[mpich-discuss] Error when compiling with mpif90
Brandt Belson
bbelson at princeton.edu
Fri Feb 11 10:38:57 CST 2011
Thanks for your reply. To answer your questions, I configured MPICH2 to use
gfortran (v 4.5.1). I am compiling with the newly installed mpif90, not the
original
which mpif90
/usr/local/mpich2/bin/mpif90
not /usr/bin/mpif90, which gives a different error message about not
supporting fortran.
The output from using show is:
/usr/local/bin/gfortran -c bla.f -mcmodel=large -I/usr/local/mpich2/include
-L/usr/local/mpich2/lib -cpp -I/usr/local/mpich2/include
-I/usr/local/mpich2/include
And just to repeat, the compiler error messages are below.
/var/folders/zz/zzzivhrRnAmviuee++2ZO++-7KU/-Tmp-//ccsWDdv3.s:23533:junk
`@PLTOFF' after expression
/var/folders/zz/zzzivhrRnAmviuee++2ZO++-7KU/-Tmp-//ccsWDdv3.s:23537:junk
`@GOTOFF' after expression
Thanks for your help!
Brandt
On Fri, Feb 11, 2011 at 2:35 AM, <mpich-discuss-request at mcs.anl.gov> wrote:
> Send mpich-discuss mailing list submissions to
> mpich-discuss at mcs.anl.gov
>
> To subscribe or unsubscribe via the World Wide Web, visit
> https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss
> or, via email, send a message with subject or body 'help' to
> mpich-discuss-request at mcs.anl.gov
>
> You can reach the person managing the list at
> mpich-discuss-owner at mcs.anl.gov
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of mpich-discuss digest..."
>
>
> Today's Topics:
>
> 1. Re: Error when compiling with mpif90 (Dave Goodell)
> 2. Re: problem when installing MPICH2 (Rajeev Thakur)
> 3. Re: MPICH 2 on Window 7 home premium (Koh Voon Li)
> 4. Re: Problem with spawning child with same executable name
> (Yauheni Zelenko)
> 5. Strange MPI_Recv error (Xiao Li)
> 6. Re: Strange MPI_Recv error (Xiao Li)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Thu, 10 Feb 2011 12:35:08 -0600
> From: Dave Goodell <goodell at mcs.anl.gov>
> Subject: Re: [mpich-discuss] Error when compiling with mpif90
> To: mpich-discuss at mcs.anl.gov
> Message-ID: <C92F4176-7680-48BD-ADB7-D8AC30FB16F0 at mcs.anl.gov>
> Content-Type: text/plain; charset=us-ascii
>
> What Fortran compiler are you using? Is your application compiled with
> "mpif90"? Are you sure that it's the MPICH2 mpif90 script and not the one
> from the system-installed Open MPI in /usr/bin/mpif90?
>
> Those error messages are strange. I think that indicate your compiler is
> producing assembly code that contains ELF-specific code, even though Darwin
> uses the Mach-O binary format. What adding "-show" to your failing mpif90
> compile command yield?
>
> -Dave
>
> On Feb 9, 2011, at 10:54 PM CST, Brandt Belson wrote:
>
> > Hello,
> > I'm a relatively new user of MPICH2. I installed it and tried to compile
> a fortran code on mac OS 10.6. The code has compiled on linux machines
> before with other MPI libraries. I configured with:
> >
> > ./configure --enable-sharedlibs=osx-gcc --prefix=/usr/local/mpich2
> --enable-f77 --enable-fx --enable-shared
> >
> > The installation seemed to go well, I installed to /usr/local/mpich2 and
> set my PATH and LD_LIBRARY_PATH variables to match this. When compiling, I
> also included the folder with -I/usr/local/mpich2/include. However, I get
> this strange looking (at least to me) error message.
> >
> > /var/folders/zz/zzzivhrRnAmviuee++2ZO++-7KU/-Tmp-//ccVkj3hf.s:595:junk
> `@PLTOFF' after expression
> > /var/folders/zz/zzzivhrRnAmviuee++2ZO++-7KU/-Tmp-//ccVkj3hf.s:608:junk
> `@GOTOFF' after expression
> > (many more of the same thing)
> > make: *** [bla.o] Error 1
> >
> > I tried restarting my computer thinking there might be temporary files
> that would be deleted, but I got the same error. Has anyone else had a
> similar problem and found a solution?
> >
> > Thanks,
> > Brandt
> >
> > _______________________________________________
> > mpich-discuss mailing list
> > mpich-discuss at mcs.anl.gov
> > https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss
>
>
>
> ------------------------------
>
> Message: 2
> Date: Thu, 10 Feb 2011 13:08:22 -0600
> From: Rajeev Thakur <thakur at mcs.anl.gov>
> Subject: Re: [mpich-discuss] problem when installing MPICH2
> To: mpich-discuss at mcs.anl.gov
> Message-ID: <3241C92E-E89E-46C6-B9E2-D62A9DE54962 at mcs.anl.gov>
> Content-Type: text/plain; charset=us-ascii
>
> Make sure there is no firewall preventing the two machines from
> communicating with each other.
>
> Rajeev
>
> On Feb 10, 2011, at 9:06 AM, Faiza Khali wrote:
>
> > Hello;
> > My name is Bouamra. I have Installing the Mpich2-1.3.2 package on my
> Computers; But I have a problem when executing the MPI. I have 2 Pcs Dell
> Dual core (OPTIPLEX 380). I send you the message when I execute the mpiexec.
> Can you Help me?
> > Best Regards
> >
> > <mpich2 message error.odt>_______________________________________________
> > mpich-discuss mailing list
> > mpich-discuss at mcs.anl.gov
> > https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss
>
>
>
> ------------------------------
>
> Message: 3
> Date: Fri, 11 Feb 2011 09:59:38 +0800
> From: Koh Voon Li <kohvoonli at gmail.com>
> Subject: Re: [mpich-discuss] MPICH 2 on Window 7 home premium
> To: Jayesh Krishna <jayesh at mcs.anl.gov>
> Cc: mpich-discuss at mcs.anl.gov
> Message-ID:
> <AANLkTinTncomqtajazbuhmSN7a8YjXLoVG1Jpxq6zm03 at mail.gmail.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> Yes. I able registered on both machine. But when I tried to just launch
> simply command I got error message as stated below:
>
> C:\>mpiexec -hosts 2 WIN7-PC 1 user-PC 1 "c:\program
> files\fds\fds5\bin\fds5_mpi
> _win_64.exe"
> abort: Unable to connect to user-PC
>
> For your information, I have turned off both Window firewall. But still
> failed to launch any job.
>
> On Thu, Feb 10, 2011 at 11:52 PM, Jayesh Krishna <jayesh at mcs.anl.gov>
> wrote:
>
> > Hi,
> > Is the username/password valid on the second machine (Do you have the
> same
> > Windows username/password on the second machine ? )? If so, you should be
> > able to run your job. Are you able to run your job now ?
> > Registration of username/password is local to the machine. MPICH2 does
> not
> > automatically register the same username on all the nodes. If you would
> like
> > to register username/password on each machine you should register the
> > credentials on each (Type "mpiexec -register" on each). However, to
> launch
> > your job you need to have the username/password registered only on the
> > machine/node where you launch your job.
> > Let us know the results.
> >
> > Regards,
> > Jayesh
> >
> > ----- Original Message -----
> > From: "Koh Voon Li" <kohvoonli at gmail.com>
> > To: "Jayesh Krishna" <jayesh at mcs.anl.gov>
> > Sent: Thursday, February 10, 2011 9:30:16 AM
> > Subject: Re: MPICH 2 on Window 7 home premium
> >
> > Hi,
> >
> > Thanks for the reply. I was able to registered 2 username on 1 of my
> > computer, but I got error message on my 2nd computer when I try to
> validate
> > user on it.
> >
> > Here is the error message.
> > FAIL: Unable to read the credentials from the registry.
> >
> > Thanks,
> >
> > Regards,
> > KOH
> >
> >
> >
> > On Thu, Feb 10, 2011 at 10:10 PM, Jayesh Krishna < jayesh at mcs.anl.gov >
> > wrote:
> >
> >
> > Hi,
> >
> >
> > >> Credentials for USER-PC\WIN 7 rejected connecting to user-PC
> > >> Aborting: Unable to connect to user-PC
> >
> > From the error message it looks like you haven't registered a valid
> > username/password with mpiexec. Please register a valid Windows
> > username/password with mpiexec using the "-register" option (Type
> "mpiexec
> > -register" at the command prompt and mpiexec will prompt you for the
> > username/password). Once the registration is complete validate it using
> the
> > "-validate" option (Type "mpiexec -validate" at the command prompt). If
> you
> > have registered a valid Windows username/password the validate option
> should
> > return SUCCESS.
> > Let us know the results.
> >
> > Regards,
> > Jayesh
> >
> >
> > ----- Original Message -----
> > From: "Koh Voon Li" < kohvoonli at gmail.com >
> >
> > To: jayesh at mcs.anl.gov
> >
> >
> >
> > Sent: Thursday, February 10, 2011 2:59:35 AM
> > Subject: Fwd: MPICH 2 on Window 7 home premium
> >
> >
> > Hi Jayesh,
> >
> > Sorry for bothering. Attached here is the smpd log in debug mode.
> > Million Thanks.
> >
> >
> > Regards,
> > KOH
> >
> >
> >
> > ---------- Forwarded message ----------
> > From: Koh Voon Li < kohvoonli at gmail.com >
> > Date: Thu, Feb 10, 2011 at 3:30 PM
> > Subject: MPICH 2 on Window 7 home premium
> > To: jayesh at mcs.anl.gov
> >
> >
> > Hi Jayesh,
> >
> >
> > I am trying to running parallel FDS (Fire Dynamic Simulator) via 2 PC by
> > using a config file
> >
> >
> > here is my config file
> >
> > exe "C:\Program Files\FDS\FDS5\bin\fds5_mpi_win_64.exe"
> "ParadigmV4-13.fds"
> > wdir "\\USER-PC\Project\Paradigm\"
> > hosts
> > user-PC 6
> > WIN7-PC 6
> >
> >
> > This is the error message I got from the command prompt.
> >
> > C:\>mpiexec -file config.txt
> > Credentials for USER-PC\WIN 7 rejected connecting to user-PC
> > Aborting: Unable to connect to user-PC
> >
> >
> > I used a cross over cable to connect both PCs and I think my setting for
> > the IP address is correct as I can ping each other computer in the
> command
> > prompt.
> > I tried to turned off both firewall but it failed.
> > Thanks,
> >
> >
> > Regards,
> > Koh
> >
> >
> >
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20110211/bf620fe6/attachment-0001.htm
> >
>
> ------------------------------
>
> Message: 4
> Date: Thu, 10 Feb 2011 18:41:59 -0800
> From: Yauheni Zelenko <zelenko at cadence.com>
> Subject: Re: [mpich-discuss] Problem with spawning child with same
> executable name
> To: "mpich-discuss at mcs.anl.gov" <mpich-discuss at mcs.anl.gov>
> Message-ID:
> <
> E990625543463A44A740F9148BB8C1E6077A6FE388 at MAILSJ3.global.cadence.com>
>
> Content-Type: text/plain; charset="us-ascii"
>
> Hi, Pavan!
>
> I added some debugging output with timestamps.
>
> New set of children spawned after previous set of children call
> MPI_Finalize. However all processes exited only after mater terminated.
>
> I definitely could lead to more resource usage in supposed program usage
> since children still some amount of system resources.
>
> Also I'm not sure that at this stage Hydra will have enough information to
> launch new child processes on freed hosts.
>
> Eugene.
> ________________________________________
> From: Pavan Balaji [balaji at mcs.anl.gov]
> Sent: Wednesday, February 09, 2011 2:31 PM
> To: Yauheni Zelenko
> Cc: mpich-discuss at mcs.anl.gov
> Subject: Re: [mpich-discuss] Problem with spawning child with same
> executable name
>
> So the first set of spawned processes have terminated before the next set
> is started, is it?
>
> Pavan Balaji @ iPhone
> (Big fingers. Small email.)
>
> On Feb 9, 2011, at 2:20 PM, Yauheni Zelenko <zelenko at cadence.com> wrote:
>
> > But there is still living process on host1. I think accounting fact this
> will be more correct Hydra behaviour.
> >
> > Eugene.
> > ________________________________________
> > From: Pavan Balaji [balaji at mcs.anl.gov]
> > Sent: Wednesday, February 09, 2011 2:11 PM
> > To: mpich-discuss at mcs.anl.gov
> > Cc: Yauheni Zelenko
> > Subject: Re: [mpich-discuss] Problem with spawning child with same
> executable name
> >
> > On 02/09/2011 04:06 PM, Yauheni Zelenko wrote:
> >> Then I run program with Hydra: mpiexec -host "host1:2,host2:2"
> >>
> >> Master process is run on host1. At first spawn 1 child was run on
> >> host1 and 2 on host2, but on consequent spawns, 2 children was on
> >> host1 and 1 on host2.
> >>
> >> I think such resources allocation may create balancing problems and
> >> Hydra should not spawn children processes on hosts still in use.
> >
> > That sound correct to me. Hydra looks at the host list as:
> >
> > host1, host1, host2, host2, ..., [wrap around].
> >
> > The master process is launched on the first "host1". When you spawn
> > three processes the first time, it launches them on "host1", "host2",
> > and "host2". When you spawn three processes the second time, it launches
> > them on "host1", "host1", "host2". The next spawn of three processes
> > will be "host2", "host1", "host1", etc.
> >
> > -- Pavan
> >
> > --
> > Pavan Balaji
> > http://www.mcs.anl.gov/~balaji
> -------------- next part --------------
> A non-text attachment was scrubbed...
> Name: Spawn.c
> Type: application/octet-stream
> Size: 2696 bytes
> Desc: Spawn.c
> URL: <
> http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20110210/65abc774/attachment-0001.obj
> >
>
> ------------------------------
>
> Message: 5
> Date: Fri, 11 Feb 2011 00:59:26 -0500
> From: Xiao Li <shinelee.thewise at gmail.com>
> Subject: [mpich-discuss] Strange MPI_Recv error
> To: mpich-discuss at mcs.anl.gov
> Message-ID:
> <AANLkTikDQLNX0ZLs7wCD5g0b7bWWhfJ_NW_e=cVv3hBC at mail.gmail.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> Hi,
>
> I use a small MPI program and get the following error.
>
> Fatal error in MPI_Recv: Other MPI error, error stack:
> > MPI_Recv(186)........................: MPI_Recv(buf=0012FA20, count=1,
> > MPI_INT,
> > src=MPI_ANY_SOURCE, tag=5, MPI_COMM_WORLD, status=0012FA80) failed
> > MPIDI_CH3I_Progress(335).............:
> > MPID_nem_mpich2_blocking_recv(906)...:
> > MPID_nem_newtcp_module_poll(37)......:
> > MPID_nem_newtcp_module_connpoll(2655):
> > gen_read_fail_handler(1145)..........: read from socket failed - The
> > specified network name is no longer available.
>
>
> The code framework is something like this below.
>
> if rank == 0
> {
> for iter=1 to N
> MPI_Recv any
> get proc rank from status
> MPI_Send proc
> end
> }
> else
> {
> for iter=1 to N
> MPI_Send to 0
> MPI_Recv from 0
> do some computation here
> end
> }
>
> I do check my code carefully. And I even rewrite the core computation code
> in a series way. Then I get no error. Even more strange is that the code
> will crash at different for loop iteration. I suspect the MPI can not work
> in my network environment. The network is composed by four Windows XP
> machines with 100/mbps Ethernet network. Would you help me on this issue?
>
> cheers
> Xiao
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20110211/a2cafa3e/attachment.htm
> >
>
> ------------------------------
>
> Message: 6
> Date: Fri, 11 Feb 2011 01:14:49 -0500
> From: Xiao Li <shinelee.thewise at gmail.com>
> Subject: Re: [mpich-discuss] Strange MPI_Recv error
> To: mpich-discuss at mcs.anl.gov
> Message-ID:
> <AANLkTi=PpHN9Cput+pzQh0brA4ATP4yQ5TCFTre32yjJ at mail.gmail.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> PS:
>
> When the code error is reported at iteration n, if I restart the program at
> iteration n-1, then everything goes fine for several iteration rounds.
> Then,
> the error occurs again.
>
> On Fri, Feb 11, 2011 at 12:59 AM, Xiao Li <shinelee.thewise at gmail.com
> >wrote:
>
> > Hi,
> >
> > I use a small MPI program and get the following error.
> >
> > Fatal error in MPI_Recv: Other MPI error, error stack:
> >> MPI_Recv(186)........................: MPI_Recv(buf=0012FA20, count=1,
> >> MPI_INT,
> >> src=MPI_ANY_SOURCE, tag=5, MPI_COMM_WORLD, status=0012FA80) failed
> >> MPIDI_CH3I_Progress(335).............:
> >> MPID_nem_mpich2_blocking_recv(906)...:
> >> MPID_nem_newtcp_module_poll(37)......:
> >> MPID_nem_newtcp_module_connpoll(2655):
> >> gen_read_fail_handler(1145)..........: read from socket failed - The
> >> specified network name is no longer available.
> >
> >
> > The code framework is something like this below.
> >
> > if rank == 0
> > {
> > for iter=1 to N
> > MPI_Recv any
> > get proc rank from status
> > MPI_Send proc
> > end
> > }
> > else
> > {
> > for iter=1 to N
> > MPI_Send to 0
> > MPI_Recv from 0
> > do some computation here
> > end
> > }
> >
> > I do check my code carefully. And I even rewrite the core computation
> code
> > in a series way. Then I get no error. Even more strange is that the code
> > will crash at different for loop iteration. I suspect the MPI can not
> work
> > in my network environment. The network is composed by four Windows XP
> > machines with 100/mbps Ethernet network. Would you help me on this issue?
> >
> > cheers
> > Xiao
> >
> >
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20110211/9c14b206/attachment.htm
> >
>
> ------------------------------
>
> _______________________________________________
> mpich-discuss mailing list
> mpich-discuss at mcs.anl.gov
> https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss
>
>
> End of mpich-discuss Digest, Vol 29, Issue 29
> *********************************************
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20110211/e4f941ec/attachment-0001.htm>
More information about the mpich-discuss
mailing list