Paralelización de Aplicaciones de Alto Rendimiento Utilizando Arquitecturas Híbridas

OpenMP Fundamentals. Data Environment

Clase 02 (Versión Borrador)

Clase 03 (Versión Borrador)

Introduction to CUDA: The Basics. Memory Allocation and Data Movement API Functions. Introduction to the CUDA Toolkit. Thread Scheduling. Memory and Data Locality. Tiled Parallel Algorithms. Handling Arbitrary Matrix Sizes in Tiled Algorithms

Efficiency and Performance Considerations. Memory Access Performance. Reductions

Clase 06 (Versión Borrador)

Introduction to OpenACC. Profiling and Parallelizing

MPI: One-Sided Communication