Re: [OMPI devel] Open MPI v2.0.0rc2
On 04/28/2016 05:01 PM, Jeff Squyres (jsquyres) wrote: At long last, here's the next v2.0.0 release candidate: 2.0.0rc2: https://www.open-mpi.org/software/ompi/v2.x/ We didn't keep a good list of all the things that have changed since rc1 -- but it's many things. Here's a link to the NEWS file for v2.0.0: https://github.com/open-mpi/ompi-release/blob/v2.x/NEWS Please test test test! I see that --enable-mpi-cxx appears to default to disabled now, but I don't see any mention of it in the NEWS. https://github.com/open-mpi/ompi-release/commit/84f1e14b17dcc467e315038596535d8c7717c809 I suspect I'll keep this enabled in the Fedora openmpi builds just because. But I could be persuaded otherwise. Also, I see mention of improved MPI_THREAD_MULTIPLE support but that it still defaults to disabled, so I assume it probably should still be disabled in the basic fedora package. Also filed https://github.com/open-mpi/ompi/issues/1609 for failing to find system pmix library. I think that's it for me so far. -- Orion Poplawski Technical Manager 303-415-9701 x222 NWRA/CoRA DivisionFAX: 303-415-9702 3380 Mitchell Lane or...@cora.nwra.com Boulder, CO 80301 http://www.cora.nwra.com
Re: [OMPI devel] Open MPI v2.0.0rc2
On Apr 30, 2016, at 12:20 AM, Orion Poplawski wrote: > > I see that --enable-mpi-cxx appears to default to disabled now, but I don't > see any mention of it in the NEWS. Doh! Yes, we do need to mention that in the NEWS. > https://github.com/open-mpi/ompi-release/commit/84f1e14b17dcc467e315038596535d8c7717c809 > > I suspect I'll keep this enabled in the Fedora openmpi builds just because. > But I could be persuaded otherwise. The C++ bindings have actually been deleted from the MPI specification since 3.0. Disabling them by default is the first step to (eventual) removal from Open MPI. Note: no date has been set for actual removal; that could be quite a ways in the future. Enabling them by default in a downstream package seems fine to me. > Also, I see mention of improved MPI_THREAD_MULTIPLE support but that it still > defaults to disabled, so I assume it probably should still be disabled in the > basic fedora package. Mmmm. Good question. Anyone have any opinions about this? > Also filed https://github.com/open-mpi/ompi/issues/1609 for failing to find > system pmix library. Thanks! -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
[OMPI devel] Warnings in 2.0 release candidate
On CentOS-7 using gcc 4.8:
btl_tcp.c: In function ‘mca_btl_tcp_add_procs’:
btl_tcp.c:97:28: warning: comparison between signed and unsigned integer
expressions [-Wsign-compare]
for (int j = 0 ; j < tcp_proc->proc_endpoint_count ; ++j) {
^
btl_tcp_proc.c: In function ‘mca_btl_tcp_proc_lookup’:
btl_tcp_proc.c:772:28: warning: comparison between signed and unsigned integer
expressions [-Wsign-compare]
for (int i = 0 ; i < mca_btl_tcp_component.tcp_num_btls ; ++i) {
^
btl_tcp_proc.c:761:13: warning: unused variable ‘rc’ [-Wunused-variable]
int rc;
^
io_ompio_component.c: In function ‘file_query’:
io_ompio_component.c:275:19: warning: unused variable ‘fsbuf’
[-Wunused-variable]
struct statfs fsbuf;
^
io_ompio_component.c:274:11: warning: unused variable ‘dir’ [-Wunused-variable]
char *dir;
^
io_ompio_component.c:273:9: warning: unused variable ‘err’ [-Wunused-variable]
int err;
^
mpi_MPI.c: In function ‘JNI_OnLoad’:
mpi_MPI.c:144:24: warning: ISO C forbids conversion of function pointer to
object pointer type [-Wpedantic]
if(0 != dladdr((void *)JNI_OnLoad, &info)) {
^
runtime/oshmem_shmem_exchange.c:19:5: warning: "OMPI_ENABLE_MPI_PROFILING" is
not defined [-Wundef]
#if OMPI_ENABLE_MPI_PROFILING
^
runtime/oshmem_shmem_init.c:82:2: warning: #ident is a GCC extension [enabled
by default]
#ident OSHMEM_IDENT_STRING
^
runtime/oshmem_shmem_init.c:85:5: warning: "OMPI_ENABLE_MPI_PROFILING" is not
defined [-Wundef]
#if OMPI_ENABLE_MPI_PROFILING
^
runtime/oshmem_shmem_finalize.c:61:5: warning: "OMPI_ENABLE_MPI_PROFILING" is
not defined [-Wundef]
#if OMPI_ENABLE_MPI_PROFILING
Re: [OMPI devel] Warnings in 2.0 release candidate
Ralph,
the OMPI_ENABLE_MPI_PROFILING related warnings are fixed in
https://github.com/open-mpi/ompi-release/pull/1056
Cheers,
Gilles
On Saturday, April 30, 2016, Ralph Castain wrote:
> On CentOS-7 using gcc 4.8:
>
>
> btl_tcp.c: In function ‘mca_btl_tcp_add_procs’:
> btl_tcp.c:97:28: warning: comparison between signed and unsigned integer
> expressions [-Wsign-compare]
> for (int j = 0 ; j < tcp_proc->proc_endpoint_count ; ++j) {
> ^
> btl_tcp_proc.c: In function ‘mca_btl_tcp_proc_lookup’:
> btl_tcp_proc.c:772:28: warning: comparison between signed and unsigned
> integer expressions [-Wsign-compare]
> for (int i = 0 ; i < mca_btl_tcp_component.tcp_num_btls ; ++i) {
> ^
> btl_tcp_proc.c:761:13: warning: unused variable ‘rc’ [-Wunused-variable]
> int rc;
> ^
>
>
> io_ompio_component.c: In function ‘file_query’:
> io_ompio_component.c:275:19: warning: unused variable ‘fsbuf’
> [-Wunused-variable]
> struct statfs fsbuf;
>^
> io_ompio_component.c:274:11: warning: unused variable ‘dir’
> [-Wunused-variable]
> char *dir;
>^
> io_ompio_component.c:273:9: warning: unused variable ‘err’
> [-Wunused-variable]
> int err;
> ^
>
>
> mpi_MPI.c: In function ‘JNI_OnLoad’:
> mpi_MPI.c:144:24: warning: ISO C forbids conversion of function pointer to
> object pointer type [-Wpedantic]
> if(0 != dladdr((void *)JNI_OnLoad, &info)) {
> ^
>
>
> runtime/oshmem_shmem_exchange.c:19:5: warning: "OMPI_ENABLE_MPI_PROFILING"
> is not defined [-Wundef]
> #if OMPI_ENABLE_MPI_PROFILING
> ^
> runtime/oshmem_shmem_init.c:82:2: warning: #ident is a GCC extension
> [enabled by default]
> #ident OSHMEM_IDENT_STRING
> ^
> runtime/oshmem_shmem_init.c:85:5: warning: "OMPI_ENABLE_MPI_PROFILING" is
> not defined [-Wundef]
> #if OMPI_ENABLE_MPI_PROFILING
> ^
> runtime/oshmem_shmem_finalize.c:61:5: warning: "OMPI_ENABLE_MPI_PROFILING"
> is not defined [-Wundef]
> #if OMPI_ENABLE_MPI_PROFILING
>
>
> ___
> devel mailing list
> de...@open-mpi.org
> Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/devel
> Link to this post:
> http://www.open-mpi.org/community/lists/devel/2016/04/18861.php
Re: [OMPI devel] Open MPI v2.0.0rc2
Hi Jeff, Let's just update the MPI_THREAD_MULTIPLE comment to say that enable-mpi-thread-multiple is still required as part of config. Howard 2016-04-29 22:20 GMT-06:00 Orion Poplawski : > On 04/28/2016 05:01 PM, Jeff Squyres (jsquyres) wrote: > >> At long last, here's the next v2.0.0 release candidate: 2.0.0rc2: >> >> https://www.open-mpi.org/software/ompi/v2.x/ >> >> We didn't keep a good list of all the things that have changed since rc1 >> -- but it's many things. Here's a link to the NEWS file for v2.0.0: >> >> https://github.com/open-mpi/ompi-release/blob/v2.x/NEWS >> >> Please test test test! >> >> > I see that --enable-mpi-cxx appears to default to disabled now, but I > don't see any mention of it in the NEWS. > > > https://github.com/open-mpi/ompi-release/commit/84f1e14b17dcc467e315038596535d8c7717c809 > > I suspect I'll keep this enabled in the Fedora openmpi builds just > because. But I could be persuaded otherwise. > > Also, I see mention of improved MPI_THREAD_MULTIPLE support but that it > still defaults to disabled, so I assume it probably should still be > disabled in the basic fedora package. > > Also filed https://github.com/open-mpi/ompi/issues/1609 for failing to > find system pmix library. > > I think that's it for me so far. > > -- > Orion Poplawski > Technical Manager 303-415-9701 x222 > NWRA/CoRA DivisionFAX: 303-415-9702 > 3380 Mitchell Lane or...@cora.nwra.com > Boulder, CO 80301 http://www.cora.nwra.com > ___ > devel mailing list > de...@open-mpi.org > Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/devel > Link to this post: > http://www.open-mpi.org/community/lists/devel/2016/04/18859.php >
[OMPI devel] v2.0.0rc issues
With external libevent, hwloc, and pmix 1.1.4: +-+-+-+--+--+--+--+--+---+ | Phase | Section| Pass | Fail | Time out +-+-+-+--+--+--+--+--+---+ | Test Run| ibm | 375 | 0 | 1 | Test Run| intel| 466 | 0| 8 | Test Run| intel_skip| 422 | 1| 8 | Test Run| orte | 15 | 0| 4 +-+-+-+--+--+--+--+--+—+ Total Tests:1354 Total Failures: 22 Total Passed: 1332 With all internal: Total Tests:1354 Total Failures: 1 <= ibm test suite Total Passed: 1353 I’m going to investigate the difference, but given that the packagers will only supply the external variant, we need to fix these problems. Ralph
