Parallel Computing with CUDA

Pluralsight

Course Summary

An entry-level course on CUDA - a GPU programming technology from NVIDIA.

+
Course Description

This introductory course on CUDA shows how to get started with using the CUDA platform and leverage the power of modern NVIDIA GPUs. It covers the basics of CUDA C, explains the architecture of the GPU and presents solutions to some of the common computational problems that are suitable for GPU acceleration.

Course Description

This introductory course on CUDA shows how to get started with using the CUDA platform and leverage the power of modern NVIDIA GPUs. It covers the basics of CUDA C, explains the architecture of the GPU and presents solutions to some of the common computational problems that are suitable for GPU acceleration.

+
Course Syllabus

GPU Architecture Overview
- 16m 9s

—Course Outline 2m 41s
—History of GPU Computation 4m 27s
—GPGPU Frameworks 2m 47s
—Graphics Processor Architecture 2m 41s
—Compute Capability 1m 2s
—Choosing a Graphics Card 2m 29s

Tools of The Trade
- 16m 52s

—Tools Overview 5m 4s
—Using NSight 2m 59s
—Running CUDA Apps 3m 29s
—Debugging 2m 49s
—Profiling 2m 29s

Introduction to CUDA C
- 30m 14s

—Overview 1m 7s
—Compilation Process 3m 1s
—Hello, CUDA 13m 52s
—Location Qualifiers 1m 34s
—Execution Model 2m 12s
—Grid and Block Dimensions 3m 2s
—Error Handling 0m 46s
—Device Introspection 4m 36s

Parallel Programming Patterns
- 52m 30s

—Overview 2m 49s
—Element Addressing 2m 14s
—Map 11m 54s
—Gather 12m 39s
—Scatter 0m 50s
—Reduce 12m 9s
—Scan 9m 53s

The Many Types of Memory
- 12m 42s

—Overview 1m 23s
—Global Memory 2m 19s
—Constant & Texture Memory 1m 53s
—Shared Memory 4m 43s
—Register & Local Memory 1m 32s
—Summary 0m 50s

Thread Cooperation and Synchronization
- 23m 46s

—Overview 1m 14s
—Barrier Synchronization 1m 4s
—Thread Synchronization Demo 18m 20s
—Warp Divergence 2m 7s
—Summary 1m 0s

Atomic Operations
- 22m 53s

—Overview 0m 44s
—Why Atomics? 1m 4s
—Atomic Functions 1m 57s
—Atomic Sum 7m 55s
—Monte Carlo Pi 10m 37s
—Summary 0m 33s

Events and Streams
- 35m 58s

—Overview 0m 55s
—Events 1m 14s
—Event API 1m 13s
—Event example 2m 14s
—Pinned memory 8m 17s
—Streams 0m 52s
—Stream API 1m 27s
—Example (single stream) 12m 30s
—Example (multiple streams) 6m 17s
—Summary 0m 55s

CUDA in Advanced Scenarios
- 41m 32s

—Overview 0m 44s
—Inline PTX 1m 34s
—Device API 9m 45s
—Pinned Memory 2m 15s
—Multi-GPU Programming 20m 16s
—Thrust 5m 52s
—Summary 1m 1s