Hi Jeff,
Did you mean to add it in the makefile? All i have done now is only
to sustitude the word "sm" with "ht" both in the code and configure file.
i think i have this -avoid-version in mca_btl_ht_LDFLAGS.
why sm didn't report any error?but ht report the error.they are all the
same,except the na
This has been committed in r22872.
Let me know if you see any problems with the commit.
-- Josh
On Mar 23, 2010, at 7:57 AM, Joshua Hursey wrote:
Just a reminder that this RFC will go into the trunk this evening
unless there are strong objections.
We intend to let this soak for a few days
You probably want to add "-avoid-version" to the mca_btl_ht_LDFLAGS (and the
others).
See the Libtool docs for more info here; but in general, we don't use the .so
versioning scheme for OMPI plugins. Only for actual shared libraries that apps
link against.
On Mar 23, 2010, at 9:32 AM, hu yao
Hi George,Jeff and All
Recently i add a component into the btl,named HT,it is very similar to sm.i
meet a problem when make.
steps to reproduce
1:make three ht directories under
~/ompi/mca/btl/ht ~/ompi/mca/mpool/ht ~/ompi/mca/common/ht,
2:i copy most code and file from sm component
3:i run ./autog
Just a reminder that this RFC will go into the trunk this evening unless there
are strong objections.
We intend to let this soak for a few days then bring it over to the 1.5 series
(after the 1.5.0 release).
-- Josh
On Mar 15, 2010, at 9:26 AM, Josh Hursey wrote:
> (Updated RFC, per offline d
Hello all,
It was long ago where I've asked about hints to implement a dynamic BTL
control. I've currently managed to change the MPI communication path
from a BTL module (e.g. openib) to another BTL module (e.g. tcp) at
runtime of a distributed application.
For this I've developed a so calle
