Course Outline
Introduction
Grasping the Fundamentals of Heterogeneous Computing Methodology
The Case for Parallel Computing: Understanding Its Necessity
Multi-Core Processors: Architecture and Design
Introduction to Threads: Core Concepts and Basics of Parallel Programming
Mastering GPU Software Optimization Techniques
OpenMP: A Standard for Directive-Based Parallel Programming
Practical Demonstrations of Programs on Multicore Systems
Introduction to GPU Computing
Leveraging GPUs for Parallel Computing
The GPU Programming Model
Practical Demonstrations of Programs on GPU Hardware
SDK, Toolkit, and Environment Setup for GPU Development
Working with Various Libraries
Demo of GPU Capabilities, Tools, Sample Programs, and OpenACC
Understanding the CUDA Programming Model
Studying the CUDA Architecture
Setting Up and Exploring the CUDA Development Environment
Working with the CUDA Runtime API
Understanding the CUDA Memory Model
Exploring Additional CUDA API Features
Efficient Global Memory Access in CUDA: Optimization Strategies
Optimizing Data Transfers in CUDA Using CUDA Streams
Leveraging Shared Memory in CUDA
Understanding and Implementing Atomic Operations and Instructions in CUDA
Case Study: Basic Digital Image Processing with CUDA
Working with Multi-GPU Programming
Advanced Hardware Profiling and Sampling on NVIDIA / CUDA
Utilizing the CUDA Dynamic Parallelism API for Dynamic Kernel Launch
Summary and Conclusion
Requirements
- Proficiency in C Programming
- Familiarity with Linux GCC
Testimonials (1)
Trainers energy and humor.
