Length: 3 Days (24 hours)
Course Description
This course teaches you how to program Tensilica® Vision DSPs. It provides a comprehensive guide to Vision DSPs and covers the topics shared by all members of the Vision DSP family. Topics include architecture, instruction set, programming model, performance estimation and assessment, DMA programming, and software libraries.
Learning Objectives
After completing this course, you will be able to:
- Program the Vision DSPs and implement basic image processing algorithms
- Program based on the N-way model that provides the scalability among different Vision DSP family members
- Estimate the performance of an algorithm before implementation and assess the performance after implementation
- Understand how to use DMA in your code and estimate and assess its impact on performance
- Use functions from the software libraries
Software Used in This Course
- Tensilica Xtensa Xplorer
- Tensilica Xtensa Software Tools
Software Release(s)
RJ-2024.4
Modules in this Course
- Vision DSP Deliverables
- Vision DSP Architecture
- Vision DSP ISA Highlights
- Estimating Performance
- Vision DSP Programming (includes a lab exercise)
- Assessing Performance
- Gather/Scatter Engine (includes a lab exercise)
- ISA Deep Dive
- iDMA (includes a lab exercise)
- Optional Packages
- Software Libraries (includes a lab exercise)
Audience
- Software engineers developing and optimizing codes for Vision DSPs
Prerequisites
You must have experience with or knowledge of the following:
- Basic image processing knowledge OR
- Basic computer vision application domain knowledge
You should have experience with:
- Programming DSP processors for embedded systems
And you must have completed the following courses:
Related Courses
Please see course learning maps at this link for a visual representation of courses and course relationships. Regional course catalogs may be viewed here.
Free Online Training Bytes (Videos)
