An implementation of a parallel Gaussian blur algorithm written in CUDA C++. OpenCV is used solely for reading/writing images and converting between image formats.
-
Updated
Jul 31, 2020 - Cuda
An implementation of a parallel Gaussian blur algorithm written in CUDA C++. OpenCV is used solely for reading/writing images and converting between image formats.
A simple and understandable CUDA kernel for batch-matmul operation
The MNIST classification problem is a fundamental machine learning task that involves recognizing handwritten digits (0- 9) from a dataset of 70,000 grayscale images (28x28 pixels each). It serves as a benchmark for evaluating machine learning models, particularly neural networks.
A collection of CUDA programming exercises focused on exploring and implementing high-performance GPU computing techniques. The repository covers topics such as warp-level optimization, shared memory utilization, and various algorithm implementations tailored for parallel processing.
Machine problems
Assigment 3 for the "Parallel & Distributed Systems" course (ECE, AUTh)
High-performance GPU implementations of Gaussian Blur and Sobel Edge Detection with CUDA, featuring optimized memory usage, benchmarking, and visualization of speedups over CPU.
Repository of the lab9 assignment for the Parallel Programming course.
Add a description, image, and links to the shared-memory topic page so that developers can more easily learn about it.
To associate your repository with the shared-memory topic, visit your repo's landing page and select "manage topics."