From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 11458 invoked by alias); 14 Oct 2009 14:57:00 -0000 Received: (qmail 11448 invoked by uid 22791); 14 Oct 2009 14:57:00 -0000 X-SWARE-Spam-Status: No, hits=-2.5 required=5.0 tests=AWL,BAYES_00,SPF_PASS X-Spam-Check-By: sourceware.org Received: from mail.codesourcery.com (HELO mail.codesourcery.com) (38.113.113.100) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Wed, 14 Oct 2009 14:56:53 +0000 Received: (qmail 23490 invoked from network); 14 Oct 2009 14:56:51 -0000 Received: from unknown (HELO orlando) (pedro@127.0.0.2) by mail.codesourcery.com with ESMTPA; 14 Oct 2009 14:56:51 -0000 From: Pedro Alves To: gdb@sourceware.org, Tom Tromey Subject: Re: MPI debugging support in GDB? Date: Wed, 14 Oct 2009 14:57:00 -0000 User-Agent: KMail/1.9.10 Cc: =?iso-8859-1?q?S=E9rgio_Durigan_J=FAnior?= , Daniel Qarras References: <521289.91772.qm@web36804.mail.mud.yahoo.com> <200910140127.49609.sergiodj@linux.vnet.ibm.com> In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Message-Id: <200910141556.54381.pedro@codesourcery.com> X-IsSubscribed: yes Mailing-List: contact gdb-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: gdb-owner@sourceware.org X-SW-Source: 2009-10/txt/msg00257.txt.bz2 On Wednesday 14 October 2009 15:40:45, Tom Tromey wrote: > >>>>> "S=E9rgio" =3D=3D S=E9rgio Durigan J=FAnior writes: >=20 > Tom> I haven't heard of anybody working on MPI support for GDB. >=20 > S=E9rgio> Last year, I was starting a work in order to implement such a > S=E9rgio> support on GDB. However, due to internal reasons, I had to quit > S=E9rgio> this and start another task. Unfortunately, I only spent a few > S=E9rgio> days studying MPI and did not have the chance to create an > S=E9rgio> opinion about how difficult it would be to make GDB support it. >=20 > If you know, could you say something about what kind of support would be > needed? Even that would help a bit, I think. I think that for full and transparent support, we'd need to start with being able to debug multiple (remote) targets simultaneously? GDB can't do that currently --- it can only debug multiple processes running on the same host. --=20 Pedro Alves