- 17 Aug, 2015 1 commit
-
-
Jonathan Jenkins authored
-
- 06 Aug, 2015 1 commit
-
-
Misbah Mubarak authored
-
- 04 Aug, 2015 3 commits
-
-
Jonathan Jenkins authored
-
Misbah Mubarak authored
-
Misbah Mubarak authored
-
- 30 Jul, 2015 2 commits
-
-
Misbah Mubarak authored
Adding group level mapping in the dragonfly: multiple routers can now be specified in the config file
-
Jonathan Jenkins authored
-
- 23 Jul, 2015 1 commit
-
-
Jonathan Jenkins authored
-
- 05 Jun, 2015 1 commit
-
-
Misbah Mubarak authored
Adding rough version of history window in dragonfly adaptive routing. Updating the simulation to display more stats
-
- 04 Jun, 2015 1 commit
-
-
Misbah Mubarak authored
Adding further updates to the dragonfly routing (statistics for adaptive routing updated, conditions for queue congestion sensing updated)
-
- 03 Jun, 2015 1 commit
-
-
Misbah Mubarak authored
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
-
- 08 Apr, 2015 1 commit
-
-
Misbah Mubarak authored
-
- 03 Apr, 2015 1 commit
-
-
Jonathan Jenkins authored
-
- 31 Mar, 2015 1 commit
-
-
Misbah Mubarak authored
-
- 09 Oct, 2014 1 commit
-
-
Jonathan Jenkins authored
NOTES: - torus does not use it, as it has some routing logic preventing direct usage. It probably can be done, but I'll leave that for later. - collectives in torus, dragonfly don't use it yet.
-
- 29 Aug, 2014 1 commit
-
-
Jonathan Jenkins authored
-
- 20 Aug, 2014 1 commit
-
-
Jonathan Jenkins authored
Rather than model-net LPs directly sending messages to other model-net LPs, LPs can route the intended message through the scheduler interface to be queued up for reception by the receiver (see the diff of loggp.c). This has the benefit of enabling things like priority and fairness for N->1 communication patterns. Currently, no packetizing is supported, and I haven't yet wrote checks for it - beware. Loggp is currently the only supported model. simplenet could also be supported without much trouble, but I doubt there's any demand for it at the moment. This should NOT be used by the dragonfly/torus models, as they have their own routing backend.
-
- 15 Aug, 2014 1 commit
-
-
Jonathan Jenkins authored
Torus and simplewan each have problems precluding them from the current scheduling fix: - simplewan - each "device" has N input/output ports. It can't simply tell the scheduler when they are (it is?) idle because the scheduler doesn't know which packets go to which ports - torus - also has N input/output ports (two for each dimension). Also, the same routing "queue" (via the "next_link_available_time" var) is used for incoming and outgoing messages, so we can't guarantee the scheduler that we'll be available at time x (an incoming msg could arrive and then be routed at time x-1). This isn't a problem for the dragonfly network as terminals aren't intermediate routers. Ideally what needs to happen here is for the intermediate packets/chunks to be queued up in the scheduler.
-
- 31 Jul, 2014 3 commits
-
-
Jonathan Jenkins authored
-
Jonathan Jenkins authored
-
Jonathan Jenkins authored
All configuration now proceeds on a per-LP level, and requires separate registration and configuration calls, as seen in the test programs. model_net_set_params is no longer used, and is replaced by model_net_register and model_net_configure. The dragonfly network, having two LP types bundled in the same code-path, is special-cased in the registration code. LP-mapping in model-net now has the following defaults: - counts via codes_mapping_get_lp_count are now with respect to the calling network LP's annotation. - when looking up network LPs via codes_mapping_get_lp_info/codes_mapping_get_lp_id, the annotation of the calling network LP is used. Hence, routing now occurs only between LPs of the same annotation. If the destination LP's group specified by model_net_*event does not contain a modelnet LP with the same annotation as the modelnet LP in the sender's group, then an error will occur (in codes_mapping). Known Issues: - modelnet users currently cannot specify which modelnet LP to use in the case of multiple modelnet LPs in the sender's group. This will be fixed in future commits after a consensus is reached on the best way to expose this information.
-
- 24 Jul, 2014 1 commit
-
-
Jonathan Jenkins authored
-
- 18 Jul, 2014 1 commit
-
-
Jonathan Jenkins authored
-
- 08 Jul, 2014 1 commit
-
-
Jonathan Jenkins authored
-
- 07 Jul, 2014 2 commits
- 06 Jul, 2014 1 commit
-
-
mubarak authored
-
- 03 Jul, 2014 1 commit
-
-
mubarak authored
-
- 13 Jun, 2014 1 commit
-
-
mubarak authored
Adding collective modeling functions in model-net (currently only dragonfly/torus models support it)
-
- 11 Jun, 2014 1 commit
-
-
mubarak authored
-
- 21 May, 2014 1 commit
-
-
Jonathan Jenkins authored
-
- 14 May, 2014 1 commit
-
-
Jonathan Jenkins authored
-
- 05 May, 2014 1 commit
-
-
Jonathan Jenkins authored
- pull itself not yet tested
-
- 23 Apr, 2014 1 commit
-
-
Jonathan Jenkins authored
-
- 16 Apr, 2014 1 commit
-
-
Jonathan Jenkins authored
-
- 08 Apr, 2014 1 commit
-
-
Shane Snyder authored
This prevents simulations that run for a certain duration from crashing rather than ending when simulation time is reached.
-
- 19 Dec, 2013 1 commit
-
-
Philip Carns authored
-
- 13 Dec, 2013 1 commit
-
-
Misbah Mubarak authored
-
- 29 Aug, 2013 1 commit
-
-
Misbah Mubarak authored
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
-
- 27 Aug, 2013 1 commit
-
-
Philip Carns authored
-