[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: jaguar and mercurial

To: petsc-dev@xxxxxxxxxxx
Subject: Re: jaguar and mercurial
From: Richard Tran Mills <rmills@xxxxxxxx>
Date: Tue, 06 Nov 2007 17:30:17 -0500
Cc: Peter Lichtner <lichtner@xxxxxxxx>, Glenn Hammond <glenn.hammond@xxxxxxx>, Chuan Lu <clu@xxxxxxxx>
In-reply-to: <4730CBA3.1010104@ornl.gov>
References: <6B28845D-E765-41A0-8272-EC4CD7E54A27@lanl.gov> <4730CBA3.1010104@ornl.gov>
Reply-to: petsc-dev@xxxxxxxxxxx
Sender: owner-petsc-dev@xxxxxxxxxxx
User-agent: Thunderbird 2.0.0.6 (Macintosh/20070728)

The problem was that the PETSc configuration files didn't have PETSC_HAVE_F90_2PTR_ARG defined so the F90 interfaces weren't working correctly. I think this has been fixed for the 'cray-xt3-cnl_g' and 'cray-xt3-cnl_fast' architectures. I have to leave the office right now and I will recompile the other architectures tonight.

Give things a try and let me know if they are broken.

--Richard

Richard Tran Mills wrote:

PETSc has been built for CNL.  Use
  PETSC_DIR=/apps/PETSC/petsc-2.3.3-hg
  and PETSC_ARCH=cray-xt3-cnl_g (debugging) OR
                 cray-xt3-cnl_fast  (most aggressive optimization)
                 cray-xt3-cnl_O3    (-O3 optimization)
                 cray-xt3-cnl_O2    (-O2 optimization)
All of the example PETSc codes I have tried work, but PFLOW is dying with a seg fault on the simple THC example. I am currently trying to figure the problem.

References:
- Re: jaguar and mercurial
  - From: Richard Tran Mills

Prev by Date: Re: jaguar and mercurial
Next by Date: Re: adding SNESSetLinearSolve()
Previous by thread: Re: jaguar and mercurial
Next by thread: error checking macros with optimization
Index(es):
- Date
- Thread