Re: [OMPI users] [EXTERNAL] Re: problem building 32-bit openmpi-1.9a1r27979 with Sun C

2013-01-30 Thread George Bosilca
On Wed, Jan 30, 2013 at 2:01 PM, Barrett, Brian W wrote: > As for the warnings about anachronisms, that I can't help on. This one is actually really funny. The function MPI_Register_datarep is defined in the mpi.c as {extern "C"}. As some of the arguments are pointers to function, they automatic

Re: [OMPI users] [EXTERNAL] Re: problem building 32-bit openmpi-1.9a1r27979 with Sun C

2013-01-30 Thread Barrett, Brian W
On 1/30/13 12:01 PM, "Barrett, Brian W" wrote: >Actually, the errors are in code that has changed. A couple weeks ago, we >removed the inline assembly support for C++, but I'm guessing not entirely >correctly. That is, I believe something is wrong in the #defines such >that opal_atomic_add_32 i

Re: [OMPI users] [EXTERNAL] Re: problem building 32-bit openmpi-1.9a1r27979 with Sun C

2013-01-30 Thread Barrett, Brian W
Actually, the errors are in code that has changed. A couple weeks ago, we removed the inline assembly support for C++, but I'm guessing not entirely correctly. That is, I believe something is wrong in the #defines such that opal_atomic_add_32 is being declared inline, but no inline body will be p

Re: [OMPI users] problem building 32-bit openmpi-1.9a1r27979 with Sun C

2013-01-30 Thread Jeff Squyres (jsquyres)
Weird. This particular code hasn't changed in a *long* time. Do you have successful oSUSE 12.1 and Sol x86_64 builds on this platform? On Jan 30, 2013, at 1:27 PM, Siegmar Gross wrote: > Hi > > today I tried to install openmpi-1.9a1r2797 on SunOS 10 Sparc, > SunOS 10 x86_64, and Linux x86_6

[OMPI users] problem building 32-bit openmpi-1.9a1r27979 with Sun C

2013-01-30 Thread Siegmar Gross
Hi today I tried to install openmpi-1.9a1r2797 on SunOS 10 Sparc, SunOS 10 x86_64, and Linux x86_64 with Sun C 5.12. I succeeded with all 64-bit systems and the 32-bit system on Solaris Sparc. On Linux (openSUSE 12.1) and Solaris x86_64 I got the following errors. tyr openmpi-1.9 245 tail openm

Re: [OMPI users] I have still a problem with rankfiles in openmpi-1.6.4rc3

2013-01-30 Thread Ralph Castain
Hmmmwell, it certainly works for me: [rhc@odin ~/v1.6]$ cat rf rank 0=odin093 slot=0:0-1,1:0-1 rank 1=odin094 slot=0:0-1 rank 2=odin094 slot=1:0 rank 3=odin094 slot=1:1 [rhc@odin ~/v1.6]$ mpirun -n 4 -rf ./rf --report-bindings -mca opal_paffinity_alone 0 hostname [odin093.cs.indiana.edu:046

Re: [OMPI users] Checkpointing an MPI application with OMPI

2013-01-30 Thread Maxime Boissonneault
Le 2013-01-29 21:02, Ralph Castain a écrit : On Jan 28, 2013, at 10:53 AM, Maxime Boissonneault > wrote: While our filesystem and management nodes are on UPS, our compute nodes are not. With one average generic (power/cooling mostly) failure ever

Re: [OMPI users] Checkpointing an MPI application with OMPI

2013-01-30 Thread Constantinos Makassikis
On Wed, Jan 30, 2013 at 3:02 AM, Ralph Castain wrote: > > If your node hardware is the problem, or you decide you do want/need to > pursue an FT solution, then you might look at the OMPI-based solutions from > parties such as http://fault-tolerance.org or the MPICH2 folks. > Just as Ralph said,

[OMPI users] I have still a problem with rankfiles in openmpi-1.6.4rc3

2013-01-30 Thread Siegmar Gross
Hi I applied your patch "rmaps.diff" to openmpi-1.6.4rc3r27923 and it works for my previous rankfile. > #3493: Handle the case where rankfile provides the allocation > ---+ > Reporter: rhc | Owner: jsquyres >