05.02.2013 Views

ARM Architecture Reference Manual ARMv7-A and ARMv7-R edition

ARM Architecture Reference Manual ARMv7-A and ARMv7-R edition

ARM Architecture Reference Manual ARMv7-A and ARMv7-R edition

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Square root, bits [23:20]<br />

Divide, bits [19:16]<br />

The CPUID Identification Scheme<br />

Indicates the hardware support for VFP square root operations. Permitted values are:<br />

0b0000 Not supported in hardware.<br />

0b0001 Supported.<br />

Note<br />

the FSQRTS instruction also requires the single-precision VFP attribute, bits [7:4]<br />

the FSQRTD instruction also requires the double-precision VFP attribute, bits [11:8].<br />

Indicates the hardware support for VFP divide operations. Permitted values are:<br />

0b0000 Not supported in hardware.<br />

0b0001 Supported.<br />

Note<br />

VFP exception trapping, bits [15:12]<br />

the FDIVS instruction also requires the single-precision VFP attribute, bits [7:4]<br />

the FDIVD instruction also requires the double-precision VFP attribute, bits [11:8].<br />

Indicates whether the VFP hardware implementation supports exception trapping.<br />

Permitted values are:<br />

0b0000 Not supported. This is the value for VFPv3.<br />

0b0001 Supported by the hardware. This is the value for VFPv3U, <strong>and</strong> for VFPv2.<br />

When exception trapping is supported, support code is needed to h<strong>and</strong>le the<br />

trapped exceptions.<br />

Note<br />

This value does not indicate that trapped exception h<strong>and</strong>ling is available.<br />

Because trapped exception h<strong>and</strong>ling requires support code, only the support<br />

code can provide this information.<br />

Double-precision, bits [11:8]<br />

Indicates the hardware support for VFP double-precision operations. Permitted values are:<br />

0b0000 Not supported in hardware.<br />

0b0001 Supported, VFPv2.<br />

0b0010 Supported, VFPv3.<br />

VFPv3 adds an instruction to load a double-precision floating-point constant,<br />

<strong>and</strong> conversions between double-precision <strong>and</strong> fixed-point values.<br />

<strong>ARM</strong> DDI 0406B Copyright © 1996-1998, 2000, 2004-2008 <strong>ARM</strong> Limited. All rights reserved. B5-37

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!