FWIW, I couldn't get it to build - this is on a simple Xeon-based system under CentOS 6.2:
cc1: warnings being treated as errors spml_yoda_getreq.c: In function 'mca_spml_yoda_get_completion': spml_yoda_getreq.c:98: error: pointer targets in passing argument 1 of 'opal_atomic_add_32' differ in signedness ../../../../opal/include/opal/sys/amd64/atomic.h:174: note: expected 'volatile int32_t *' but argument is of type 'uint32_t *' spml_yoda_getreq.c:98: error: signed and unsigned type in conditional expression cc1: warnings being treated as errors spml_yoda_putreq.c: In function 'mca_spml_yoda_put_completion': spml_yoda_putreq.c:81: error: pointer targets in passing argument 1 of 'opal_atomic_add_32' differ in signedness ../../../../opal/include/opal/sys/amd64/atomic.h:174: note: expected 'volatile int32_t *' but argument is of type 'uint32_t *' spml_yoda_putreq.c:81: error: signed and unsigned type in conditional expression make[2]: *** [spml_yoda_getreq.lo] Error 1 make[2]: *** Waiting for unfinished jobs.... make[2]: *** [spml_yoda_putreq.lo] Error 1 cc1: warnings being treated as errors spml_yoda.c: In function 'mca_spml_yoda_put_internal': spml_yoda.c:725: error: pointer targets in passing argument 1 of 'opal_atomic_add_32' differ in signedness ../../../../opal/include/opal/sys/amd64/atomic.h:174: note: expected 'volatile int32_t *' but argument is of type 'uint32_t *' spml_yoda.c:725: error: signed and unsigned type in conditional expression spml_yoda.c: In function 'mca_spml_yoda_get': spml_yoda.c:1107: error: pointer targets in passing argument 1 of 'opal_atomic_add_32' differ in signedness ../../../../opal/include/opal/sys/amd64/atomic.h:174: note: expected 'volatile int32_t *' but argument is of type 'uint32_t *' spml_yoda.c:1107: error: signed and unsigned type in conditional expression make[2]: *** [spml_yoda.lo] Error 1 make[1]: *** [all-recursive] Error 1 Only configure arguments: enable_picky=yes enable_debug=yes gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-3) On Aug 10, 2013, at 7:21 PM, "Barrett, Brian W" <bwba...@sandia.gov> wrote: > On 8/6/13 10:30 AM, "Joshua Ladd" <josh...@mellanox.com> wrote: > >> Dear OMPI Community, >> >> Please find on Bitbucket the latest round of OSHMEM changes based on >> community feedback. Please git and test at your leisure. >> >> https://bitbucket.org/jladd_math/mlnx-oshmem.git > > Josh - > > In general, I think everything looks ok. However, the "right" thing > doesn't happen if the CM PML is used (at least, when using the Portals 4 > MTL). When configured with: > > ./configure --enable-mca-no-build=pml-ob1,pml-bfo,pml-v,btl,bml,mpool > > The build segfaults trying to run a SHMEM program: > > mpirun -np 2 ./bcast > [shannon:90397] *** Process received signal *** > [shannon:90397] Signal: Segmentation fault (11) > [shannon:90397] Signal code: Address not mapped (1) > [shannon:90397] Failing at address: (nil) > [shannon:90398] *** Process received signal *** > [shannon:90398] Signal: Segmentation fault (11) > [shannon:90398] Signal code: Address not mapped (1) > [shannon:90398] Failing at address: (nil) > [shannon:90397] [ 0] /lib64/libpthread.so.0() [0x38b7a0f4a0] > [shannon:90397] *** End of error message *** > [shannon:90398] [ 0] /lib64/libpthread.so.0() [0x38b7a0f4a0] > [shannon:90398] *** End of error message *** > -------------------------------------------------------------------------- > mpirun noticed that process rank 1 with PID 90398 on node shannon exited > on signal 11 (Segmentation fault). > -------------------------------------------------------------------------- > > > > Brian > > -- > Brian W. Barrett > Scalable System Software Group > Sandia National Laboratories > > > > > _______________________________________________ > devel mailing list > de...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/devel
