The following simple test code will exercise the following:
start_pes()
shmalloc()
shmem_int_get()
shmem_int_put()
shmem_barrier_all()
To compile:
shmemcc test_shmem.c -o test_shmem
To launch:
shmemrun -np 2 test_shmem
or for those who prefer to launch with SLURM
srun -n 2 test_shmem
Josh
-----Original Message-----
From: devel [mailto:devel-boun...@open-mpi.org] On Behalf Of Ralph Castain
Sent: Wednesday, August 14, 2013 5:32 PM
To: Open MPI Developers
Subject: Re: [OMPI devel] [EXTERNAL] OpenSHMEM round 2
Can you point me to a test program that would exercise it? I'd like to give it
a try first.
I'm okay with on by default as it builds its own separate library, and with the
RFC
On Aug 14, 2013, at 2:03 PM, "Barrett, Brian W" <bwba...@sandia.gov> wrote:
> Josh -
>
> In general, I don't have a strong opinion of whether OpenSHMEM is on
> by default or not. It might cause unexpected behavior for some users
> (like on Crays, where one should really use Cray's SHMEM), but maybe
> it's better on other platforms.
>
> I also would have no objection to the RFC, provided the segfaults I
> found get resolved.
>
> Brian
>
> On 8/14/13 2:08 PM, "Joshua Ladd" <josh...@mellanox.com> wrote:
>
>> Ralph, and Brian
>>
>> Thanks a bunch for taking the time to review this. It is extremely
>> helpful. Let me comment of the building of OSHMEM and solicit some
>> feedback from you guys (along with the rest of the community.)
>> Originally we had planned to enable OSHMEM to build only if
>> '--with-oshmem' flag was passed at configure time. However,
>> (unbeknownst to me) this behavior was changed and now OSHMEM is built by
>> default, i.e.
>> yes, Ralph this is the intended behavior now. I am wondering if this
>> is such a good idea. Do folks have a strong opinion on this one way
>> or the other? From my perspective I can see arguments for both sides
>> of the coin.
>>
>> Other than cleaning up warnings and resolving the segfault that Brian
>> observed are we on a good course to getting this upstream? Is it
>> reasonable to file an RFC for three weeks out?
>>
>> Josh
>>
>> -----Original Message-----
>> From: devel [mailto:devel-boun...@open-mpi.org] On Behalf Of Barrett,
>> Brian W
>> Sent: Sunday, August 11, 2013 1:42 PM
>> To: Open MPI Developers
>> Subject: Re: [OMPI devel] [EXTERNAL] OpenSHMEM round 2
>>
>> Ralph -
>>
>> I think those warnings are just because of when they last synced with
>> the trunk; it looks like they haven't updated in the last week, when
>> those (and some usnic fixes) went in.
>>
>> More concerning is the --enable-picky stuff and the disabling of
>> SHMEM in the right places.
>>
>> Brian
>>
>> On 8/11/13 11:24 AM, "Ralph Castain" <r...@open-mpi.org> wrote:
>>
>>> Turning off the enable_picky, I get it to compile with the following
>>> warnings:
>>>
>>> pget_elements_x_f.c:70: warning: no previous prototype for
>>> 'ompi_get_elements_x_f'
>>> pstatus_set_elements_x_f.c:70: warning: no previous prototype for
>>> 'ompi_status_set_elements_x_f'
>>> ptype_get_extent_x_f.c:69: warning: no previous prototype for
>>> 'ompi_type_get_extent_x_f'
>>> ptype_get_true_extent_x_f.c:69: warning: no previous prototype for
>>> 'ompi_type_get_true_extent_x_f'
>>> ptype_size_x_f.c:69: warning: no previous prototype for
>>> 'ompi_type_size_x_f'
>>>
>>> I also found that OpenShmem is still building by default. Is that
>>> intended? I thought you were only going to build if --with-shmem (or
>>> whatever option) was given.
>>>
>>> Looks like some cleanup is required
>>>
>>> On Aug 10, 2013, at 8:54 PM, Ralph Castain <r...@open-mpi.org> wrote:
>>>
>>>> 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
>>>>
>>>
>>> _______________________________________________
>>> devel mailing list
>>> de...@open-mpi.org
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>
>>
>>
>> --
>> 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
>> _______________________________________________
>> devel mailing list
>> de...@open-mpi.org
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>
>
>
> --
> 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
_______________________________________________
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel
#include "shmem.h"
#include "stdio.h"
#define N 100
static int target[N];
static int source[N];
#define STATIC_CHECK 1
#define DYNAMIC_CHECK 1
#define ATOMIC 1
#define PEER 1
int main()
{
int *source_d,*target_d;
int i;
start_pes(0);
source_d = shmalloc(sizeof(*source_d)*N);
target_d = shmalloc(sizeof(*target_d)*N);
for (i = 0; i < N; i++)
{
source_d[i] = source[i] = 1;
target[i] = target_d[i] = 9;
}
int peer = PEER;
if (_my_pe() == 0)
{
#if STATIC_CHECK
int c, f;
int a = c, b = f;
#if ATOMIC
for (i = 0; i < N; i++)
target[i] = shmem_int_g(source + i, peer);
#else
shmem_int_get(target, source, N, PEER);
#endif
#endif
#if DYNAMIC_CHECK
#if ATOMIC
for (i = 0; i < N; i++)
{
target_d[i] = shmem_int_g(source_d + i, peer);
}
#else
shmem_int_get(target_d, source_d, N, PEER);
#endif
#endif
}
if(_my_pe() == 0)
{
for (i = 0; i < N; i++)
{
#if DYNAMIC_CHECK
if(target_d[i] != 1)
{
printf("Get dynamic error %d, target + i = %p, target[0] = %d,
target[1] = %d\n",i, target_d + i,target_d[0], target_d[1]);
fflush(stdout);
return 1;
#endif
#if STATIC_CHECK
if (target[i] != 1)
{
printf("Get static error %d, target + i = %p, target[i] =
%d\n",i, target + i,target[i]);
fflush(stdout);
return 1;
}
#endif
}
}
}
/*put check*/
for (i = 0; i < N; i++)
{
source_d[i] = source[i] = 1;
target[i] = target_d[i] = -9;
}
shmem_barrier_all();
if (_my_pe() == 0)
{
#if STATIC_CHECK
shmem_int_put(target, source, N, PEER);
#endif
#if DYNAMIC_CHECK
shmem_int_put(target_d, source_d, N, PEER);
#endif
}
shmem_barrier_all();
if(_my_pe() == PEER)
{
for (i = 0; i < N; i++)
{
#if DYNAMIC_CHECK
if(target_d[i] != 1)
{
printf("Put dynamic error\n");
fflush(stdout);
return 1;
}
#endif
#if STATIC_CHECK
if (target[i] != 1)
{
printf("Put static error\n");
fflush(stdout);
return 1;
}
#endif
}
}
printf("All test passed\n");fflush(stdout);
return 0;
}
