MATHLIB Release Notes

Version: 09.02.00.04

Contents

  1. Introduction
  2. Licensing
  3. Getting Started
  4. Documentation
  5. What's New
  6. Upgrade and Compatibility Information
  7. Device Support
  8. Validation Information
  9. Fixed Issues
  10. Deprecation
  11. Known Issues
  12. Technical Support
  13. Package Versioning

Introduction

The MATHLIB package consists of the Texas Instruments optimized kernels for floating point Math algorithms.

Licensing

The licensing information of this library and a complete manifest along with export control information is detailed here [HTML].

Getting Started

The MATHLIB User Guide [USER_GUIDE] provides the documentation and references necessary to begin development on TI's platforms. Currently, Windows build is not supported.

Documentation

Refer to following documentation for further details:

MATHLIB User Guide Build instructions, API Guide [USER_GUIDE]
Software Manifest Licenses, terms of use [HTML]

What's New

API changes from 02_06_01_00:

MATHLIB no longer has <kernel>_init and <kernel>_exec functions. Its replaced with a single API. For example, MATHLIB_cos_init and MATHLIB_cos_exec do not exist anymore. Instead, they are replaced with one API in MATHLIB_cos. The SE0/SA0 settings which was previously a part of MATHLIB_init is now part of MATHLIB_cos.

In order to perform elementwise cosine of a given vector, please call MATHLIB_cos as follows:

MATHLIB_cos(length, in, out); where, 'length' is the size of input vector pointed to by buffer pointer 'in', and 'out' is the pointer to buffer with elementwise cosine of input vector. Please refer to <mathlib root>/examples/<kernel>/<kernel>_example.cpp for more details on how to call the API.

New Kernels:

Upgrade and Compatibility Information

File Change description User application change required User application recompile required

Device Support

SoC Host (OS) Target (OS) Test Platform
C7x No OS No OS

Validation Information

This release was built and validated using the following tools:

Build Tools (NOT included in MATHLIB):

Supported Kernels

  1. [XLIB-21] MATHLIB_cosh single precision
  2. [XLIB-23] MATHLIB_tanh single precision
  3. [XLIB-19] MATHLIB_rsqrt single precision
  4. [XLIB-22] MATHLIB_sinh single precision
  5. [XLIB-14] MATHLIB_atanh single precision
  6. [XLIB-12] MATHLIB_acosh single precision
  7. [XLIB-17] MATHLIB_exp10 single precision
  8. [XLIB-15] MATHLIB_atan2 single precision
  9. [XLIB-13] MATHLIB_asinh single precision
  10. [XLIB-2] MATHLIB_sin single precision
  11. [XLIB-6] MATHLIB_atan single precision
  12. [XLIB-7] MATHLIB_div single precision
  13. [XLIB-5] MATHLIB_asin single precision
  14. [XLIB-4] MATHLIB_acos single precision
  15. [XLIB-8] MATHLIB_sqrt single precision
  16. [XLIB-3] MATHLIB_tan single precision

Fixed Issues

Known Issues

Technical Support

For technical support, please post your questions on TI E2E Forum for Processors.

For additional assistance, contact local TI Field Application Engineer

Package Versioning

Each package version is composed of 4 period-delimited numbers - represented here by the letters M, m, p and b [M.m.p.b]. The table below provides a descriptive reference regarding package version numbering.

Digit Meaning Description
1 (M=Major) Major revision Incremented when the new version is substantially different from the previous For example, a new module added or an existing module's algorithm significantly altered.
2 (m=minor) Minor revision Incremented when the new version has changed but not in a major way. For example, some minor changes in the API or feature set.
3 (p=patch) Patch number Incremented for all other source code changes. This include any packaging support code.
4 (b=build) Build number Incremented for each release delivery to CM. Reset for any change to M, m or p
Copyright 2023, Texas Instruments Incorporated