This repository documents my journey through 100 days of GPU programming challenges, focusing on CUDA and parallel computing concepts.
| Day | Date | Topic/Challenge | Status | Notes |
|---|---|---|---|---|
| 001 | 2025-02-05 | Hello World CUDA | Done | Basic CUDA program setup |
| 002 | 2025-02-06 | Grid 1D CUDA | Done | |
| 003 | 2025-02-07 | Vector Addition | Done | |
| 004 | 2025-02-08 | Performance Benchmarking | Done | Memory transfer vs kernel execution analysis |
| 005 | 2025-02-09 | 2D Matrix Addition | Done | |
| 006 | 2025-02-10 | Modular Matrix Addition | Done | using device functions |
| 007 | 2025-02-11 | Matrix Addition Performance Analysis | Done | Block size optimization (8x8, 16x16, 32x32) with Nsight profiling |
| 008 | 2025-02-15 | Image Brightness Adjustment using CUDA | Done | CUDA-based image processing with brightness adjustment, host/device memory management, and PGM file I/O |
| 009 | 2025-02-16 | Image Blur using CUDA | Done | Parallel box blur implementation with configurable kernel size, boundary handling, and PGM image processing |
| 010 | 2025-02-17 | Matrix Multiplication using CUDA | Done | Basic parallel matrix multiplication with 2D grid/block organization |
| 011 | 2025-02-19 | Matrix Multiplication Performance Benchmarking | Done | Systematic performance analysis with different block sizes (8x8 to 32x32) on 1024x1024 matrices |
| 012 | ||||
| 013 | ||||
| 014 | ||||
| 015 | ||||
| 016 | ||||
| 017 | ||||
| 018 | ||||
| 019 | ||||
| 020 |
Note: Table will be updated daily with new entries and progress.
- Each day's work is stored in its own directory (e.g.,
Day001,Day002, etc.) - Each directory contains the source code and documentation for that day's challenge