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=0.4 required=5.0 tests=BAYES_00,FORGED_MUA_MOZILLA
	autolearn=no autolearn_force=no version=3.4.4
X-Google-Thread: 103376,a32653cf595422e6
X-Google-NewGroupId: yes
X-Google-Attributes: gida07f3367d7,domainid0,public,usenet
X-Google-Language: ENGLISH,ASCII-7-bit
Received: by 10.68.202.37 with SMTP id kf5mr5383151pbc.7.1334920652999;
        Fri, 20 Apr 2012 04:17:32 -0700 (PDT)
Path: 
 r9ni77796pbh.0!nntp.google.com!news1.google.com!feed-C.news.volia.net!volia.net!news2.volia.net!feed-A.news.volia.net!news.musoftware.de!wum.musoftware.de!feeder.erje.net!news.internetdienste.de!news.tu-darmstadt.de!news.belwue.de!newsfeed.arcor.de!newsspool2.arcor-online.net!news.arcor.de.POSTED!not-for-mail
Date: Fri, 20 Apr 2012 13:17:09 +0200
From: Georg Bauhaus <rm.dash-bauhaus@futureapps.de>
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.7;
 rv:11.0) Gecko/20120327 Thunderbird/11.0.1
MIME-Version: 1.0
Newsgroups: comp.lang.ada
Subject: Re: GNAT and register allocation
References: <4f9138c2$0$6628$9b4e6d93@newsspool2.arcor-online.net>
In-Reply-To: <4f9138c2$0$6628$9b4e6d93@newsspool2.arcor-online.net>
Message-ID: <4f9145b5$0$6557$9b4e6d93@newsspool4.arcor-online.net>
Organization: Arcor
NNTP-Posting-Date: 20 Apr 2012 13:17:09 CEST
NNTP-Posting-Host: 78cb456f.newsspool4.arcor-online.net
X-Trace: 
 DXC=g]]Ro`c^ObG[6=1B@oB@@@4IUK<Cl32<A4Fo<]lROoRA8kF<OcfhCOKhn@@Y2U:<lNPCY\c7>ejVHPHZYW8\gm6G\Kkcg]4m[eG
X-Complaints-To: usenet-abuse@arcor.de
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Date: 2012-04-20T13:17:09+02:00
List-Id: <comp.lang.ada>

On 20.04.12 12:21, Georg Bauhaus wrote:
> Hi,
>
> in short, is there anything that one can do to make
> GNAT use many registers? MMX registers in particular,
> but not only.

SSE, that is, darn, the registers being named xmmN.

> It appears that the number of registers allocated increases
> with inline expansion enabled. But only so much.

In the (meaningless) example below, the translations of both
Comp.A and Comp.B will use the same set of registers, xmm0 .. xmm1.
If they were instead using xmm0 .. xmm1 and xmm2 .. xmm3,
respectively, speed might well double.


package Comp is

    type F is digits 15;

    function A (One, Two : F) return F;
    function B (One, Two : F) return F;

end Comp;

package body Comp is

    function A (One, Two : F) return F is
       X, Y, Z: F;
    begin
       X := One - 1.0;
       Y := Two / 3.14;
       Z := 2.0 * X + Y;
       return Z * Z;
    end A;

    function B (One, Two : F) return F is
       X, Y, Z: F;
    begin
       X := One + 1.0;
       Y := Two  * (1.0 / 3.14);
       Z := X + 2.0 * Y;
       return (Z * Z) / 3.0;
    end B;

    function Use_Them (Start : F) return F is
       Ra, Rb : F;
    begin
       Ra := Start;
       Rb := 0.0 - Start;
       for K in 1 .. 1_000_000 loop
          Ra := A (Ra, Rb);
          Rb := B (Ra, Rb);
       end loop;
       return (Ra + Rb) / 2.0;
    end Use_Them;

    Result : F;
    pragma Volatile (Result);
begin
    if Result'Valid then
       Result := Use_Them (Result);
    else
       raise Constraint_Error;
    end if;
end Comp;