Short Courses of the 23rd Regional School of High Performance Computing from Southern Brazil
Keywords:
ERAD-RS 2023, Short Courses of the ERAD-RS 2023, ERAD-RS, High Performance ComputingSynopsis
This book presents the text of five mini-courses accepted and presented at the XXIII Regional High-Performance School of the Southern Region (ERAD/RS). The mini-courses aim to disseminate technical and scientific knowledge on topics related to high-performance processing in the southern region of the country. In the first chapter of this book, "Parallel Directives of OpenMP: A Case Study" the authors present different types of OpenMP directives and how each of them impacts the performance of a parallel application. In the second chapter, "Parallel Application Design", the author provides an overview of the parallel application design process. Two approaches are presented: PCAM and Design Patterns. In the third chapter, "DevOps for HPC: How to set up a cluster for shared use" the authors present a set of software and services that can be used to build a shared cluster infrastructure for the execution of parallel applications. In the fourth chapter, "Machine Learning and High-Performance Computing", the authors discuss the fundamentals of machine learning, its implications for high-performance computing, and the main techniques employed in this context. Computational models, commonly used frameworks, and various state-of-the-art scientific works are explored. In the fifth chapter, "Exploring Compression Techniques to Improve IoT Data Processing Efficiency", the authors address different data compression techniques and how they can contribute to improving performance in the compression and restoration processes of information, leading to greater efficiency in data transmission and storage.
Chapters
-
1. Parallel Directives of OpenMP: A Case Study
-
2. Parallel Application Design
-
3. DevOps for HPC: How to set up a cluster for shared use
-
4. Machine Learning and High-Performance Computing
-
5. Exploring Compression Techniques to Improve IoT Data Processing Efficiency
Downloads
