GPU Programming with OpenCL Training Course

Introduction

• Overview of OpenCL: Core concepts and definitions.
• Comparative analysis of OpenCL, CUDA, and SYCL.
• Overview of key OpenCL features and architectural components.
• Steps to setting up a comprehensive development environment.

Getting Started

• Initiating a new OpenCL project using Visual Studio Code.
• Exploring project structure and essential file components.
• Processes for compiling and running OpenCL programs.
• Techniques for displaying output using printf and fprintf.

OpenCL API

• The role of the OpenCL API in host program management.
• Querying device information and assessing capabilities via the API.
• Creating contexts, command queues, buffers, kernels, and events using the OpenCL API.
• Enqueuing commands such as read, write, copy, map, unmap, execute, and wait.
• Implementing robust error and exception handling within the API.

OpenCL C

• The function of OpenCL C in device-side programming.
• Writing kernels for device execution and data manipulation using OpenCL C.
• Utilizing OpenCL C data types, qualifiers, operators, and expressions.
• Applying built-in functions for math, geometric, and relational operations.
• Leveraging extensions and libraries such as atomic operations, image processing, and cl_khr_fp16.

OpenCL Memory Model

• Distinguishing between host and device memory models.
• Managing memory spaces including global, local, constant, and private.
• Working with memory objects such as buffers, images, and pipes.
• Configuring memory access modes (read-only, write-only, read-write).
• Implementing memory consistency models and synchronization mechanisms.

OpenCL Execution Model

• Understanding the differences between host and device execution models.
• Defining parallelism using work-items, work-groups, and ND-ranges.
• Utilizing work-item functions like get_global_id, get_local_id, and get_group_id.
• Employing work-group functions such as barrier, work_group_reduce, and work_group_scan.
• Applying device functions including get_num_groups, get_global_size, and get_local_size.

Debugging

• Identifying and understanding common errors and bugs in OpenCL programs.
• Inspecting variables, breakpoints, and call stacks using the Visual Studio Code debugger.
• Debugging and analyzing OpenCL programs on AMD devices with CodeXL.
• Debugging and analyzing OpenCL programs on Intel devices with Intel VTune.
• Debugging and analyzing OpenCL programs on NVIDIA devices with NVIDIA Nsight.

Optimization

• Analyzing factors that influence the performance of OpenCL programs.
• Improving arithmetic throughput using OpenCL vector data types and vectorization techniques.
• Reducing control overhead and increasing locality through loop unrolling and loop tiling.
• Optimizing memory access and bandwidth using local memory and local memory functions.
• Measuring and improving execution time and resource utilization via OpenCL profiling and associated tools.