Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] Joe Griffin: "Re: Cannot compile on LinuxItanium system"
From: Jeff Squyres (jsquyres_at_[hidden])
Date: 2009-02-01 06:41:49

I'm afraid I don't have access to any Itaniums, so debugging this will
be difficult.

The source file between OMPI v1.2 and OMPI v1.3 should be the same.
So *something* is different between the two. Can one of you examine
the output of "make" to determine what is different?

- check the specific compile command for the two versions:
   - see if any different assemblers/flags/etc. flags are being used
   - verify that the same file is being compiled (please also check
these files with diff to ensure that they really are the same)
- check the output of the compile after the preprocessor has been
applied (probably via the -E switch to the specific compiler/assembler
command) and see if there are differences in what is actually being

On Jan 29, 2009, at 2:32 PM, Joe Griffin wrote:

> Tony,
> I had tried just the compile line using –O0, but it did not help.
> The last
> assembly I actually wrote was for a Cray Y-MP I think, so I don’t
> intend on
> delving into that.
> Sorry I couldn’t be more help.
> I do have access to what I call a Frankenstein Cluster of Itaniums
> ( different
> manufactures and different OS’s) to support our clients, so I don’t
> mind
> testing.
> Sorry I could not help,
> Joe
> From: users-bounces_at_[hidden] [mailto:users-bounces_at_[hidden]]
> On Behalf Of Iannetti, Anthony C. (GRC-RTB0)
> Sent: Thursday, January 29, 2009 11:22 AM
> To: Open MPI Users
> Subject: Re: [OMPI users] Joe Griffin: "Re: Cannot compile on
> LinuxItanium system"
> Joe,
> Intel recommends to set all of the compile flags, like CCFLAGS, to
> -O2. Other than than, we are doing nothing different than what
> Intel recommends.
> When I set CCAS=ias, ./configure does not make it through the
> Assembler stage.
> When I set CCAS=ias and CASFLAGS= (I am setting it to nothing), it
> makes it through the Assembler config stage and fails at another
> point in make. I will send another email with the actual errors. I
> thought I would relay this information to you,
> Tony
> Anthony C. Iannetti, P.E.
> NASA Glenn Research Center
> Aeropropulsion Division, Combustion Branch
> 21000 Brookpark Road, MS 5-10
> Cleveland, OH 44135
> phone: (216)433-5586
> email: Anthony.C.Iannetti_at_[hidden]
> Please note: All opinions expressed in this message are my own and
> NOT of NASA. Only the NASA Administrator can speak on behalf of NASA.
> _______________________________________________
> users mailing list
> users_at_[hidden]

Jeff Squyres
Cisco Systems