Algorithm Acceleration Study

Step 1 : Introduction to GPGPU/CUDA

Overview of GPGPU/CUDA

Thread and Execution Model

Step 2 : CUDA Memory Model

CUDA memory hierarchy 

Memory model & Performance

Using shared memory

Step 3 : Maximizing Memory Throughput

Global memory 

Shared memory

Step 4 : Synchronization & Concurrent Execution

Synchronization 

CUDA stream & Concurrent execution

CUDA Event

Step 5 : Algorithm Implementation and Acceleration

Algorithm Implementation with MATLAB 

Algorithm Implementation with C/C++

Algorithm Acceleration with GPGPU/CUDA