This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: [gomp4] Preserve NVPTX "reconvergence" points

From: Nathan Sidwell <nathan at codesourcery dot com>
To: Bernd Schmidt <bernds at codesourcery dot com>, Jakub Jelinek <jakub at redhat dot com>, Julian Brown <julian at codesourcery dot com>
Cc: Thomas Schwinge <thomas at codesourcery dot com>, <gcc-patches at gcc dot gnu dot org>
Date: Mon, 22 Jun 2015 12:08:36 -0400
Subject: Re: [gomp4] Preserve NVPTX "reconvergence" points
Authentication-results: sourceware.org; auth=none
References: <20150528150635 dot 7bd5db23 at octopus> <20150528142011 dot GN10247 at tucnak dot redhat dot com> <87pp5kg3js dot fsf at schwinge dot name> <20150528150802 dot GO10247 at tucnak dot redhat dot com> <5583E68A dot 9020608 at codesourcery dot com> <20150619122557 dot GO10247 at tucnak dot redhat dot com> <20150622145549 dot 481d4549 at octopus> <20150622142456 dot GZ10247 at tucnak dot redhat dot com> <5588273C dot 60109 at codesourcery dot com>

On 06/22/15 11:18, Bernd Schmidt wrote:

You can have a hint that it is desirable, but not a hint that it is correct
(because passes in between may invalidate that). The OpenACC directives
guarantee to the compiler that the program can be transformed into a parallel
form. If we lose them early we must then rely on our analysis which may not be
strong enough to prove that the loop can be parallelized. If we make these
transformations early enough, while we still have the OpenACC directives, we can
guarantee that we do exactly what the programmer specified.

How does this differ from openmp's needs to preserve parallelism on a parallelloop? Is it more than the reconvergence issue?


nathan

--
Nathan Sidwell

Follow-Ups:
- Re: [gomp4] Preserve NVPTX "reconvergence" points
  - From: Jakub Jelinek

References:
- Re: [gomp4] Preserve NVPTX "reconvergence" points
  - From: Bernd Schmidt
- Re: [gomp4] Preserve NVPTX "reconvergence" points
  - From: Jakub Jelinek
- Re: [gomp4] Preserve NVPTX "reconvergence" points
  - From: Julian Brown
- Re: [gomp4] Preserve NVPTX "reconvergence" points
  - From: Jakub Jelinek
- Re: [gomp4] Preserve NVPTX "reconvergence" points
  - From: Bernd Schmidt

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]