Vector Floating Point (VFP)

Vector Floating Point (VFP) coprocessor support is an architecture option. The VFP architecture supports single and double precision floating point arithmetic, and is fully IEEE 754 compliant with suitable software library support. The VFP architecture also includes a fully deterministic ‘Run fast Mode’.Provision of a hardware floating point is essential for many applications, and can be used as part of a SoC design flow using technical computing tools (eg MatLab® and MATRIXx®) to directly model the system and derive the application code. The vector processing capability of the ARM VFP can be used to increase performance of imaging applications such as scaling, 2D and 3D transforms, font generation, and digital filters.ARM currently has VFP support for the ARM9™, ARM10™ and ARM11™ processor families: VFP9-S™ and VFP10™. Additional VFP options, VFPv3, were introduced with the ARMv7 architecture.