Charm++ parallel programming system

[Gengbin Zheng <gzheng AT illinois.edu>]

yes, it is in the main branch.

Gengbin

On Mon, Feb 25, 2013 at 10:25 PM, Pavanakumar Mohanamuraly
<m.pavanakumar AT gmail.com>
 wrote:
> Thanks, will test it out,
>
> Is the script available from the git repo ?
>
>
> On Tue, Feb 26, 2013 at 3:16 AM, Gengbin Zheng 
> <gzheng AT illinois.edu>
>  wrote:
>>
>> ok, I added -print-prog-name= to be recognized by charmc. Let's see if
>> this helps.
>>
>> Gengbin
>>
>> On Mon, Feb 25, 2013 at 1:29 AM, Pavanakumar Mohanamuraly
>> <m.pavanakumar AT gmail.com>
>>  wrote:
>> > Thanks Zheng,
>> >
>> > 1) I ran the configure as follows
>> > "./configure
>> >
>> > CC='/home3/pavanakumar/Source/charm-6.4.0_net/net-linux-x86_64-ifort-smp-icc/bin/ampiCC
>> > -default-to-aout' --enable-parallel"
>> >
>> > 2) I can go past
>> > "checking whether the C compiler works... yes"
>> >
>> > 3) but it fails again in
>> > "checking for ld used by ....ampiCC -default-to-aout... no
>> > configure: error: no acceptable ld found in $PATH"
>> >
>> > 4) config.log says
>> > "configure:8346: checking for ld used by ampiCC -default-to-aout
>> > icpc: error #10236: File not found:  'moduleinit5309.o'
>> > configure:8416: result: no
>> > configure:8419: error: no acceptable ld found in $PATH"
>> >
>> > On Mon, Feb 25, 2013 at 12:44 PM, Gengbin Zheng 
>> > <gzheng AT illinois.edu>
>> > wrote:
>> >>
>> >> I don't think you should modify the generated configure file.
>> >> When running configure, pass "-default-to-aout" to charmc.
>> >>
>> >>
>> >> Gengbin
>> >>
>> >> On Mon, Feb 25, 2013 at 12:32 AM, Jain, Nikhil 
>> >> <nikhil AT illinois.edu>
>> >> wrote:
>> >> > You can make charmc pass this test by modifying the configure script:
>> >> >
>> >> > line 4553 onwards can be made to look like:
>> >> > ---**STARTING FILE LINES**--
>> >> >   case $ac_file in
>> >> >     conftest.o )
>> >> >         break;;
>> >> >     *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg
>> >> > |
>> >> > *.map | *.inf | *.dSYM | *.o | *.obj )
>> >> >         ;;
>> >> > --**ENDING FILE LINES**--
>> >> >
>> >> > Note the addition of conftest.o case for the switch.
>> >> >
>> >> > --Nikhil
>> >> >
>> >> >
>> >> >
>> >> > --
>> >> > Nikhil Jain, 
>> >> > nikhil AT illinois.edu,
>> >> > http://charm.cs.uiuc.edu/people/nikhil
>> >> > Doctoral Candidate @ CS, UIUC
>> >> >
>> >> >
>> >> >
>> >> > From: Pavanakumar Mohanamuraly 
>> >> > <m.pavanakumar AT gmail.com>
>> >> > Date: Monday, February 25, 2013 12:15 AM
>> >> > To: Nikhil Jain 
>> >> > <nikhil AT illinois.edu>
>> >> > Cc: "Kale, Laxmikant V" 
>> >> > <kale AT illinois.edu>,
>> >> >  
>> >> > "charm AT cs.illinois.edu"
>> >> > <charm AT cs.illinois.edu>
>> >> > Subject: Re: [charm] AMPI porting I/O issue
>> >> > Resent-From: Nikhil Jain 
>> >> > <nikhil AT illinois.edu>
>> >> > Resent-Date: Mon, 25 Feb 2013 00:15:33 -0600
>> >> >
>> >> > The problem is
>> >> >
>> >> > 1) "charmc" always puts the -c flag when -o is not specified. So when
>> >> > HDF5
>> >> > config script tries the -
>> >> >
>> >> > "Checking whether the C compiler works
>> >> > configure:4355:
>> >> > /home3/pavanakumar/Source/charm-6.4.0_net/net-linux-x86_64-ifort
>> >> > -smp-icc/bin/ampiCC -lmpi       conftest.c  >&5 "
>> >> >
>> >> > it creates conftest.o and not a.out ! So the configure fails.
>> >> >
>> >> > I am still figuring out how to change this behavior.
>> >> >
>> >> > On Thu, Feb 21, 2013 at 2:28 AM, Nikhil Jain 
>> >> > <nikhil AT illinois.edu>
>> >> > wrote:
>> >> >>
>> >> >> Hi Pavanakumar,
>> >> >>
>> >> >> Can you provide more details on compilation issues that you are
>> >> >> facing
>> >> >> in
>> >> >> building HDF5 with AMPI? I just tried building HDF5 with AMPI and
>> >> >> could
>> >> >> see
>> >> >> some of the issues that you might have encountered; however, with
>> >> >> some
>> >> >> tweaks to the build script/Makefile of HDF5, I think one can build
>> >> >> HDF5
>> >> >> with
>> >> >> AMPI.
>> >> >>
>> >> >> At the very least, I will mention that AMPI ships with a version of
>> >> >> ROMIO
>> >> >> that can be built by passing
>> >> >> --with-romio as a build flag. I just checked in a fix to handle a
>> >> >> scenario
>> >> >> that was earlier preventing this flag from being effective.
>> >> >>
>> >> >> --Nikhil
>> >> >>
>> >> >>
>> >> >> --
>> >> >> Nikhil Jain, 
>> >> >> nikhil AT illinois.edu,
>> >> >> http://charm.cs.uiuc.edu/people/nikhil
>> >> >> Doctoral Candidate @ CS, UIUC
>> >> >>
>> >> >>
>> >> >>
>> >> >> From: "Kale, Laxmikant V" 
>> >> >> <kale AT illinois.edu>
>> >> >> Date: Tuesday, February 19, 2013 12:53 PM
>> >> >> To: Nikhil Jain 
>> >> >> <nikhil AT illinois.edu>
>> >> >> Subject: FW: [charm] AMPI porting I/O issue
>> >> >> Resent-From: Nikhil Jain 
>> >> >> <nikhil AT illinois.edu>
>> >> >> Resent-Date: Tue, 19 Feb 2013 12:54:40 -0600
>> >> >>
>> >> >>
>> >> >> --
>> >> >> Laxmikant (Sanjay) Kale         http://charm.cs.uiuc.edu
>> >> >> Professor, Computer Science     
>> >> >> kale AT illinois.edu
>> >> >> 201 N. Goodwin Avenue           Ph:  (217) 244-0094
>> >> >> Urbana, IL  61801-2302          FAX: (217) 265-6582
>> >> >>
>> >> >> On 2/19/13 12:35 AM, "Pavanakumar Mohanamuraly"
>> >> >> <m.pavanakumar AT gmail.com>
>> >> >> wrote:
>> >> >>
>> >> >> Hi
>> >> >>
>> >> >> 1) I am porting one of our in-house CFD solver (MPI based) to AMPI.
>> >> >>
>> >> >> 2) The solver uses a single network mounted file for mesh and
>> >> >> solution
>> >> >> data
>> >> >>
>> >> >> 3) The individual MPI process (based on local decomposition
>> >> >> information)
>> >> >> read/write to this single file in parallel.
>> >> >>
>> >> >> 4) I am unable to successfully compile HDF5 library (v1.8.10-p1)
>> >> >> using
>> >> >> AMPI and hence cannot use the HDF5 file I/O
>> >> >>
>> >> >> Can someone suggest a work around ?
>> >> >>
>> >> >> Regards,
>> >> >>
>> >> >> --
>> >> >> Pavanakumar Mohanamuraly
>> >> >
>> >> >
>> >> >
>> >> >
>> >> > --
>> >> > Pavanakumar Mohanamuraly
>> >
>> >
>> >
>> >
>> > --
>> > Pavanakumar Mohanamuraly
>
>
>
>
> --
> Pavanakumar Mohanamuraly