On Mar 19, 2012, at 3:35 PM, Alex Margolin wrote:
> I've removed put and get from mosix (feels good to cut down on code
> lines...), but now the question has to be asked:
> Threre are send and sendi (is sendi sufficient, or must i include send as
> well?)
send is sufficient. sendi is an optimi
I've removed put and get from mosix (feels good to cut down on code
lines...), but now the question has to be asked:
Threre are send and sendi (is sendi sufficient, or must i include send
as well?) for the outgoing, but what about the incoming?
How does a process request input? Do I poll for inco
You don't have to implement all the protocols. The default is send protocol,
and this is the minimum you have to implement. The RMA protocols (GET or PUT)
are optional, and are specified by setting specific bits in your BTL flag.
Regarding the TCP BTL, the two RMA operations are "fake", they are
We're getting close. I swear! 1.5.5rc4 is posted:
http://www.open-mpi.org/software/ompi/v1.5/
Fixes since rc3:
- MXM fixes
- Coll tuned fixes for large data (> 2GB)
- Fix "external" hwloc component build
- Fix pmi modex so local/node ranks are correctly assigned
- Print error when mpool fa
I got it.
The patch looks ok.
Pavel (Pasha) Shamis
---
Application Performance Tools Group
Computer Science and Math Division
Oak Ridge National Laboratory
On Mar 18, 2012, at 9:59 PM, Christopher Samuel wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> On 16/03/12 08:14, Shami
I'm not sure I'm the best one to comment on OB1 these days, but I didn't
see anything obviously wrong.
Brian
On 3/19/12 9:32 AM, "Jeffrey Squyres" wrote:
>George / Brian --
>
>Can you guys comment on this patch?
>
>
>On Mar 15, 2012, at 5:07 PM, Nathan Hjelm wrote:
>
>> What: Update ob1 to do t
George / Brian --
Can you guys comment on this patch?
On Mar 15, 2012, at 5:07 PM, Nathan Hjelm wrote:
> What: Update ob1 to do the following:
> - fallback on send after rdma_put_retries_limit failures of prepare_dst
> - fallback on put (single non-pipelined) if the btl returns
> O
Nope - that will always be a problem, I'm afraid.
On Mar 19, 2012, at 1:54 AM, David Singleton wrote:
>
> Minor issue.
>
> We have a user with a --debug argument to their executable. This argument
> is removed when they use mpirun --debug ... ./a.out --debug ...
> This is still a problem in 1.5
Minor issue.
We have a user with a --debug argument to their executable. This argument
is removed when they use mpirun --debug ... ./a.out --debug ...
This is still a problem in 1.5.5. I haven't checked if this has changed
in later code.
David
