<?xml version="1.0" encoding="utf-8"?>

<!-- Copyright (c) 2007-2010 Nokia Corporation and/or its subsidiary(-ies) All rights reserved. -->

<!-- This component and the accompanying materials are made available under the terms of the License 

"Eclipse Public License v1.0" which accompanies this distribution, 

and is available at the URL "http://www.eclipse.org/legal/epl-v10.html". -->

<!-- Initial Contributors:

    Nokia Corporation - initial contribution.

Contributors: 

-->

<!DOCTYPE concept

  PUBLIC "-//OASIS//DTD DITA Concept//EN" "concept.dtd">

<concept id="GUID-5E358AB4-03A7-5859-ABF2-A8B64B74AF56" xml:lang="en"><title>Vector

Floating Point Architecture (VFP)</title><shortdesc>Describes the implementation of the ARM Vector Floating Point Architecture

(VFPv2) on Symbian platform. </shortdesc><prolog><metadata><keywords/></metadata></prolog><conbody>

<p>ARM provide a hardware floating point coprocessor that provides floating

point computation that is fully compliant with IEEE Std 754-1985.We refer

to the coprocessor as the <i>VFP unit</i>. </p>

<p>Symbian platform supports the use of VFPv2 on platforms where the required

hardware is present in both <i>RunFast</i> mode and in <i>IEEE-without-exceptions</i> mode.

See ARM's Vector Floating-point Coprocessor Technical reference Manual for

more details on the coprocessor, its architecture, and its execution modes. </p>

<p>You should read the information in <xref href="GUID-D525B9A9-6B32-535B-A282-60C85A48D3FB.dita">Floating

point support</xref> about applications and user side code as this is also

applicable to code running on the kernel side. However there are a number

of restrictions that must be observed: </p>

<ul>

<li id="GUID-2205026D-0E6F-54AE-B74F-5478D6047B70"><p>You <i>cannot</i> use

VFP instructions in any interrupt service routine. </p> </li>

<li id="GUID-C8D896E1-CF36-52CD-A984-61D7A8189268"><p>You <i>cannot</i> use

VFP instructions when the kernel is locked, for example, in an IDFC or after

calling <xref href="GUID-3A3C08F3-3D33-3D9E-80E7-7855C7B21E02.dita#GUID-3A3C08F3-3D33-3D9E-80E7-7855C7B21E02/GUID-7CBBF72B-4519-38DD-92CA-38AF636AFD8A"><apiname>NKern::Lock()</apiname></xref>  </p> </li>

<li id="GUID-A7466A83-A8F2-58CE-AB8B-E05607BB6D95"><p>You <i>cannot</i> use

VFP instructions in any section of code which runs with a fast mutex held. </p> </li>

</ul>

<p>Using VFP instructions in these situations can lead to data being corrupted,

or the kernel panicking. If you rely on the compiler to generate VFP instructions,

rather than using inline assembler, it is extremely important that you do

not use any floating point values in these situations. The compiler may generate

VFP instructions for the most trivial floating point operations and even for

simple assignments. </p>

</conbody></concept>