[SimGrid-user] SimGrid 3.16 is expected to be released by June 21.
martin.quinson at ens-rennes.fr
Thu Jun 8 22:42:48 CEST 2017
we are trying to release SimGrid every 3 months, so the next version
should happen in about 2 weeks now. This mails aims at keep you posted
on what is going on in the source code currently, and there is a lot
to say. I even think that the codename of v3.16 will be "Blooming
Spring", given the amount of work that was done since last release.
SMPI performance were further improved, using various OS-level magic
to speed up our virtualization of the MPI code to be run. This allowed
Tom to run a simulation of HPL involving 10^6 processes... Wow.
The dlopen privatization schema should even allows to run your ranks
in parallel (even if it's not well tested yet).
On the Cloud side, we implemented multi-core VMs, which naturally acts
as containers of processes. The sharing is still somewhat
questionnable, but this is the purpose of the pull request #181 on
GitHub. This should be fixed before the release.
S4U, the future interface of SimGrid 4.0 also progressed quite a bit.
The Storage is currently cleaned up by Fred, and some API changes are
to be expected. We are sorry but the exisiting API is so crappy that
nobody ever used it, I guess. If you need it, please speak up soon!
We renamed AS into NetZone in the XML files (but the old one still
work so no rush to update your platform). Since our platforms are
hierarchical, it makes no sense to name our zones "Autonomous
Systems". Some other documentation pages got updated and modified. If
you see a particularly old, misleading or otherwise ugly doc page,
please tell us and we'll fix it. Even typo reports are welcome.
But most of the work on S4U is not directly visible from the user. We
rewamped the whole code of activities (comms, execs, mutex, etc) to
not mix the applicative logic (calling test() or wait()) with the
object refcounting. Now, you can test your comm object as many time as
you want. This change was really intrusive in our internals, and we're
not done with restabilizing every bits, but we're on it.
Still on the S4U front, we managed to remove a few more XBT modules.
We prefer to use the std or boost libraries nowadays, and switching
away from the XBT module enable to reduce our maintainance burden. Be
warned that XBT will not always remain included in SimGrid.
On the infrastructure side, we are trying to setup a regular build
task for the main projects using SimGrid, to check that our changes
don't break them. The one of StarPU is close to be working (even if
not completely). If you want to have your own code tested regularly
against the SimGrid git to warn us about breakage that we introduce,
please come to us. We can grant you the right to do the needed config
in our Jenkins instance.
v3.16 will also contain the usual bug fixes, such as the jarfile that
should now work on Mac OSX (this time for real :) or the Java bindings
that should now be clear of any memory leak.
And the work for v3.17 started already. Here are some changesets that
are not ready to be included yet but may well be part of 3.17:
- Energy modeling for the network too
- New reduction algorithm for the model-checker, based on event
- multi-model simulations, to specify a differing networking model
for each netzone.
We have a plenty of other ideas and ongoing areas, but the most
important is that SimGrid is a free software. You too can contribute
your ideas to the melting pot and share them with our collegues.
See you soon, on the mailing list or elsewhere,
Honest criticism is hard to take, particularly from a relative, a
friend, an acquaintance, or a stranger. -- Franklin P. Jones.
-------------- next part --------------
A non-text attachment was scrubbed...
Size: 833 bytes
Desc: not available
More information about the Simgrid-user