From mboxrd@z Thu Jan  1 00:00:00 1970
X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on polar.synack.me
X-Spam-Level: 
X-Spam-Status: No, score=-0.9 required=5.0 tests=BAYES_00,FORGED_GMAIL_RCVD,
	FREEMAIL_FROM autolearn=no autolearn_force=no version=3.4.4
X-Google-Thread: 103376,c08aa0f01f894da6
X-Google-NewGroupId: yes
X-Google-Attributes: gida07f3367d7,domainid0,public,usenet
X-Google-Language: ENGLISH,ASCII
Path: 
 g2news2.google.com!postnews.google.com!h38g2000pro.googlegroups.com!not-for-mail
From: Anatoly Chernyshev <achernyshev@gmail.com>
Newsgroups: comp.lang.ada
Subject: Re: GPUs and CUDA
Date: Mon, 11 Jul 2011 22:59:54 -0700 (PDT)
Organization: http://groups.google.com
Message-ID: 
 <c09e6d8e-662e-4670-ae2e-0ad2fea99081@h38g2000pro.googlegroups.com>
References: 
 <09ad3bbb-b0a3-438b-9263-b2cb49098e5c@glegroupsg2000goo.googlegroups.com>
 <iv8381$l44$1@speranza.aioe.org>
 <bf681a4d-d0d1-4bcc-95b4-b336fe469009@ct4g2000vbb.googlegroups.com>
 <4e1b4333$0$6583$9b4e6d93@newsspool3.arcor-online.net>
NNTP-Posting-Host: 212.72.17.30
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-Trace: posting.google.com 1310451321 25980 127.0.0.1 (12 Jul 2011 06:15:21
 GMT)
X-Complaints-To: groups-abuse@google.com
NNTP-Posting-Date: Tue, 12 Jul 2011 06:15:21 +0000 (UTC)
Complaints-To: groups-abuse@google.com
Injection-Info: h38g2000pro.googlegroups.com; posting-host=212.72.17.30;
 posting-account=g6PEmwoAAADhFsmVm6Epjviaw4MLU0b5
User-Agent: G2/1.0
X-HTTP-Via: 1.1 porxy.unizwa.edu.om:80 (IronPort-WSA/7.1.1-027)
X-Google-Web-Client: true
X-Google-Header-Order: NKUALESRCHV
X-HTTP-UserAgent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.2.13)
 Gecko/20101203 Firefox/3.6.13,gzip(gfe)
Xref: g2news2.google.com comp.lang.ada:21146
Date: 2011-07-11T22:59:54-07:00
List-Id: <comp.lang.ada>

On Jul 11, 10:38=A0pm, Georg Bauhaus <rm.dash-bauh...@futureapps.de>
wrote:
> Wouldn't a multicore PC with additional Graphics processors be
> a candidate for an Ada 2012 Ravenscar multicore runtime?

I'm not sure about that, taking into account that Ada's original
purpose is embedded systems, which are often missing GPUs whatsoever.
Yet, I believe, GPU's cores are not quite the same as CPU's, even in
terms of synchronization and communication.

>Err... I think "binding" is perhaps a horrid idea. (Raise your hand if
>you just want a light wrapper around C-headers.)
>The way to go, IMO, is to allow a specialized pragma to indicate to
>the compiler that such and such subprogram is intended for
>distribution to the GPUs for parallel work.

>This would allow something like
> Pragma CUDA( Ralph );

I guess, in this particular case, the binding or port is better. The
suggested pragma makes the language (or at least compiler) hardware-
dependend, which I, personally, would hate to see. Yet, the IT's
hardware sector is much more agile than Ada's standards, so that today
we have CUDA, and tomorrow it will be replaced by who-knows-what...