GPU Accelerated Image Filters | GPU Cache & Constant Memory | CUDA C/C++
Tushar Gautam
0:00 / 0:00
GPU Accelerated Image Filters | GPU Cache & Constant Memory | CUDA C/C++
3 595 просмотров · 1 год назад
Tushar Gautam
13,1 тыс. подписчиков
3 595 просмотров · 1 год назад
Apply filters to high-resolution images using GPU-accelerated convolution.
Code Repository: https://github.com/tgautam03/xFilters...
Video Notes and Code Explainers: https://0mean1sigma.com/xfilters/
Animations: https://github.com/tgautam03/0Mean1Sigma
Other Projects: https://0mean1sigma.com/mini-projects/
References:
1. Kirk, David B., and W. Hwu Wen-Mei. Programming massively parallel processors: a hands-on approach. Morgan kaufmann, 2016.
2. Ansorge, Richard. Programming in parallel with CUDA: a practical guide. Cambridge University Press, 2022.
3. Memory types in GPU by CisMine Ng: https://github.com/CisMine/Parallel-C...
4. Shouldn't be 3x3 convolution much faster on GPU (OpenCL): https://stackoverflow.com/questions/4...
Chapters:
00:00 - Introduction
00:20 - What is Convolution
01:54 - Naive GPU Convolution
02:28 - Constant and Shared Memory
04:24 - Caches and Pinned Memory
06:27 - Conclusion