Programmer’s Reference

4.27Vector Floating Point, VFP9

The VFP9-S coprocessor is an implementation of the Vector Floating-point Architecture version 2 (VFPv2). It provides low-costfloating-point computation that is fully compliant with the ANSI/IEEE Std. 754-1985, IEEE Standard for Binary Floating-Point Arithmetic. The VFP9-S coprocessor supports all addressing modes described in section 5 of the ARM Architecture Reference Manual.

 

Table 4-76 VFP9 implementation

 

 

Property

Value

 

 

Location

ARM926EJ-S PXP Development Chip

 

 

Memory base address

The VFP registers are not memory-mapped. Access is from the

 

coprocessor instructions.

 

 

Interrupt

NA

 

 

DMA

NA

 

 

Release version

VFP9 r0p1

 

 

Reference documentation

ARM VFP9 Coprocessor Technical Reference Manual

 

 

Note

The following operations from the IEEE 754 standard are not supplied by the VFP9-S instruction set:

remainder

round floating-point number to integer-valued floating-point number

binary-to-decimal conversions

decimal-to-binary conversions

direct comparison of single-precision and double-precision values.

Complete implementation of the IEEE 754 standard is achieved by support code that is provided with the ARM compilation tools.

The latest VFP support code can be obtained as part of Application Note 98. If you are using RealView Compilation Tools (RVCT), the appropriate code and documentation are provided within your installation. If you are using the ARM Developer Suite (ADS) 1.2, Application Note 98 can be downloaded from www.arm.com/support/.

4-100

Copyright © 2003-2010 ARM Limited. All rights reserved.

ARM DUI 0224I

Page 266
Image 266
ARM ARM DUI 0224I manual Vector Floating Point, VFP9, 76 VFP9 implementation