This has now been fixed as of https://svn.open-mpi.org/trac/ompi/changeset/18995
; MTT should [finally] run tonight without problems.
On Jul 22, 2008, at 12:38 PM, Jeff Squyres wrote:
On Jul 22, 2008, at 12:32 PM, Roland Dreier wrote:
So I think using byteorder.h is not a good idea (note the warning).
How about just having two #defines, picking the Right one based on
WORDS_BIGENDIAN?
On Linux, the public <byteswap.h> header might have what you need.
For that matter <infiniband/arch.h> has htonll() defined.
The problematic line is:
#define IB_CM_ASSIGN_SERVICE_ID __cpu_to_be64(0x0200000000000000ULL)
There's no reason this has to be byte-swapped at compile time,
right? Using htonll or OMPI's hton64() should be sufficient, right?
--
Jeff Squyres
Cisco Systems
_______________________________________________
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel
--
Jeff Squyres
Cisco Systems
