CUDA Dot Product Reduction: Beyond Simple Array Operations
Learn parallel reduction with a practical dot product implementation. Discover grid-stride loops and shared memory patterns for real machine learning applications.
All Posts
CUDA Week 2: Mastering Thread Organization and Grid-Stride Loops
Dive deeper into CUDA programming with proper thread indexing, grid-stride loops, and achieving real GPU speedup. Learn why proper thread organization finally makes GPU faster than CPU.
My First CUDA Adventure: Adding and Multiplying Arrays on the GPU
Learn CUDA programming with array addition and multiplication. Discover why GPU is not always faster than CPU and common beginner mistakes to avoid.Process API in UNIX
The exec family of functions in Unix systems allows a process to replace its own executable code with a different executable.When you feel lost
Don't compare yourselves to others. Live your own unique life and be thankful of being alive.