This course introduces the principles and techniques of GPU-accelerated computing for high-performance applications in AI, data analytics, and scientific simulation. Students will learn modern GPU architectures, the CUDA and ROCm programming models, memory hierarchy, thread organization, and performance optimization strategies. Through hands-on programming and a term-long project, students will gain practical experience in leveraging massive parallelism to solve real-world computational challenges.
Unlock more information by signing in with your HKUST account.