GitLab

Need to cut down synthetic dragonfly network size, currently running out of memory on jenkins server (commenting the test for now)

1) Adding dragonfly adaptive and prog-adaptive routing algorithms--- still testing with more workloads and crosschecking the computation 2) Two bug fixes in credit-based flow control

NOTE: very inefficient

Tired of explaining that it's not a good representation of a WAN. Instead, it's
now a simple point-to-point latency/bandwidth model.

- N priorities processed in increasing order
- queue for priority i not touched until 0...i-1 queues are empty
- example injection API usage shown in test program
  - currently, only the priority scheduler has need of it

- "modelnet" parameter in cfg is now a no-op
- "modelnet_order" parameter in cfg is required,
  listing order in which networks are indexed to
  the model
- modified "model_net_set_params" signature
- updated tests to use the new interface

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

For a particular LP type:
- get the global number of LPs of that type
- get the relative ID w.r.t. LPs of the same type

Now, specify the darshan install directory with --with-darshan=/dir/
to build the darshan workload generator and link it with test
applications.

Modifications to autotools to include necessary info for building
the darshan workload API. This API compiles fine, but the mpi replay
test is not linking properly with darshan library.

Now, specify the darshan install directory with --with-darshan=/dir/
to build the darshan workload generator and link it with test
applications.

Modifications to autotools to include necessary info for building
the darshan workload API. This API compiles fine, but the mpi replay
test is not linking properly with darshan library.

adding the mpi-replay tool to the tests/workload directory for replaying workloads from the codes workload api