Cortex-R DSP Software Library

Version2.0.0

Introduction

This user manual describes the Cortex-R DSP software library, a suite of common signal processing functions for use on Cortex-R4/Cortex-R5 processor based devices.

The library is divided into a number of functions each covering a specific category:

• Basic math functions
• Fast math functions
• Complex math functions
• Filters
• Matrix functions
• Transforms
• Motor control functions
• Statistical functions
• Support functions
• Interpolation functions

The library has separate functions for operating on 8-bit integers, 16-bit integers, 32-bit integer and 32-bit floating-point values.

Pre-processor Macros

Each library project have differant pre-processor macros.

• UNALIGNED_SUPPORT_DISABLE:

Define macro UNALIGNED_SUPPORT_DISABLE, If the silicon does not support unaligned memory access

• ARM_MATH_BIG_ENDIAN:

Define macro ARM_MATH_BIG_ENDIAN to build the library for big endian targets. By default library builds for little endian targets.

• ARM_MATH_MATRIX_CHECK:

Define macro ARM_MATH_MATRIX_CHECK for checking on the input and output sizes of matrices

• ARM_MATH_ROUNDING:

Define macro ARM_MATH_ROUNDING for rounding on support functions

• FPU_PRESENT:

Define macro FPU_PRESENT when building on FPU supported Targets.

• CCS:

Define macro CCS if the code composer studio tool is used.

Processor Support

The library is completely written in C. High performance is achieved through maximum use of Cortex-R intrinsics. This library supports both Cortex-R4 and Cortex-R5 processors.

Toolchain Support

The library has been developed and tested with MDK Version 4.21. The library also built on differant tools like Code composer studio, GCC-MDK, GCC-CodeSourcery, DS-5 and RVDS

Using the Library

The library installer contains prebuilt versions of the libraries in the Lib folder on MDK.

• arm_math_Cortex_R4_bspf.lib(bspf stands for Big-Endian Single precision Floating point support)
• arm_math_Cortex_R4_lspf.lib(lspf stands for Little-Endian Single precision Floating point support)

The following libraries supports both Cortex-R4/R5

• arm_math_Cortex_R_b.lib(b stands for Big-Endian without floating point unit)
• arm_math_Cortex_R_l.lib(l stands for little-Endian without floating point unit)

The library functions are declared in the public file arm_math.h which is placed in the Include folder. Simply include this file and link the appropriate library in your application and begin calling the library functions.

Building the Libraries on MDK

The library project files are located at Lib/ARM/MDK. To re-build the library on MDK Tool chain open the corresponding project and build.

Tool Version: MDK Version 4.21

• Lib\ARM\MDK\arm_math_Cortex_R_b.uvproj
• Lib\ARM\MDK\arm_math_Cortex_R4_bspf.uvproj
• Lib\ARM\MDK\arm_math_Cortex_R_l.uvproj
• Lib\ARM\MDK\arm_math_Cortex_R4_lspf.uvproj

Building the Library on CCS

Tool Version: Code Composer studio CGT 4.91 Tool

The library installer also contains project files to re build the library on Code Composer studio CGT 4.91 Tool chain in the Lib/TI/CCS folder.

• Lib\TI\CCS\arm_math_Cortex_R4_bspf\.project
• Lib\TI\CCS\arm_math_Cortex_R4_lspf\.project
• Lib\TI\CCS\arm_math_Cortex_R_b\.project
• Lib\TI\CCS\arm_math_Cortex_R_l\.project

Building the Library on DS-5

Tool Version: Eclipse Platform Version: 3.7.0 Build id: I20110613-1736

The library installer also contains project files to re build the library on DS-5 Tool chain in the Lib/ARM/DS5 folder.

• Lib\ARM\DS5\arm_math_Cortex_R4_bspf\.project
• Lib\ARM\DS5\arm_math_Cortex_R4_lspf\.project
• Lib\ARM\DS5\arm_math_Cortex_R5_bspf\.project
• Lib\ARM\DS5\arm_math_Cortex_R5_lspf\.project
• Lib\ARM\DS5\arm_math_Cortex_R_b\.project
• Lib\ARM\DS5\arm_math_Cortex_R_l\.project

Building the Library on GCC-CodeSourcery

Tool Version: Sourcery CodeBench IDE version: 2011.90-60

The library installer also contains project files to re build the library on CodeSourcery Tool chain in the Lib/ARM/SourceryCodeBench folder.

• Lib\ARM\SourceryCodeBench\arm_math_Cortex_R4_bspf\.project
• Lib\ARM\SourceryCodeBench\arm_math_Cortex_R4_lspf\.project
• Lib\ARM\SourceryCodeBench\arm_math_Cortex_R_b\.project
• Lib\ARM\SourceryCodeBench\arm_math_Cortex_R_l\.project

Building the Libraries on GCC-MDK

The library installer also contains project files to re build the library on MDK Tool chain in the Lib/ARM/MDK folder.

• Lib\ARM\MDK\arm_math_Cortex_R_b_GNU.uvproj
• Lib\ARM\MDK\arm_math_Cortex_R4_bspf_GNU.uvproj

Building the Library on RVDS

Tool Version: RVDS ARM Workbench IDE version: 4.0 Build Id: 159

The library installer also contains project files to re build the library on RVDS Tool chain in the Lib/ARM/RVDS folder.

• Lib\ARM\RVDS\arm_math_Cortex_R4_lspf\.project
• Lib\ARM\RVDS\arm_math_Cortex_R_l\.project
• Lib\ARM\RVDS\arm_math_Cortex_R4_bspf\.project
• Lib\ARM\RVDS\arm_math_Cortex_R_b\.project

Copyright Notice

Copyright (C) 2011 ARM Limited. All rights reserved.