Re: [OMPI devel] Datatype initialization bug?

2013-05-22 Thread Kawashima, Takahiro
George, Thanks for your quick response. Your fix seemed good to me last week, but this week my colleague found it's not sufficient. There are two issues. (A) We should update opt_desc too. In current ompi_datatype_init, we copy OPAL desc to OMPI desc. But opt_desc still points to OPAL de

[OMPI devel] Porting Open MPI

2013-05-22 Thread jhonatan alves
Hello, We are trying port Open MPI to a new operating system, called EPOS, but our main problem at the moment is that this operating system is not POSIX compatible. Our question is there some way to know what are the OS dependencies of Open MPI? Is there a porting manual of Open MPI? Is there a doc

[OMPI devel] RFC: Python-generated Fortran wrappers

2013-05-22 Thread Jeff Squyres (jsquyres)
WHAT: Replace all mpif.h, use mpi, and use mpi_f08 code with Python-generated code WHY: there are ***7*** copies of the Fortran bindings; keeping them all in sync when adding a new MPI-3 function (or updating/fixing an old one) is a nightmare WHERE: run a python generator script in ompi/mpi/for

Re: [OMPI devel] RFC: Python-generated Fortran wrappers

2013-05-22 Thread Ralph Castain
I have no issues other than wondering why we don't do it in perl given that we already do all non-shell actions in perl - is it necessary to intro another language? On May 22, 2013, at 5:58 AM, Jeff Squyres (jsquyres) wrote: > WHAT: Replace all mpif.h, use mpi, and use mpi_f08 code with Pytho

Re: [OMPI devel] RFC: Python-generated Fortran wrappers

2013-05-22 Thread Jeff Squyres (jsquyres)
On May 22, 2013, at 9:18 AM, Ralph Castain wrote: > I have no issues other than wondering why we don't do it in perl given that > we already do all non-shell actions in perl - is it necessary to intro > another language? Because Craig is writing it and he (strongly) prefers Python. That's rea

Re: [OMPI devel] RFC: Python-generated Fortran wrappers

2013-05-22 Thread Ralph Castain
On May 22, 2013, at 6:37 AM, "Jeff Squyres (jsquyres)" wrote: > On May 22, 2013, at 9:18 AM, Ralph Castain wrote: > >> I have no issues other than wondering why we don't do it in perl given that >> we already do all non-shell actions in perl - is it necessary to intro >> another language? >

Re: [OMPI devel] Porting Open MPI

2013-05-22 Thread Ralph Castain
On May 22, 2013, at 4:55 AM, jhonatan alves wrote: > > Hello, > We are trying port Open MPI to a new operating system, called EPOS, but our > main problem at the moment is that this operating system is not POSIX > compatible. That could make things difficult, depending on how incompatible i

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Barrett, Brian W
On 5/22/13 6:50 AM, "Ralph Castain" wrote: > >On May 22, 2013, at 6:37 AM, "Jeff Squyres (jsquyres)" > wrote: > >> On May 22, 2013, at 9:18 AM, Ralph Castain wrote: >> >>> I have no issues other than wondering why we don't do it in perl given >>>that we already do all non-shell actions in perl

Re: [OMPI devel] [EXTERNAL] Re: Porting Open MPI

2013-05-22 Thread Barrett, Brian W
On 5/22/13 6:54 AM, "Ralph Castain" wrote: >On May 22, 2013, at 4:55 AM, jhonatan alves >wrote: > >> >> Hello, >> We are trying port Open MPI to a new operating system, called EPOS, but >>our main problem at the moment is that this operating system is not >>POSIX compatible. > >That could make

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Jeff Squyres (jsquyres)
On May 22, 2013, at 10:00 AM, "Barrett, Brian W" wrote: >> Hmmm...the issue is that perl usually is included in the distro, but >> python often is not - you have to add that module. This seems to be a key argument, but I'm not sure it's still true. I'm a RHEL guy; I see that RHEL has installed

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Josh Hursey
Is this Python 2.x or 3.x? I ask because they are not 100% compatible due to changes in the language syntax. Meaning not all 2.x compilant Python programs work with a 3.x interpreter. IIRC there is a way to write a 2.x compliant Python program so that it is also 3.x compliant, but my Python knowled

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Jeff Squyres (jsquyres)
Good question. All the pythons I see are 2.x (OSX, RHEL). On May 22, 2013, at 12:18 PM, Josh Hursey wrote: > Is this Python 2.x or 3.x? I ask because they are not 100% compatible due to > changes in the language syntax. Meaning not all 2.x compilant Python programs > work with a 3.x interpre

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Ralph Castain
Good question - I haven't gone that far into it either. As for Jeff's other questions: * python packaging. I don't know if/where it comes standard. I typically add it to CentOS when I install, but that is always a selection option. I don't know if it has some basic level of python support inclu

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Barrett, Brian W
On 5/22/13 9:35 AM, "Ralph Castain" wrote: >* this isn't about Craig and his abilities - this is a more general >requirements discussion. I personally wouldn't change my comments if it >was Jeff or Brian making the request - the issue remains the same. >Introducing another language requirement on

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Ralph Castain
fwiw: macports is at py3.3 On May 22, 2013, at 9:27 AM, Jeff Squyres (jsquyres) wrote: > Good question. All the pythons I see are 2.x (OSX, RHEL). > > > On May 22, 2013, at 12:18 PM, Josh Hursey wrote: > >> Is this Python 2.x or 3.x? I ask because they are not 100% compatible due to >> cha

Re: [OMPI devel] Datatype initialization bug?

2013-05-22 Thread George Bosilca
Takahiro, I used your second patch the one that remove the copy of the description in the OMPI level (r28553). Thanks for your help and your patience in investigating this issues. George. On May 22, 2013, at 02:05 , "Kawashima, Takahiro" wrote: > George, > > Thanks for your quick respon

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Paul Hargrove
Let me jump in here with a different perspective. First, for those who don't know me: + I am NOT an OMPI developer + I am NOT an MPI application author either + I am a developer of "competing" HPC communications software (GASNet) + I contribute to OMPI mainly by building release candidates

[OMPI devel] In reply to: Re: [EXTERNAL] Re: Porting Open MPI

2013-05-22 Thread João Zeni
Hello, About how non-POSIX EPOS is, he don't provide any POSIX support but we can implement some support using EPOS funcionalities. About C library, yes EPOS provides a standard C library. Thank you -- João G. Zeni Ciências da Computação - INE UFSC Undergrad Researcher at LRG - INE UFSC Cel: (48)

Re: [OMPI devel] [EXTERNAL] Re: RFC: Python-generated Fortran wrappers

2013-05-22 Thread Ralph Castain
On May 22, 2013, at 11:51 AM, Paul Hargrove wrote: > Let me jump in here with a different perspective. > First, for those who don't know me: > + I am NOT an OMPI developer > + I am NOT an MPI application author either > + I am a developer of "competing" HPC communications software (GASNet)