Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction
- What is GPU programming?
- Why use GPU programming?
- What are the challenges and trade-offs of GPU programming?
- What frameworks and tools are available for GPU programming?
- Choosing the right framework and tool for your application
OpenCL
- What is OpenCL?
- What are the advantages and disadvantages of OpenCL?
- Setting up the development environment for OpenCL
- Creating a basic OpenCL program that performs vector addition
- Using the OpenCL API to query device information, allocate and deallocate device memory, copy data between host and device, launch kernels, and synchronise threads
- Writing kernels using the OpenCL C language that execute on the device and manipulate data
- Using OpenCL built-in functions, variables, and libraries to perform common tasks and operations
- Utilising OpenCL memory spaces, such as global, local, constant, and private, to optimise data transfers and memory access
- Using the OpenCL execution model to control work-items, work-groups, and ND-ranges that define parallelism
- Debugging and testing OpenCL programs using tools such as CodeXL
- Optimising OpenCL programs using techniques such as coalescing, caching, prefetching, and profiling
CUDA
- What is CUDA?
- What are the advantages and disadvantages of CUDA?
- Setting up the development environment for CUDA
- Creating a basic CUDA program that performs vector addition
- Using the CUDA API to query device information, allocate and deallocate device memory, copy data between host and device, launch kernels, and synchronise threads
- Writing kernels using the CUDA C/C++ language that execute on the device and manipulate data
- Using CUDA built-in functions, variables, and libraries to perform common tasks and operations
- Utilising CUDA memory spaces, such as global, shared, constant, and local, to optimise data transfers and memory access
- Using the CUDA execution model to control threads, blocks, and grids that define parallelism
- Debugging and testing CUDA programs using tools such as CUDA-GDB, CUDA-MEMCHECK, and NVIDIA Nsight
- Optimising CUDA programs using techniques such as coalescing, caching, prefetching, and profiling
ROCm
- What is ROCm?
- What are the advantages and disadvantages of ROCm?
- Setting up the development environment for ROCm
- Creating a basic ROCm program that performs vector addition
- Using the ROCm API to query device information, allocate and deallocate device memory, copy data between host and device, launch kernels, and synchronise threads
- Writing kernels using the ROCm C/C++ language that execute on the device and manipulate data
- Using ROCm built-in functions, variables, and libraries to perform common tasks and operations
- Utilising ROCm memory spaces, such as global, local, constant, and private, to optimise data transfers and memory access
- Using the ROCm execution model to control threads, blocks, and grids that define parallelism
- Debugging and testing ROCm programs using tools such as ROCm Debugger and ROCm Profiler
- Optimising ROCm programs using techniques such as coalescing, caching, prefetching, and profiling
HIP
- What is HIP?
- What are the advantages and disadvantages of HIP?
- Setting up the development environment for HIP
- Creating a basic HIP program that performs vector addition
- Using the HIP language to write kernels that execute on the device and manipulate data
- Using HIP built-in functions, variables, and libraries to perform common tasks and operations
- Utilising HIP memory spaces, such as global, shared, constant, and local, to optimise data transfers and memory access
- Using the HIP execution model to control threads, blocks, and grids that define parallelism
- Debugging and testing HIP programs using tools such as ROCm Debugger and ROCm Profiler
- Optimising HIP programs using techniques such as coalescing, caching, prefetching, and profiling
Comparison
- Comparing the features, performance, and compatibility of OpenCL, CUDA, ROCm, and HIP
- Evaluating GPU programs using benchmarks and metrics
- Learning best practices and tips for GPU programming
- Exploring current and future trends and challenges in GPU programming
Summary and Next Steps
Requirements
- A solid understanding of the C/C++ language and parallel programming concepts
- Foundational knowledge of computer architecture and memory hierarchy
- Practical experience with command-line tools and code editors
Audience
- Developers seeking to learn the fundamentals of GPU programming and the core frameworks and tools for developing GPU applications
- Developers aiming to write portable and scalable code capable of running across different platforms and devices
- Programmers interested in exploring the advantages and challenges of GPU programming and optimisation
21 Hours
