Hi all, Does anybody have done experiments comparing the speed between mpich and openmpi?
Best regards, Yin Zhao > 在 2013年10月3日,0:00,users-requ...@open-mpi.org 写道: > > Send users mailing list submissions to > us...@open-mpi.org > > To subscribe or unsubscribe via the World Wide Web, visit > http://www.open-mpi.org/mailman/listinfo.cgi/users > or, via email, send a message with subject or body 'help' to > users-requ...@open-mpi.org > > You can reach the person managing the list at > users-ow...@open-mpi.org > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of users digest..." > > > Today's Topics: > > 1. Re: Error compiling openmpi-1.9a1r29292 (Jeff Squyres (jsquyres)) > 2. Re: non-functional mpif90 compiler (Gus Correa) > 3. Re: non-functional mpif90 compiler (Jeff Squyres (jsquyres)) > 4. CUDA-aware usage (Rolf vandeVaart) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Tue, 1 Oct 2013 18:38:15 +0000 > From: "Jeff Squyres (jsquyres)" <jsquy...@cisco.com> > To: Siegmar Gross <siegmar.gr...@informatik.hs-fulda.de>, Open MPI > Users <us...@open-mpi.org> > Subject: Re: [OMPI users] Error compiling openmpi-1.9a1r29292 > Message-ID: > <ef66bbeb19badc41ac8ccf5f684f07fc4f913...@xmb-rcd-x01.cisco.com> > Content-Type: text/plain; charset="us-ascii" > > These should now be fixed. > >> On Sep 30, 2013, at 3:41 AM, Siegmar Gross >> <siegmar.gr...@informatik.hs-fulda.de> wrote: >> >> Hi, >> >> today I tried to install openmpi-1.9a1r29292 on my platforms >> (openSuSE 12.1 Linux x86_64, Solaris 10 x86_64, and Solaris 10 Sparc) >> with Sun C 5.12 and gcc-4.8.0. I have the following error on all >> platforms, when I compile a 32- or 64-bit version with Sun C. >> >> ... >> PPFC mpi-f08-interfaces.lo >> >> module mpi_f08_interfaces >> ^ >> "../../../../../openmpi-1.9a1r29292/ompi/mpi/fortran/base/mpi-f08-interfaces.F90", >> Line = 19, Column = 8: ERROR: The compiler has detected >> errors in module "MPI_F08_INTERFACES". No module information >> file will be created for this module. >> >> use :: mpi_f08_types, only : MPI_Datatype, MPI_Comm, MPI_Aint, >> MPI_ADDRESS_KIND >> ^ >> >> "../../../../../openmpi-1.9a1r29292/ompi/mpi/fortran/base/mpi-f08-interfaces.F90", >> Line = 4419, Column = 57: ERROR: "MPI_AINT" is not in module "MPI_F08_TYPES". >> >> f90comp: 4622 SOURCE LINES >> f90comp: 2 ERRORS, 0 WARNINGS, 0 OTHER MESSAGES, 0 ANSI >> make[2]: *** [mpi-f08-interfaces.lo] Error 1 >> make[2]: Leaving directory >> `.../openmpi-1.9a1r29292-Linux.x86_64.64_cc/ompi/mpi/fortran/base' >> make[1]: *** [all-recursive] Error 1 >> make[1]: Leaving directory >> `.../openmpi-1.9a1r29292-Linux.x86_64.64_cc/ompi' >> make: *** [all-recursive] Error 1 >> linpc1 openmpi-1.9a1r29292-Linux.x86_64.64_cc 122 >> >> >> >> >> I have the following error on all platforms, when I compile a 32-bit >> version with gcc-4.8.0. >> >> linpc1 openmpi-1.9a1r29292-Linux.x86_64.32_gcc 120 tail -150 >> log.make.Linux.x86_64.32_gcc >> Making all in mca/spml >> make[2]: Entering directory >> `/export2/src/openmpi-1.9/openmpi-1.9a1r29292-Linux.x86_64.32_gcc/oshmem/mca/spml' >> CC base/spml_base_frame.lo >> CC base/spml_base_select.lo >> CC base/spml_base_request.lo >> CC base/spml_base_atomicreq.lo >> CC base/spml_base_getreq.lo >> CC base/spml_base_putreq.lo >> CC base/spml_base.lo >> CCLD libmca_spml.la >> make[2]: Leaving directory >> `/export2/src/openmpi-1.9/openmpi-1.9a1r29292-Linux.x86_64.32_gcc/oshmem/mca/spml' >> Making all in . >> make[2]: Entering directory >> `/export2/src/openmpi-1.9/openmpi-1.9a1r29292-Linux.x86_64.32_gcc/oshmem' >> CC op/op.lo >> ../../openmpi-1.9a1r29292/oshmem/op/op.c: In function >> 'oshmem_op_max_freal16_func': >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:15: error: 'a' undeclared >> (first use in this function) >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:194:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(max, freal16, ompi_fortran_real16_t, __max_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:15: note: each undeclared >> identifier is reported only once for each function it appears in >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:194:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(max, freal16, ompi_fortran_real16_t, __max_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:26: error: expected expression >> before ')' token >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:194:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(max, freal16, ompi_fortran_real16_t, __max_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:135:15: error: 'b' undeclared >> (first use in this function) >> type *b = (type *) out; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:194:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(max, freal16, ompi_fortran_real16_t, __max_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:135:26: error: expected expression >> before ')' token >> type *b = (type *) out; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:194:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(max, freal16, ompi_fortran_real16_t, __max_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c: In function >> 'oshmem_op_min_freal16_func': >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:15: error: 'a' undeclared >> (first use in this function) >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:211:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(min, freal16, ompi_fortran_real16_t, __min_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:26: error: expected expression >> before ')' token >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:211:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(min, freal16, ompi_fortran_real16_t, __min_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:135:15: error: 'b' undeclared >> (first use in this function) >> type *b = (type *) out; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:211:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(min, freal16, ompi_fortran_real16_t, __min_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:135:26: error: expected expression >> before ')' token >> type *b = (type *) out; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:211:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(min, freal16, ompi_fortran_real16_t, __min_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c: In function >> 'oshmem_op_sum_freal16_func': >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:15: error: 'a' undeclared >> (first use in this function) >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:230:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(sum, freal16, ompi_fortran_real16_t, __sum_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:26: error: expected expression >> before ')' token >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:230:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(sum, freal16, ompi_fortran_real16_t, __sum_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:135:15: error: 'b' undeclared >> (first use in this function) >> type *b = (type *) out; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:230:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(sum, freal16, ompi_fortran_real16_t, __sum_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:135:26: error: expected expression >> before ')' token >> type *b = (type *) out; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:230:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(sum, freal16, ompi_fortran_real16_t, __sum_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c: In function >> 'oshmem_op_prod_freal16_func': >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:15: error: 'a' undeclared >> (first use in this function) >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:249:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(prod, freal16, ompi_fortran_real16_t, __prod_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:134:26: error: expected expression >> before ')' token >> type *a = (type *) in; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:249:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(prod, freal16, ompi_fortran_real16_t, __prod_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:135:15: error: 'b' undeclared >> (first use in this function) >> type *b = (type *) out; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:249:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(prod, freal16, ompi_fortran_real16_t, __prod_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:135:26: error: expected expression >> before ')' token >> type *b = (type *) out; \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:249:1: note: in expansion of macro >> 'FUNC_OP_CREATE' >> FUNC_OP_CREATE(prod, freal16, ompi_fortran_real16_t, __prod_op); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c: In function 'oshmem_op_init': >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:149:62: error: expected expression >> before ')' token >> oshmem_op_##name##_##type_name->dt_size = sizeof(type); >> \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:302:5: note: in expansion of macro >> 'OBJ_OP_CREATE' >> OBJ_OP_CREATE(max, freal16, ompi_fortran_real16_t, OSHMEM_OP_MAX, >> OSHMEM_OP_TYPE_FREAL16); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:149:62: error: expected expression >> before ')' token >> oshmem_op_##name##_##type_name->dt_size = sizeof(type); >> \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:318:5: note: in expansion of macro >> 'OBJ_OP_CREATE' >> OBJ_OP_CREATE(min, freal16, ompi_fortran_real16_t, OSHMEM_OP_MIN, >> OSHMEM_OP_TYPE_FREAL16); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:149:62: error: expected expression >> before ')' token >> oshmem_op_##name##_##type_name->dt_size = sizeof(type); >> \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:336:5: note: in expansion of macro >> 'OBJ_OP_CREATE' >> OBJ_OP_CREATE(sum, freal16, ompi_fortran_real16_t, OSHMEM_OP_SUM, >> OSHMEM_OP_TYPE_FREAL16); >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:149:62: error: expected expression >> before ')' token >> oshmem_op_##name##_##type_name->dt_size = sizeof(type); >> \ >> ^ >> ../../openmpi-1.9a1r29292/oshmem/op/op.c:354:5: note: in expansion of macro >> 'OBJ_OP_CREATE' >> OBJ_OP_CREATE(prod, freal16, ompi_fortran_real16_t, OSHMEM_OP_PROD, >> OSHMEM_OP_TYPE_FREAL16); >> ^ >> make[2]: *** [op/op.lo] Error 1 >> make[2]: Leaving directory >> `/export2/src/openmpi-1.9/openmpi-1.9a1r29292-Linux.x86_64.32_gcc/oshmem' >> make[1]: *** [all-recursive] Error 1 >> make[1]: Leaving directory >> `/export2/src/openmpi-1.9/openmpi-1.9a1r29292-Linux.x86_64.32_gcc/oshmem' >> make: *** [all-recursive] Error 1 >> linpc1 openmpi-1.9a1r29292-Linux.x86_64.32_gcc 121 >> >> >> I would be grateful, if somebody can fix the problems. Thank you very >> much for your help in advance. >> >> >> Kind regards >> >> Siegmar >> >> _______________________________________________ >> users mailing list >> us...@open-mpi.org >> http://www.open-mpi.org/mailman/listinfo.cgi/users > > > -- > Jeff Squyres > jsquy...@cisco.com > For corporate legal information go to: > http://www.cisco.com/web/about/doing_business/legal/cri/ > > > > ------------------------------ > > Message: 2 > Date: Tue, 01 Oct 2013 15:07:42 -0400 > From: Gus Correa <g...@ldeo.columbia.edu> > To: Open MPI Users <us...@open-mpi.org> > Subject: Re: [OMPI users] non-functional mpif90 compiler > Message-ID: <524b1d7e.7040...@ldeo.columbia.edu> > Content-Type: text/plain; charset=ISO-8859-1; format=flowed > > Hi Damiano > > Glad to know you sorted out the problem with > your environment variables. > Home-brewed Open MPI tastes much better > than those six-pack canned RPMs. > Did OpenFOAM (was it OpenFoam?) eventually compile and run? > > Thanks Jeff for clarifying where is the hurdle (on Infiniband) > when one tries to build Open MPI as group of static libraries. > I tried to build OMPI static, and had failures in the past. > I eventually gave up, but it was never clear why it would fail > (although the error messages suggested that IB played a role). > However, all my attempts were on machines with Infinband hardware. > > Good to know that one can build OMPI static on TCP/IP machines. > And presumably also on (non-IB) standalone machines that will > only use the shared memory features of OMPI). > This may (or may not?) be useful when one intends to run MPI > programs in a single box. > (I wonder if this is what Damiano plans to do.) > > I know these questions may be somewhat off-topic, > but from the standpoint of performance, > once upon a time there was a popular wisdom that > static linking produced faster executables > than when linking to shared libraries > (static producing larger executables, though). > Is this "static is faster" view still valid? > Does it apply to Open MPI in particular? > Was it ever true? > > Many thanks, > Gus Correa > >> On 10/01/2013 05:16 AM, Jeff Squyres (jsquyres) wrote: >> If you are using a TCP network for MPI communications,static is fine. >> >> However, if you're trying to use an OS-bypass network such as >> InfiniBand, RoCE, or iWARP, using static libraries can be >> somewhat of a nightmare (because of how the OpenFabrics Verbs >> support libraries work). >> Specifically, I don't see the "openib" BTL plugin in your >> ompi_info output, meaning that your Open MPI installation >> is not capable of using InfiniBand/RoCE/iWARP. >> >> So just be aware that with your current builds, >> you're basically TCP-only. >> >> >>> On Oct 1, 2013, at 3:34 AM, Damiano Natali<damiano.nat...@gmail.com> wrote: >>> >>> Hi Gus, today I noticed there was another ompi directory in my path and >>> maybe it gave some strange errors so I put the new ompi installation at the >>> first place in PATH and LD_LIBRARY_PATH before the building and everything >>> went nicely! >>> >>> So, as you and Jeff said, the problem was in having the rigth paths! >>> >>> Thank you very much for your support! >>> >>> Damiano >>> >>> p.s. Building static libraries didn't result in any problem so far! >>> _______________________________________________ >>> users mailing list >>> us...@open-mpi.org >>> http://www.open-mpi.org/mailman/listinfo.cgi/users > > > > ------------------------------ > > Message: 3 > Date: Tue, 1 Oct 2013 19:19:01 +0000 > From: "Jeff Squyres (jsquyres)" <jsquy...@cisco.com> > To: Open MPI Users <us...@open-mpi.org> > Subject: Re: [OMPI users] non-functional mpif90 compiler > Message-ID: > <ef66bbeb19badc41ac8ccf5f684f07fc4f913...@xmb-rcd-x01.cisco.com> > Content-Type: text/plain; charset="us-ascii" > >> On Oct 1, 2013, at 3:07 PM, Gus Correa <g...@ldeo.columbia.edu> wrote: >> >> Thanks Jeff for clarifying where is the hurdle (on Infiniband) >> when one tries to build Open MPI as group of static libraries. >> I tried to build OMPI static, and had failures in the past. >> I eventually gave up, but it was never clear why it would fail >> (although the error messages suggested that IB played a role). >> However, all my attempts were on machines with Infinband hardware. > > If you care: > > http://www.open-mpi.org/faq/?category=mpi-apps#static-mpi-apps > http://www.open-mpi.org/faq/?category=mpi-apps#static-ofa-mpi-apps > > -- > Jeff Squyres > jsquy...@cisco.com > For corporate legal information go to: > http://www.cisco.com/web/about/doing_business/legal/cri/ > > > > ------------------------------ > > Message: 4 > Date: Tue, 1 Oct 2013 14:43:03 -0700 > From: Rolf vandeVaart <rvandeva...@nvidia.com> > To: "us...@open-mpi.org" <us...@open-mpi.org> > Subject: [OMPI users] CUDA-aware usage > Message-ID: > <3af945ebf4d3ec41afe44eed9b0585f36007be8...@hqmail02.nvidia.com> > Content-Type: text/plain; charset="us-ascii" > > We have done some work over the last year or two to add some CUDA-aware > support into the Open MPI library. Details on building and using the feature > are here. > > http://www.open-mpi.org/faq/?category=building#build-cuda > http://www.open-mpi.org/faq/?category=running#mpi-cuda-support > > I am looking for any feedback on this feature from anyone who has taken > advantage of it. You can send just send the response to me if you want and I > will compile the feedback. > > Rolf > > ----------------------------------------------------------------------------------- > This email message is for the sole use of the intended recipient(s) and may > contain > confidential information. Any unauthorized review, use, disclosure or > distribution > is prohibited. If you are not the intended recipient, please contact the > sender by > reply email and destroy all copies of the original message. > ----------------------------------------------------------------------------------- > -------------- next part -------------- > HTML attachment scrubbed and removed > > ------------------------------ > > Subject: Digest Footer > > _______________________________________________ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users > > ------------------------------ > > End of users Digest, Vol 2696, Issue 1 > **************************************