View source for ITK Registration Optimization/2007-04-06-tcon

= Agenda =

=== Tests ===
* Two types of tests
** Baseline: LinearInterp is useful for profiling
*** Profile reports in Reports subdir
** Optimization: OptMattesMI is a self-contained test
*** Submit to dashboard
**** test name / method
**** non-optimized speed
**** optimized speed
**** optimized error (difference from non-optimized results)

=== Timing ===
* Priority
* Thread affinity

=== Performance Dashboard ===
* <em>Ranking computers?</em>
** CPU, memory, etc in dashboard
** MFlops as measured by Whetstone?
* Public submission of performance
** Logins and passwords configured in cmake
** <em>Encryption in cmake?</em>
* <em>Organization of Experiments/Dashboards</em>
** <em>When new experiment?</em>
* <em>Appropriate summary statistics</em>
** Per machine: batch -vs- speed/error
** Per test: mflops -vs- speed/error
** All, batch -vs- % change in performance

=== Review of OptMattesMI ===
* Lessons learned
** Mutex bad
** Memory good

=== ctest suite ===
* Ideal set of tests is machine specific
** e.g., Number of threads and image size

= Tasks =

=== Julien ===
# Work with Seb to get reports from Amber2
#* Result
#** Amber2 is allocated to another project - therefore work will transition to machines at SPL
# Define role of experiments and batches
#* Work with Seb to integrate with cmake dashboard
#* New experiment = new cvs tag
#* New batch = nightly (possibly only if cvs has changed)
# CMake knows of # of CPUs and CPU cores
# CMake knows of memory available
# Implement BMDashboards

=== Brad ===
# Continue to develop registration pipelines
#* Commit into CVS
#* Implement as ctests
# Optimize the meansquareddifferenceimagetoimagemetric

=== Seb ===
# Setup CMake Dashboard
# Add md5 encryption function to CMake for BatchMake passwords
# Work with Julien on BatchMake Dashboard designs
# Investigate other opportunities for optimization

=== Stephen ===
# Get Seb/Brad access to SPL machines
# Continue to optimize MattesMIMetric
# Determine BMDashboard table structure
# Have programs switch between baseline, optimized, and both testing/reporting