Length : 3/4 day
Course Description
The focus of this training class is the Tensilica® HiFi 2 Audio DSP. The class is also applicable to the HiFi EP and HiFi Mini variations of the HiFi 2 Audio DSP. The class covers the basics of HiFi 2 architecture, instruction set, and programming model. It includes hands-on labs to practice writing C programs for the HiFi 2 DSP. This class provides the software developer or firmware engineer the skills necessary to develop and optimize audio/voice algorithms and kernels on the HiFi 2 audio DSP.
Learning Objectives
After completing this course, you will be able to:
- Understand the architecture and instruction set of the HiFi 2, EP, and Mini DSPs
- Write, profile, and debug C programs on the HiFi 2 DSP
- Optimize the performance of your code utilizing the audio-centric ISA of HiFi 2 and by using the advanced capabilities of the Tensilica software development tool chain
Software Used in This Course
- Xtensa Software Tools Release RE-2013.3
Software Release(s)
Course Agenda
Day 1
HiFi 2/EP/Mini Architecture
- The HiFi Product Family of Audio DSPs
- Architecture Overview
- HiFi EP and HiFi Mini Augmentations
- Instruction Set Highlights
HiFi 2/EP/Mini Programming Model
- C Data Types and Conversions
- Load/Store Operations and Addressing Modes
- Computation Units – MUL/MAC, ALU
- Programming Using Intrinsics
Labs
- Load/Store and Data Conversion
- Dot-Product Example
Audience
- Software developers writing and optimizing code for the HiFi 2 Audio DSP
Prerequisites
You must have experience with or knowledge of the following:
- Programming in C/C++ for embedded processors/DSP’s
You must have completed the following courses:
Related Courses
Click here to view course learning maps, and here for complete course catalogs.
