Bookmark and Share

Technical Articles

What was science fiction or research is now becoming real and practical. It will be transformative. And it will be everywhere.

This chapter describes the performance of some common 3 x 3 convolution matrices using the fully optimized code.

Academy

This chapter describes variations to the algorithm for 3 x 3 convolution matrices to create an algorithm for 5 x 5 convolution matrices.

Academy

This chapter describes describes some general concepts to consider when optimizing kernels.

Academy

This chapter describes describes some useful optimization methods, the logic for them, and the results they provide on the test platform.

Academy

This chapter describes some initial (as well as the simplest and most intuitive) implementations of convolution algorithms.

Academy

Convolution operations are important in image processing, particularly in filtering. GPU compute can improve performance significantly.

Academy

Imagination provides all of the hardware components needed to build efficient vision products today.

OpenVX enables embedded vision application software developers to efficiently harness the processing resources available in SoCs and systems

Academy

This article discusses the optimization motivation, vectorization techniques and resultant performance of the FFT on ARM Mali GPUs.

Academy