ROCm for Windows Training Course

As an open-source platform for GPU programming, ROCm supports AMD GPUs while offering compatibility with CUDA and OpenCL. It grants programmers direct access to hardware specifics and complete authority over the parallelization workflow. However, mastering this level of control demands a robust understanding of device architecture, memory models, execution logic, and optimization strategies.

The introduction of ROCm for Windows marks a significant advancement, enabling users to install and operate ROCm on the widely adopted Windows operating system. This capability allows professionals and enthusiasts to tap into the power of AMD GPUs for diverse applications, including artificial intelligence, gaming, graphics rendering, and scientific computing.

This live, instructor-led training is designed for developers ranging from beginner to intermediate levels. It guides participants through the process of installing and utilizing ROCm on Windows to program AMD GPUs and exploit their parallel processing potential.

By the conclusion of this course, participants will be equipped to:

• Establish a development environment featuring the ROCm Platform, an AMD GPU, and Visual Studio Code on Windows.
• Build a fundamental ROCm program that executes vector addition on the GPU and retrieves the outcome from GPU memory.
• Employ the ROCm API to query device details, manage device memory allocation and release, transfer data between host and device, launch kernels, and synchronize threads.
• Use the HIP language to create kernels that execute on the GPU and manipulate data.
• Apply HIP built-in functions, variables, and libraries to carry out standard tasks and operations.
• Optimize data transfers and memory accesses by utilizing ROCm and HIP memory spaces, including global, shared, constant, and local.
• Control parallelism by managing threads, blocks, and grids via ROCm and HIP execution models.
• Debug and test ROCm and HIP programs using tools such as the ROCm Debugger and ROCm Profiler.
• Optimize ROCm and HIP program performance using techniques like coalescing, caching, prefetching, and profiling.

Course Format

• Interactive lectures and facilitated discussions.
• Extensive exercises and practical drills.
• Hands-on implementation within a live-lab setting.

Course Customization Options

• For tailored training requirements, please contact us to discuss and arrange a customized session.