is responsible for checking this condition. At the datatype engine, I accept it just as a nice way to set
the soft UB for a data (without using a real UB marker). This approach can be used to create
the subarray and darray datatype. However from the MPI level this function should never be
called directly with a count set to 0.
This commit was SVN r4512.
the same predefined datatype as in the C version. Each language is responsible to return datatypes matching
the current language.
This commit was SVN r4497.
Add a match_size function. This function match depending on the language, the kind of data required and
the size. Special care should be taken for C++ if we are looking for integer or real types as C++ can
return C datatypes. We use MPI_DATATYPE_NULL as a return error if there is no matching datatype.
This commit was SVN r4496.
correct size in type_match_size function. I update the dump datatype function. However these flags are
only available for predefined datatypes, it's seems to be useless to use them for the derived datatypes ...
This commit was SVN r4479.
* mpi_show_mca_params
If set to true, this turns on the dumping of all MCA parameters when MPI_INIT is called.
Only the 'rank 0' processes will print the parameters.
* mpi_show_mca_params_file
(This value is only used if the first argument is set to true) If this value is non-NULL
it specifies the file to put the dump into. This file can then be used as input to mpirun
for debugging purposes. If this value is not set (and mpi_show_mca_params is set) then
the parameters are dumped to stdout.
I also changed the following parameters to internal=true:
gpr_base_replica
ns_base_replica
pcmclient_env_cellid
This commit was SVN r4475.
* SPARC Assembly fixes:
- Use SPARC assembly type only when not able to use the SPARC v9
instruction set (instead of previous whenever sizeof(void*) == 4
- Use SPARCV9_32 (aka sparc v8plus) and SPARCV9_64 (aka sparc v9) when
possible. Already were doing so for the 64bit, but on 32bit we
were falling back to SPARC.
- Implemented SPARCV9_32 atomic operations
- Emit warning if user is going to get SPARC atomic, as that probably
isn't what the user wants for best performance.
* Started shell of MIPS assembly. Does not work, but wanted something
so that everyone would only have to re-autogen once today....
This commit was SVN r4465.
threads (defaults to use MPI threads, disable progress threads). This
allows us to have MPI threaded support, but without progress threads
and all that fun stuff.
This commit was SVN r4443.
- Use fcntl.h, not sys/fcntl.h (man pages on every platform I could find
say fcntl.h and solaris/AIX don't provide sys/fcntl.h)
- Make timeradd macro available on platforms where sys/time.h exists but
timeradd macro doesn't (Solaris)
- Include util/printf.h from ompi_config_bottom.h so that ompi_asprintf
and friends are always available.
This commit was SVN r4441.
couple register moves here and there). Also inline the cmpset calls from
the aquire and release cmpset calls, which should save a bunch.
This commit was SVN r4437.
* Fix compiler error on Sparc64 when not inlining assembly
* Fix error in Sparc64 compare&swap operations. Now pass test suite
This commit was SVN r4436.
* Make sure the update.sh scripts all use OMPI_WANT_SMP_LOCKS
* Add sparc (32bit) assembly
- Memory barriers
- spinlocks
- emulate add/sub using the spinlock table with hashed lookups, as
suggested by the linux kernel folk (better than the other option,
requiring the counters only use 24 bits)
This commit was SVN r4429.
