Intel® MPI Library
Get help with building, analyzing, optimizing, and scaling high-performance computing (HPC) applications.
2241 Discussions

MPI program intermittently crashes

Matt_Rinella
Beginner
245 Views

Below I've provided the MPI part of the program, the debugging information I get when the program fails, and the versions of Visual Studio and the one API and HPC toolkits I'm using.  A sincere thanks in advance for any help.

     
do k=1,5000
     if(proc.eq.0)then
          do i=2,nprocs
                call MPI_SEND(xp(i,1:d),d,MPI_real,i-1,1,MPI_COMM_WORLD,ierr)
           enddo
     else
          call MPI_recv(xp(1,1:d),d,MPI_real,0,1,MPI_COMM_WORLD, MPI_STATUS_IGNORE,ierr)
     endif

     call call_hydrus(proc,xp(1,1:d),d,ndata,convergevec(1),sse(1))

     If(proc.ne.0)then
          call MPI_SEND(sse(1),1,MPI_real,0,2,MPI_COMM_WORLD,ierr)
     else
          do i=2,nprocs
               call MPI_recv(sse(i),1,MPI_real,i-1,2,MPI_COMM_WORLD, MPI_STATUS_IGNORE,ierr)
          enddo
     endif
enddo


!****************************************************************************************
subroutine call_hydrus(proc,pars,d,ndata,convergeq,sse)
implicit none
integer :: ndata,d,i,proc
real :: pars(d),sse
logical :: convergeq
CHARACTER(100) :: filenumberstring

write(filenumberstring, '(I5)') proc

open(30,file=Trim("selector"//trim(adjustl(filenumberstring))//".in"),status='old',action='read')
open(32,file=Trim("profile"//trim(adjustl(filenumberstring))//".dat"),status='old',action='read')
open(31,file=Trim("ATMOSPH"//trim(adjustl(filenumberstring))//".in"),status='old',action='read')
open(666,file=Trim("tdr"//trim(adjustl(filenumberstring))//".in"),status='old',action='read')


!this subroutine calls several other subroutines written in fortran 77
call hydrus(proc,pars,sse,convergeq,ndata)

close(30)
close(31)
close(32)
close(666)
end
!****************************************************************************************

 

 

'mpiexec.exe' (Win32): Loaded 'C:\Program Files (x86)\Intel\oneAPI\mpi\2021.8.0\bin\mpiexec.exe'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\ntdll.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\kernel32.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\KernelBase.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\ws2_32.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\rpcrt4.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\crypt32.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\ucrtbase.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\bcrypt.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\secur32.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\mswsock.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\advapi32.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\mpr.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\msvcrt.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\sechost.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\IPHLPAPI.DLL'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\ntdsapi.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\sspicli.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\dsparse.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\NapiNSP.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\bcryptprimitives.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\pnrpnsp.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\dnsapi.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\nsi.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\winrnr.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\wshbth.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\nlansp_c.dll'.
'mpiexec.exe' (Win32): Loaded 'C:\Windows\System32\msvcp_win.dll'.
onecore\net\netprofiles\service\src\nsp\dll\namespaceserviceprovider.cpp(613)\nlansp_c.dll!00007FFB645AF6CD: (caller: 00007FFB7131ACF6) LogHr(1) tid(afe0) 8007277C No such service is known. The service cannot be found in the specified name space.
onecore\net\netprofiles\service\src\nsp\dll\namespaceserviceprovider.cpp(613)\nlansp_c.dll!00007FFB645AF6CD: (caller: 00007FFB7131ACF6) LogHr(2) tid(afe0) 8007277C No such service is known. The service cannot be found in the specified name space.
onecore\net\netprofiles\service\src\nsp\dll\namespaceserviceprovider.cpp(613)\nlansp_c.dll!00007FFB645AF6CD: (caller: 00007FFB7131ACF6) LogHr(3) tid(afe0) 8007277C No such service is known. The service cannot be found in the specified name space.
'mpiexec.exe' (Win32): Unloaded 'C:\Windows\System32\NapiNSP.dll'
'mpiexec.exe' (Win32): Unloaded 'C:\Windows\System32\pnrpnsp.dll'
'mpiexec.exe' (Win32): Unloaded 'C:\Windows\System32\winrnr.dll'
'mpiexec.exe' (Win32): Unloaded 'C:\Windows\System32\wshbth.dll'
'mpiexec.exe' (Win32): Unloaded 'C:\Windows\System32\msvcp_win.dll'
'mpiexec.exe' (Win32): Unloaded 'C:\Windows\System32\nlansp_c.dll'
The thread 0xb55c has exited with code -1 (0xffffffff).
The thread 0x93f8 has exited with code -1 (0xffffffff).
The thread 0x6e4c has exited with code -1 (0xffffffff).
The thread 0x8b44 has exited with code -1 (0xffffffff).
The thread 0x9fc8 has exited with code -1 (0xffffffff).
The program '[42104] mpiexec.exe' has exited with code -1 (0xffffffff).

 

Microsoft Visual Studio Community 2019
Version 16.11.17

 

Product: Intel® oneAPI Base & HPC Toolkit (Single-Node)
Serial Number 1: C6VB-4H4H55R2
SKU: ABS999OSGE01X1Z - Intel® oneAPI Base & HPC Toolkit (Single-Node) - Named-user Commercial (ESD)
Vendor: Climb Channel Solutions
Version: 2022
Quantity: 1
Support Period End: 2023-02-06
Order Number: IRC:414043 T20925690101 X04757840101

 

 

 

0 Kudos
1 Reply
TobiasK
Moderator
134 Views

@Matt_Rinella please consider contacting priority support to share more details on your code and the failure. With the information you provided here, we are not able to help you.

0 Kudos
Reply