Roland Dreier wrote:
> ./dapl/udapl/linux/dapl_osd.h:82:24: error: asm/atomic.h: No such file or
directory
> In file included from ./dapl/include/dapl.h:50,
> from dapl/udapl/dapl_init.c:39:
> ./dapl/udapl/linux/dapl_osd.h: In function 'dapl_os_atomic_inc':
> ./dapl/udapl/linux/dapl_osd.h:163: warning: implicit declaration of function
'IA64_FETCHADD'
I seem to recall udapl does some very bogus things with <asm/atomic.h>
and atomic operations in general.
Probably the easiest solution on ia64 is just to disable udapl. (Not
sure how to do that because I don't really work with the OFED build system)
Looks like if I don't ask it to build "everything" it doesn't try to
build the part(s) with the problems. Sooo, with that as my workaround I
can run some IPoIB tests on my cards, which has shown me that the MTU
has gotten a _lot_ bigger than it was before :)
Meanwhile, in all the stuff in docs/ at which I have glanced thusfar,
none of it seems to describe how to go about building a "native" SDP
application - one which creates an AF_INET_SDP socket explicitly. Ie
which include file(s) to include and any libraries against which it
should be linked. Is that actually part of 1.2rc2?
happy benchmarking,
rick jones
_______________________________________________
general mailing list
[email protected]
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
