From mint-bounce@lists.fishpool.fi  Mon Jun 14 11:17:07 2010
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=gmail.com; s=gamma;
        h=domainkey-signature:received:received:sender:message-id:date:from
         :user-agent:mime-version:to:subject:references:in-reply-to
         :content-type:content-transfer-encoding;
        bh=q0BP1OxHPafGLMM8aXFRD+hVkgHztUPJ91N35G6Q6PE=;
        b=h0nEbftsUFTswGsvd97CDJ5vlvAz01pGttz+8HInKjxumOk2ewFI6DjjJWFpglljkn
         5+p46Leuqf1s4NRcvqtDFp6UOc4UKeCfDbyMKBiKnIsh0O5tm4zdShpEw+o95IFMZAPQ
         kNQbHdi6Jg2uFLV1gl65FhC5nGbElwFx3IwOE=
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=sender:message-id:date:from:user-agent:mime-version:to:subject
         :references:in-reply-to:content-type:content-transfer-encoding;
        b=SoOeGIKYIq+ShwWEVe4f9R3cH6t4Uy9DslEr7Q0iirwKrwSN6MKOprlIxcZWTmjgPU
         0kt9ejmdzK1Wgamv38FXallec3swzeMg5rIb8XQ+PytnWE38qxNG47RMYtTNq2VzNGW8
         E9Mzcz2ucx51ixDB0oNEDerE+u5IkOQDquFCs=
Message-ID: <4C16472E.20003@freesbee.fr>
Date: Mon, 14 Jun 2010 17:13:50 +0200
From: =?ISO-8859-1?Q?Vincent_Rivi=E8re?= <vincent.riviere@freesbee.fr>
User-Agent: Thunderbird 2.0.0.24 (Windows/20100228)
MIME-Version: 1.0
To: mint <mint@lists.fishpool.fi>
Subject: Re: [MiNT] Libcurl-ssl / RPM package
References: <ed8542bdc154dd7693c8d3210c31d89b-EhVcX1lFRQVaRwYcDTpQCEFddQZLVF5dQUBFBDBTXF5bVkYOWkF0A1w6XF1YR0AAWlhfQw==-webmailer2@server08.webmailer.hosteurope.de> <4C163DF4.9060102@freesbee.fr> <845495def3bc16e5a0fcba375627015b-EhVcX1lFRQVaRwYcDTpQCEFddQZLVF5dQUBFBDBTXF5bVkYOWkF0A1w6XF1YR0AAWF9bSA==-webmailer2@server08.webmailer.hosteurope.de>
In-Reply-To: <845495def3bc16e5a0fcba375627015b-EhVcX1lFRQVaRwYcDTpQCEFddQZLVF5dQUBFBDBTXF5bVkYOWkF0A1w6XF1YR0AAWF9bSA==-webmailer2@server08.webmailer.hosteurope.de>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 8bit
X-ecartis-version: Ecartis v1.0.0
Sender: mint-bounce@lists.fishpool.fi
Errors-to: mint-bounce@lists.fishpool.fi
X-original-sender: vincent.riviere@freesbee.fr
Precedence: bulk
List-help: <mailto:ecartis@lists.fishpool.fi?Subject=help>
List-unsubscribe: <mailto:mint-request@lists.fishpool.fi?Subject=unsubscribe>
List-Id: <mint.lists.fishpool.fi>
X-List-ID: <mint.lists.fishpool.fi>
List-subscribe: <mailto:mint-request@lists.fishpool.fi?Subject=subscribe>
List-owner: <mailto:tjhukkan@fishpool.fi>
List-post: <mailto:mint@lists.fishpool.fi>

m0n0 a écrit :
> That mean's when compiling for -m68020, the FPU is completly ignored, too.
> Right?  

On GCC 2.x, -m68020 means 68020 without FPU.
On GCC 4.x, -m68020 means 68020 with a mandatory FPU.
This is a difference.

And I highly recommend to compile any FPU software with -m68020-60 since 
this is the option we have chosen for standard multilibs.

> I know that an FPU can speed up floating point operations dramatically,
> and floating point math is involved alot in encryption / decryption - as
> far as I know. 

The problem with floating point is the fact it is imprecise by design: 
there are rounding errors. Most of times, it doesn't matter because they 
are extremely small.
But encryption/decryption software needs to be 100% accurate. I suspect 
these algorithms to use integer math only.
Well, I don't know.

> Anyone here has numbers regarding the speedup when using the FPU? I would
> at least expect values like 100% speed inprovement ;)  But maybe I'm
> totally wrong? 

For standard software: no gain.
For math/3D software: huge gain.

-- 
Vincent Rivière