Nobleprog

Understanding the Fundamentals of Heterogeneous Computing Methodology, Why Parallel Computing? Understanding the Need for Parallel Computing, Multi-Core Processors - Architecture and Design, Introduction to Threads, Thread Basics and Basic Concepts of Parallel Programming, Understanding the Fundamentals of GPU Software Optimization Processes, OpenMP - A Standard for Directive-Based Parallel Programming, Hands on / Demonstration of Various Programs on Multicore Machines, Introduction to GPU Computing, GPUs for Parallel Computing, GPUs Programming Model, Hands on / Demonstration of Various Programs on GPU, SDK, Toolkit and Installation of Environment for GPU, Working with Various Libraries, Demonstration of GPU and Tools with Sample Programs and OpenACC, Understanding the CUDA Programming Model, Learning the CUDA Architecture, Exploring and Setting Up the CUDA Development Environments, Working with the CUDA Runtime API, Understanding the CUDA Memory Model, Exploring Additional CUDA API Features, Accessing Global Memory Efficiently in CUDA: Global Memory Optimization, Optimizing Data Transfers in CUDA Using CUDA Streams, Using Shared Memory in CUDA, Understanding and Using 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, Using CUDA Dynamic Parallelism API for Dynamic Kernel Launch, Summary and Conclusion

Course Details