ROCm for Windows Training Course

ROCm is an open-source GPU programming platform that supports AMD GPUs while offering compatibility with both CUDA and OpenCL. By exposing hardware details, it grants programmers complete control over the parallelization process. However, leveraging this capability requires a solid grasp of device architecture, memory models, execution models, and optimization strategies.

ROCm for Windows is a recent advancement that enables users to install and utilize ROCm on the Windows operating system, a platform widely adopted for both personal and professional tasks. This allows users to harness the capabilities of AMD GPUs for diverse applications, including artificial intelligence, gaming, graphics rendering, and scientific computing.

This live, instructor-led training, available either online or onsite, is designed for developers ranging from beginner to intermediate levels who aim to install and utilize ROCm on Windows to program AMD GPUs and exploit their parallel processing capabilities.

Upon completing this training, participants will be equipped to:

• Establish a development environment on Windows that incorporates the ROCm Platform, an AMD GPU, and Visual Studio Code.
• Develop a fundamental ROCm program that executes vector addition on the GPU and retrieves the resulting data from GPU memory.
• Leverage the ROCm API to query device details, manage device memory allocation and deallocation, transfer data between host and device, initiate kernels, and synchronize threads.
• Utilize the HIP language to create kernels that run on the GPU and manipulate data.
• Employ HIP built-in functions, variables, and libraries to carry out standard tasks and operations.
• Apply ROCm and HIP memory spaces, including global, shared, constant, and local, to enhance data transfer efficiency and memory access patterns.
• Utilize ROCm and HIP execution models to manage the threads, blocks, and grids that define parallelism.
• Debug and test ROCm and HIP programs using specialized tools such as the ROCm Debugger and ROCm Profiler.
• Optimize ROCm and HIP programs by implementing techniques like coalescing, caching, prefetching, and profiling.

Course Format

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

Course Customization Options

• To request a tailored training experience for this course, please reach out to us for arrangements.