On Thursday 10 May 2007, Jeff Squyres wrote:
> On May 10, 2007, at 8:08 AM, Peter Kjellstrom wrote:
> > I recently tried ompi on early ConnectX hardware/software.
> > The good news, it works =)
>
> We've seen some really great 1-switch latency using the early access
> ConnectX hardware. I have a p
On Thu, 2007-05-10 at 23:10 -0400, Donald Kerr wrote:
>
> Caitlin Bestler wrote:
>
> >devel-boun...@open-mpi.org wrote:
> >
> >
> >>>There are two new issues so far:
> >>>
> >>>1) this has uncovered a connection migration issue in the Chelsio
> >>>driver/firmware. We are developing and testing
All,
MTT can now be used to test your developer workspaces. The
quick, cut-n-paste way to get started is:
$ svn co https://svn.open-mpi.org/svn/mtt/branches/ompi-core-testers
$ cd samples
$ cat developer.ini trivial.ini | ../client/mtt - hostlist=host1,host2
alreadyinstalled_dir=/your/mpi/ins
Donal Kerr wrote:
>>> order of business after connection establishment
>>> (mba_btl_udapl_sendrecv(). The RECV buffer post for this exchange,
>>> however, should really be done _before_ the
>>> dat_ep_connect() on the active side, and _before_ the
>>> dat_cr_accept() on the server side.
>>> Curre
More like trying to work around the race condition that exists: The
server side sends an rdma message first thus violating the iwarp
protocol. For those who want the gory details: when the server sends
first -and- that rdma message arrives at the client _before_ the
client
transitions into r
Caitlin Bestler wrote:
[snip]
> The DAPL semantics are very clear that send/recv operations must
> be matched one to one, that the receive buffer must be large
> enough for the received message and that there must be a receive
> buffer for each incoming send/recv message. That means that
> the send
As an aside, my personal feeling is that even when running over IB the
preposting of recvs is worth the small overhead of piggybacking a
credit
system on the messages that already cross the wire. If nothing else,
this avoids adding congestion of RNR-NAKS and the resends they
trigger.
Put
