GitLab

Adding collective modeling functions in model-net (currently only dragonfly/torus models support it)

- currently stupid, stats don't really mean
  anything when pulling
- enable manually by setting do_pull = 1 (no
  cmdline option yet)

- pull itself not yet tested

minor changes to model-net plug-in: (1) making the torus network's chunk size configurable (2) handling some edge cases which we haven't encountered so far but its good to have them for future

- these calls should be made by the top level model only, so that all
  results are consolidated into the same subdirectory
- add corresponding calls to modelnet test programs

- also tweak temporary hard-coded network parameters in loggp method to
  look somewhat like Tukey IB network for quick sanity checking of
  output

- right now this runs out of event memory when you run it

- just a slightly modified copy of normal modelnet test for now; will
  update to use as the primary test harness for loggp validation

also misc update to how loggp method plugs into modelnet

Adding statistics collection using lp-io in model-net API (comes from the simple-net stats collection), works for simple-net, torus and the dragonfly network models

Updates to modelnet (1) Updated the mapping configuration for dragonfly (the mapping now distributes the routers equally on all the PES.  The old dragonly mapping configuration was placing the routers on a single PE which was causing congestion on that PE leading to slow model performance in parallel ) (2) Updated 'make check' to handle dragonfly and torus test cases as well (3) Remove the num_servers argument from model-net test case, the number of servers are now calculated from the config file (4) Placing the ross mapping parameters in the codes mapping file

Adding dragonfly network model with codes, model-net-test case run time parameters are updated (see README_MN_TEST.txt for details)