Visible to Intel only — GUID: shd1506201174145
Ixiasoft
Visible to Intel only — GUID: shd1506201174145
Ixiasoft
6. Nios II Floating Point Hardware 2 Component
The FPH2 component provides low cycle count implementations of add, sub, multiply, and divide operations, and custom instruction implementations of additional floating point operations.
The FPH2 component is the preferred floating point implementation for the Nios II processor. Intel recommends FPH2 rather than the legacy FPH1 because it provides better performance and a smaller device footprint.
You should compile newlib from source code with individual –mcustom-<operation> options, selected to match your hardware configuration. This allows newlib to incorporate the benefits of all FPH2 operations that can be inferred by GCC. If you use the Nios II software build tools, the BSP generator takes care of this for you.
Section Content
Overview of the Floating Point Hardware 2 Component
Floating Point Hardware 2 IEEE 754 Compliance
IEEE 754 Exception Conditions with FPH2
Floating Point Hardware 2 Operations
Building the FPH2 Example Hardware
Building the FPH2 Example Software
FPH2 Implementation of GCC Options
Nios II FPH2 and the Newlib Library
C Macros for round(), fmins(), and fmaxs()