MATH-454: Parallel and high-performance computing

About
Privacy
Disclaimer

Graph Chatbot

Lectures in this course (7)

Conjugate Gradient Method: Solving Linear Systems

Covers the Conjugate Gradient method for solving linear systems without pre-conditioning, exploring parallel computing implementations and performance predictions.

MPI Basics: Point-to-Point and Collective Communications

Covers the basics of MPI, including point-to-point and collective communications, synchronizations, and avoiding race conditions.

MPI Advanced: Datatypes, Communicators, and I/O

Covers advanced MPI functions, including datatypes, communicators, and I/O, emphasizing the importance of using collectives for better performance.

Hybrid Programming and Project Proposals

Covers hybrid programming models, project proposals, thread safety, topology problems, and performance expectations in MPI.

GPU Introduction: Performance and Programming

Explores the motivation and advantages of using GPUs for computation, focusing on their performance and programming through CUDA.

GPU Advanced: Memory Management and Optimization

Explores advanced GPU memory management, CUDA programming, and data-parallel computing for optimizing performance.

Hybrid Programming Models Comparison

Compares hybrid programming models, discusses project proposals, and emphasizes the importance of considering physical topology in application development.

Page 1 of 1