<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=us-ascii">
<STYLE type=text/css>DIV {
MARGIN: 0px
}
</STYLE>
<META content="MSHTML 6.00.6000.16608" name=GENERATOR></HEAD>
<BODY>
<DIV dir=ltr align=left><SPAN class=346034120-20032008><FONT face=Arial
color=#0000ff size=2>Hi,</FONT></SPAN></DIV>
<DIV dir=ltr align=left><SPAN class=346034120-20032008><FONT face=Arial
color=#0000ff size=2> The fortran bindings for MPI funcs is in
src/binding/f77 (Note that these source files are generated by
scripts).</FONT></SPAN></DIV>
<DIV><FONT face=Arial color=#0000ff size=2></FONT> </DIV>
<DIV><SPAN class=346034120-20032008><FONT face=Arial color=#0000ff
size=2>Regards,</FONT></SPAN></DIV>
<DIV><SPAN class=346034120-20032008><FONT face=Arial color=#0000ff
size=2>Jayesh</FONT></SPAN></DIV><BR>
<DIV class=OutlookMessageHeader lang=en-us dir=ltr align=left>
<HR tabIndex=-1>
<FONT face=Tahoma size=2><B>From:</B> owner-mpich-discuss@mcs.anl.gov
[mailto:owner-mpich-discuss@mcs.anl.gov] <B>On Behalf Of </B>trymelz
trymelz<BR><B>Sent:</B> Thursday, March 20, 2008 3:38 PM<BR><B>To:</B>
mpich-discuss@mcs.anl.gov<BR><B>Subject:</B> Re: [mpich-discuss] exit code
-1073741819<BR></FONT><BR></DIV>
<DIV></DIV>
<DIV
style="FONT-SIZE: 12pt; FONT-FAMILY: times new roman, new york, times, serif">
<P>Hi, </P>
<P> </P>
<P>By specifying character length as 11, the program behaviors the same as 15
since the order of arguments is messed up. </P>
<P> </P>
<P>Do you know where is the protype or definition in the source code of
MPI_SEND/RECV? Thanks.</P>
<P> </P>
<P> </P>
<P>Linfa</P>
<DIV
style="FONT-SIZE: 12pt; FONT-FAMILY: times new roman, new york, times, serif"><BR><BR>
<DIV
style="FONT-SIZE: 12pt; FONT-FAMILY: times new roman, new york, times, serif">-----
Original Message ----<BR>From: Anthony Chan <chan@mcs.anl.gov><BR>To:
mpich-discuss@mcs.anl.gov<BR>Cc: Jayesh Krishna
<jayesh@mcs.anl.gov><BR>Sent: Thursday, March 20, 2008 2:33:51
PM<BR>Subject: Re: [mpich-discuss] exit code -1073741819<BR><BR><BR>What happens
if you specify character length as 11 instead of 15 in<BR>your MPI_Sned and
MPI_Recv ?<BR><BR>On Thu, 20 Mar 2008, trymelz trymelz wrote:<BR><BR>>
Hi,<BR>><BR>> Sure. After changing the calling convention to default in
Intel Compiler, I successfully linked with fmpich2.lib. But again, it runs fine
when the string length is passed at the end of argument list, and it crashes
when the string length is passed after the string pointer.<BR>><BR>>
Probably, more MPICH2 FORTRAN libraries are needed to be
provided.<BR>><BR>> Linfa<BR>><BR>> ----- Original Message
----<BR>> From: Jayesh Krishna <<A href="mailto:jayesh@mcs.anl.gov"
ymailto="mailto:jayesh@mcs.anl.gov">jayesh@mcs.anl.gov</A>><BR>> To:
trymelz trymelz <<A href="mailto:trymelz@yahoo.com"
ymailto="mailto:trymelz@yahoo.com">trymelz@yahoo.com</A>><BR>> Cc: <A
href="mailto:mpich-discuss@mcs.anl.gov"
ymailto="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</A><BR>>
Sent: Thursday, March 20, 2008 2:08:46 PM<BR>> Subject: RE: [mpich-discuss]
exit code -1073741819<BR>><BR>><BR>> Hi,<BR>> Can you also try
compiling your program with fmpich2.lib ?<BR>><BR>> Regards,<BR>>
Jayesh<BR>><BR>><BR>><BR>> From: trymelz trymelz [mailto:<A
href="mailto:trymelz@yahoo.com"
ymailto="mailto:trymelz@yahoo.com">trymelz@yahoo.com</A>]<BR>> Sent:
Thursday, March 20, 2008 2:06 PM<BR>> To: Jayesh Krishna; <A
href="mailto:mpich-discuss@mcs.anl.gov"
ymailto="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</A><BR>>
Subject: Re: [mpich-discuss] exit code -1073741819<BR>><BR>><BR>>
Hi<BR>><BR>> I have no problem to compile & run the sample fpi.f using
fmpich2s.lib. Actually, I have identified the culprit: MPI_SEND/RECV work find
with integer, but have problem with string.<BR>><BR>> The main reason I
beleive is that, in Fortran, different compiler treats the string arguments
differently: either add the string length as a invisible argument immediately
after the string pointer, or the string lengh is added as a invisible arguments
at the end of arguments list. So in my understanding MPI_SEND/RECV will have 28
byte of arguments for integer, but 32 byte of arguments for string because the
invisible string length argument.<BR>><BR>> It will cause crash if the
positions of the invisible string length arguments are different in the .obj
file and in fmpich2s.lib. The following program dimenstrate this<BR>><BR>>
program main<BR>> implicit none<BR>> #include <mpif.h><BR>>
integer status(MPI_STATUS_SIZE)<BR>> character * 15 pcomand<BR>> integer
MYID,mpimodbg,ierr<BR>> ierr=MPI_SUCCESS<BR>> call MPI_INIT(ierr)<BR>>
call MPI_COMM_RANK( MPI_COMM_WORLD, MYID, ierr )<BR>> if(MYID .eq.
1)then<BR>> mpimodbg=99<BR>> pcomand='hello world'<BR>> call
MPI_SEND(mpimodbg,1,MPI_INTEGER,0<BR>> * ,11,MPI_COMM_WORLD,ierr)<BR>>
write(*,*)'node',MYID,pcomand,mpimodbg<BR>> call
MPI_SEND(pcomand,15,MPI_CHARACTER,0<BR>> * ,11,MPI_COMM_WORLD,ierr)<BR>>
write(*,*)'node',MYID,pcomand,mpimodbg<BR>> elseif(MYID.eq.0)then<BR>>
mpimodbg=0<BR>> pcomand='hello'<BR>> call
MPI_RECV(mpimodbg,1,MPI_INTEGER,1<BR>> *
,11,MPI_COMM_WORLD,status,ierr)<BR>>
write(*,*)'node',MYID,pcomand,mpimodbg<BR>> call
MPI_RECV(pcomand,15,MPI_CHARACTER,1<BR>> *
,11,MPI_COMM_WORLD,status,ierr)<BR>>
write(*,*)'node',MYID,pcomand,mpimodbg<BR>> endif<BR>> call
MPI_FINALIZE(ierr)<BR>> end<BR>><BR>> When compiled with the string
length as a invisible argument immediately after the string pointer (by default
in Intel Compiler):<BR>><BR>> $ "/cygdrive/c/Program
Files/MPICH2/bin/mpiexec.exe" -n 3 ./Debug/fortestargs.exe<BR>> node
0 hello
99<BR>> node 1
hello world 99<BR>> forrtl:
severe (157): Program Exception - access violation<BR>> Image
PC Routine
Line
Source<BR>> fmpich2s.dll 1000507F Unknown
Unknown Unknown<BR>>
fortestargs.exe 004A783D Unknown
Unknown Unknown<BR>> fortestargs.exe
0044AA53 Unknown
Unknown Unknown<BR>> fortestargs.exe 0044A81D
Unknown Unknown
Unknown<BR>> kernel32.dll 7C816FD7 Unknown
Unknown Unknown<BR>> forrtl:
severe (157): Program Exception - access violation<BR>> Image
PC Routine
Line
Source<BR>> fmpich2s.dll 1000492B Unknown
Unknown Unknown<BR>>
fortestargs.exe 004A783D Unknown
Unknown Unknown<BR>> fortestargs.exe
0044AA53 Unknown
Unknown Unknown<BR>> fortestargs.exe 0044A81D
Unknown Unknown
Unknown<BR>> kernel32.dll 7C816FD7 Unknown
Unknown Unknown<BR>> job
aborted:<BR>> rank: node: exit code[: error message]<BR>> 0: abyss: 157:
process 0 exited without calling finalize<BR>> 1: abyss: 157: process 1
exited without calling finalize<BR>> 2: abyss: 123<BR>><BR>> When
compiled with the string length as a invisible argument at the end of arguments
list:<BR>><BR>> $ "/cygdrive/c/Program Files/MPICH2/bin/mpiexec.exe" -n 3
./Debug/fortestargs.exe<BR>><BR>> node 1
hello world 99<BR>>
node 1 hello world
99<BR>> node 0
hello
99<BR>> node 0 hello world
99<BR>><BR>><BR>> Thanks all
for your help.<BR>><BR>> Linfa<BR>><BR>><BR>> ----- Original
Message ----<BR>> From: Jayesh Krishna <<A
href="mailto:jayesh@mcs.anl.gov"
ymailto="mailto:jayesh@mcs.anl.gov">jayesh@mcs.anl.gov</A>><BR>> To:
trymelz trymelz <<A href="mailto:trymelz@yahoo.com"
ymailto="mailto:trymelz@yahoo.com">trymelz@yahoo.com</A>><BR>> Cc: <A
href="mailto:mpich-discuss@mcs.anl.gov"
ymailto="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</A><BR>>
Sent: Thursday, March 20, 2008 9:15:21 AM<BR>> Subject: RE: [mpich-discuss]
exit code -1073741819<BR>><BR>><BR>> Hi,<BR>> Can you
compile & run the sample fpi.f (provided in MPICH2\examples in your
installation dir) using fmpich2s.lib ?<BR>><BR>> Regards,<BR>>
Jayesh<BR>><BR>><BR>><BR>><BR>> From: <A
href="mailto:owner-mpich-discuss@mcs.anl.gov"
ymailto="mailto:owner-mpich-discuss@mcs.anl.gov">owner-mpich-discuss@mcs.anl.gov</A>
[mailto:<A href="mailto:owner-mpich-discuss@mcs.anl.gov"
ymailto="mailto:owner-mpich-discuss@mcs.anl.gov">owner-mpich-discuss@mcs.anl.gov</A>]
On Behalf Of trymelz trymelz<BR>> Sent: Wednesday, March 19, 2008 6:30
PM<BR>> To: <A href="mailto:mpich-discuss@mcs.anl.gov"
ymailto="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</A><BR>>
Subject: Re: [mpich-discuss] exit code -1073741819<BR>><BR>><BR>>
Hi<BR>><BR>> The MPI program is too big to be sent. Here is what I got
from the debugger<BR>><BR>> Before calling PMPI_ISEND:<BR>> Symbol
Value Type<BR>> buf(1) 3 INTEGER(4)<BR>> cnt 1
INTEGER(4)<BR>> datatype 1275069467 INTEGER(4)<BR>> dest 0
INTEGER(4)<BR>> tag 24 INTEGER(4)<BR>> comm 1140850688
INTEGER(4)<BR>> reqs(1) 1243468 INTEGER(4)<BR>> ierr 0
INTEGER(4)<BR>><BR>> call
PMPI_ISEND(buf,cnt,datatype,dest,tag,comm,reqs(1),ierr)<BR>><BR>>
Unhandled exception at 0x003b41c9 in EXEC.exe:0xC0000005:<BR>> Access
violation writing location 0x00000000<BR>><BR>> After the break at the
crash, all the arguments becomes "undefined address".<BR>><BR>> When I
check the library, I got<BR>> $ nm fmpich2s.lib | grep MPI_SEND@<BR>>
00000000 T _MPI_SEND@28<BR>> 00000000 I __imp__MPI_SEND@28<BR>> 00000000 T
_MPI_SEND@32<BR>> 00000000 I __imp__MPI_SEND@32<BR>> 00000000 T
_PMPI_SEND@28<BR>> 00000000 I __imp__PMPI_SEND@28<BR>> 00000000 T
_PMPI_SEND@32<BR>> 00000000 I __imp__PMPI_SEND@32<BR>><BR>> I am
wondering why there are two definitions: _MPI_SEND@28 and
_MPI_SEND@32. And I could not find corresponding source code for
_MPI_SEND@32. Any comments? Thanks.<BR>><BR>>
Linfa<BR>><BR>><BR>><BR>> ----- Original Message ----<BR>> From:
Jayesh Krishna <<A href="mailto:jayesh@mcs.anl.gov"
ymailto="mailto:jayesh@mcs.anl.gov">jayesh@mcs.anl.gov</A>><BR>> To:
trymelz trymelz <<A href="mailto:trymelz@yahoo.com"
ymailto="mailto:trymelz@yahoo.com">trymelz@yahoo.com</A>><BR>> Cc: <A
href="mailto:mpich-discuss@mcs.anl.gov"
ymailto="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</A><BR>>
Sent: Wednesday, March 19, 2008 2:32:59 PM<BR>> Subject: RE: [mpich-discuss]
exit code -1073741819<BR>><BR>><BR>> Hi,<BR>> Can you send us your
MPI program ?<BR>> You can also try to debug your program by setting the
error handler to MPI_ERRORS_RETURN (MPI_Comm_set_errhandler() ) & using
MPI_Error_string() to get the description of the error code.<BR>><BR>>
Regards,<BR>> Jayesh<BR>><BR>><BR>><BR>><BR>> From: <A
href="mailto:owner-mpich-discuss@mcs.anl.gov"
ymailto="mailto:owner-mpich-discuss@mcs.anl.gov">owner-mpich-discuss@mcs.anl.gov</A>
[mailto:<A href="mailto:owner-mpich-discuss@mcs.anl.gov"
ymailto="mailto:owner-mpich-discuss@mcs.anl.gov">owner-mpich-discuss@mcs.anl.gov</A>]
On Behalf Of trymelz trymelz<BR>> Sent: Wednesday, March 19, 2008 2:11
PM<BR>> To: <A href="mailto:mpich-discuss@mcs.anl.gov"
ymailto="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</A><BR>>
Subject: [mpich-discuss] exit code -1073741819<BR>><BR>><BR>> Hi
all,<BR>><BR>> I got an strange error when I run my parallel
program.<BR>><BR>> job aborted:<BR>> rank: node: exit code[: error
message]<BR>> 0: abyss: -1073741819: process 0 exited without calling
finalize<BR>> 1: abyss: -1073741819: process 1 exited without calling
finalize<BR>> 2: abyss: -1073741819: process 2 exited without calling
finalize<BR>><BR>> My program works as expected under Linux. But when I
porting it to windows I got above error. It is compiled by VC8 and Intel FORTRAN
10.0.<BR>> I didn't built my own MPICH2, but link my program with
fmpich2s.lib and mpi.lib which were installed from
mpich2-1.0.6p1-win32-ia32.msi.<BR>><BR>> This error happened inside the
call to MPI_SEND. Does anyone have an idea about this
error?<BR>><BR>><BR>> Linfa<BR>><BR>><BR>><BR>> Be a better
friend, newshound, and know-it-all with Yahoo! Mobile. Try it
now.<BR>><BR>><BR>><BR>><BR>><BR>> Looking for last minute
shopping deals? Find them fast with Yahoo!
Search.<BR>><BR>><BR>><BR>><BR>><BR>> Looking for last minute
shopping deals? Find them fast with Yahoo! Search.<BR>><BR>><BR>>
____________________________________________________________________________________<BR>>
Looking for last minute shopping deals?<BR>> Find them fast with Yahoo!
Search. <A
href="http://tools.search.yahoo.com/newsearch/category.php?category=shopping"
target=_blank>http://tools.search.yahoo.com/newsearch/category.php?category=shopping</A><BR><BR></DIV><BR></DIV></DIV><BR>
<HR SIZE=1>
Be a better friend, newshound, and know-it-all with Yahoo! Mobile. <A
href="http://us.rd.yahoo.com/evt=51733/*http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ ">Try
it now.</A></BODY></HTML>