead Communications Between Processors is SLOW – See Last Week’s Briefing by Babak Behzad

10. Current Implementation (1.0) I/O and Reprojection Separated into Stages I/O Can Be Batched and Reordered Partitioning More Flexible – Partition can be less than a row

11. Version 1.0 Components Prologue – Open input files, calculate size of output, calculate partitions, create output and temp files Reprojection – for each partition in parallel – Read input to memory, iterate through output pixels and reproject, write partition to temp files Epilogue – Write final output

12. Performance Observations Evaluations ongoing – Working closely with CIGI The Overhead of Copying the Output File is Very High Likely to Adopt CIGI Suggestion/ Work – Related to creating a new, high performance I/O based on netCDF-4/ HDF-5 parallel functions Need More Testing In Other Environments

13. Current Status pRasterBlaster development continuing pRasterBlaster Version 1.0 released 01 April pRasterBlaster Version 1.5 soon (fix identified bottlenecks) Iterative testing dRasterBlaster – d forDesktop; essentially mapIMG 4.0 Library of core functions shared by both dRasterBlaster & pRasterBlaster (libRasterBlaster)

14. References Atkins, D. E., K. K. Droegemeier, et al. (2003). Revolutionizing Science and Engineering Through Cyberinfrastructure: Report of the National Science Foundation Blue-Ribbon Advisory Panel on Cyberinfrastructure. Arlington, VA, National Science Foundation. Behzad, Babak, Yan Liu, Eric Shook, Michael P. Finn, David M. Mattli, and Shaowen Wang (2012). A Performance Profiling Strategy for High-Performance Map Re-Projection of Coarse- Scale Spatial Raster Data. Abstract accepted for presentation at the Auto-Carto 2012, A Cartography and Geographic Information Society Research Symposium, Columbus, OH. Wang, Shaowen and Yan Liu (2009) TeraGrid GIScience Gateway: Bridging cyberinfrastructure and GIScience. International Journal of Geographical Information Science, Volume 23, Number 5, May, pages 631-656. Wang, Shaowen, Yan Liu, Nancy Wilkins-Diehr, and Stuart Martin (2009) SimpleGrid toolkit: Enabling geosciences gateways to cyberinfrastructure. Computers and Geosciences, Volume 35, Number 12, December, pages 2283-2294. Williams, Michael S., Michael P. Finn, and Robert A. Buehler (2006). An Open Source, Object- Oriented General Cartographic Transformation Program (GCTP). Abstract presented at the International Society for Photogrammetry and Remote Sensing Commission IV Symposium on Geospatial Databases for Sustainable Development, Goa, India.

15. Background Presentations and Publications Multi-Resolution Raster Project – Map Projections: http://cegis.usgs.gov/projection/index.html http://cegis.usgs.gov/projection/index.html – Older MRR: http://cegis.usgs.gov/watershed/index.html and http://cegis.usgs.gov/soil_moisture/index.html http://cegis.usgs.gov/watershed/index.html http://cegis.usgs.gov/soil_moisture/index.html

16. Plans for Near-Term Release pRasterBlaster 1.5 Finish libRasterBlaster Release dRasterBlaster

17. Small-Scale Raster Map Projection Transformation Using a Virtual System to Interactively Share Computing Resources and Data U.S. Department of the Interior U.S. Geological Survey QUESTIONS??!? Briefing to CyberGIS Technical Points of Contact Best Practices Series 19 July 2012