[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Gomp-discuss] Start of an OpenMP Implementation Spec
From: |
Lars Segerlund |
Subject: |
Re: [Gomp-discuss] Start of an OpenMP Implementation Spec |
Date: |
Thu, 26 Aug 2004 18:15:55 +0200 |
Well I did hack in the dummy lib, but no one even commented, so I dropped it.
If we had the library interface down we could make libraries for different
configurations, thus supporting NUMA ( threads ), MPI, PVM and so on .
A small MPI cluster is really cheap, perhaps $100 per node if you use cheap
motherboards with onboard gigabit lan and sempron CPU's or similar, thus I'm
still pushing for support for clusters in addition to threading since the
differences are easily overcome.
I can do some library work, and I can have a look at gfortran, I haven't had
any time to do something worthwhile on it for a while, but I figure we can hook
into the part of the parser dealing with comments , and do the dirty work at
gimplification time , ( processing into something usefull later ).
The point is, we have plenty of work to do, and large parts of it can be done
NOW independent of eachother.
I will read the ompspec and comment, but I hope we can start to do something.
/ regards, Lars Segerlund.
On Thu, 26 Aug 2004 16:45:25 +0200
Biagio Lucini <address@hidden> wrote:
> On Thursday 26 August 2004 00.22, Ross Towle wrote:
> > Looking for comments. Is anybody interested in moving GOMP forward?
> >
>
> Hi Ross,
>
> many thanks for your letter and welcome among us. I think we *all* are
> interested in moving gomp forward. The problem is that the project has big
> pushes when new and enthusiast members like you join it, but they won't last
> a forthnight. What we really need is someone who says "look: I'm here, ready
> to hack something" or better "I did this and that: what do you think"?
> Discussing theoretical proposals so far has brought us nowhere.
>
> Going into the specific, your note looks fine with me, although it is not
> clear to me whether you want to do a rewriting of the code and then a
> gimplification or if the operations you describe apply to the middle end.
>
> Hope you can lead us somewhere :-)
>
> Cheers
> Biagio
>
> --
> =========================================================
>
> Biagio Lucini
> Institut Fuer Theoretische Physik
> ETH Hoenggerberg
> CH-8093 Zuerich - Switzerland
> Tel. +41 (0)1 6332562
>
> =========================================================
>
>
> _______________________________________________
> Gomp-discuss mailing list
> address@hidden
> http://lists.nongnu.org/mailman/listinfo/gomp-discuss
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, (continued)
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Biagio Lucini, 2004/08/26
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Scott Robert Ladd, 2004/08/26
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Biagio Lucini, 2004/08/26
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Scott Robert Ladd, 2004/08/26
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Lars Segerlund, 2004/08/26
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Diego Novillo, 2004/08/26
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Lars Segerlund, 2004/08/26
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Scott Robert Ladd, 2004/08/26
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Ross Towle, 2004/08/30
- Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Ross Towle, 2004/08/30
Re: [Gomp-discuss] Start of an OpenMP Implementation Spec,
Lars Segerlund <=
Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Ross Towle, 2004/08/30
Re: [Gomp-discuss] Start of an OpenMP Implementation Spec, Lars Segerlund, 2004/08/26