From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:52261)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <Leon.Alrae@imgtec.com>) id 1YLEUw-0001gL-Gm
	for qemu-devel@nongnu.org; Tue, 10 Feb 2015 12:21:19 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <Leon.Alrae@imgtec.com>) id 1YLEUr-0007BI-E2
	for qemu-devel@nongnu.org; Tue, 10 Feb 2015 12:21:18 -0500
Received: from mailapp01.imgtec.com ([195.59.15.196]:5282)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <Leon.Alrae@imgtec.com>) id 1YLEUr-0007Ax-6D
	for qemu-devel@nongnu.org; Tue, 10 Feb 2015 12:21:13 -0500
Message-ID: <54DA3E03.5050808@imgtec.com>
Date: Tue, 10 Feb 2015 17:21:07 +0000
From: Leon Alrae <leon.alrae@imgtec.com>
MIME-Version: 1.0
References: <alpine.DEB.1.10.1412081805400.19155@tp.orcam.me.uk>
	<alpine.DEB.1.10.1412082308490.19155@tp.orcam.me.uk>
	<54D8EA12.3030004@imgtec.com>
	<alpine.LFD.2.11.1502092008040.22715@eddie.linux-mips.org>
	<54D9E116.9060201@imgtec.com>
	<alpine.LFD.2.11.1502101402540.22715@eddie.linux-mips.org>
In-Reply-To: <alpine.LFD.2.11.1502101402540.22715@eddie.linux-mips.org>
Content-Type: text/plain; charset="ISO-8859-1"
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [PATCH 7/7] target-mips: Add IEEE 754-2008
	features support
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: "Maciej W. Rozycki" <macro@linux-mips.org>
Cc: qemu-devel@nongnu.org, Aurelien Jarno <aurelien@aurel32.net>, Thomas Schwinge <thomas@codesourcery.com>

On 10/02/2015 14:30, Maciej W. Rozycki wrote:
> On Tue, 10 Feb 2015, Leon Alrae wrote:
> 
>>>  These cases could be addressed by either replacing subtraction from 0.0 
>>> with multiplication by -1.0, or by tweaking the rounding mode as needed 
>>> temporarily.  Given that the computational cost of multiplication is 
>>> uncertain and likely higher or at best the same as the cost of addition or 
>>> subtraction, I'd be leaning towards the latter solution.
>>
>> My first thought was to treat zero in NEG.fmt as a special case and use
>> float32_chs() for it. But tweaking the rounding mode temporarily
>> probably is better as we will get consistent behaviour for zero as well
>> as input denormals which are squashed in float32_sub() when
>> flush_inputs_to_zero flag is set (actually I'm not sure if legacy fp
>> instructions should flush input denormals, but according to the spec
>> this is implementation dependent so I won't worry about this).
> 
>  As expected setting CP1.FCSR.FS on a randomly picked R4400 processor:
> 
> CPU0 revision is: 00000440 (R4400SC)
> FPU revision is: 00000500
> 
> does flush a NEG.fmt's input denormal to 0.  Given this program:

Good to know, thanks for checking that on the real CPU!

Leon