ROCm for Windows Training Course

ROCm serves as an open-source GPU programming framework designed for AMD GPUs, offering compatibility with both CUDA and OpenCL. While ROCm grants developers comprehensive control over hardware details and the parallelization workflow, effectively leveraging this capability requires a solid grasp of device architecture, memory models, execution flows, and advanced optimization strategies.

With the introduction of ROCm for Windows, users can now deploy and utilize the platform on the Windows operating system, a standard environment for both personal and professional workloads. This expansion enables users to harness the capabilities of AMD GPUs for a wide range of applications, including artificial intelligence, gaming, high-end graphics, and scientific computing.

This instructor-led live training, available online or on-site, is tailored for developers ranging from beginner to intermediate levels who are eager to install and operate ROCm on Windows to program AMD GPUs and exploit their inherent parallelism.

Upon completion of this training, participants will be equipped to:

• Configure a development environment on Windows that integrates the ROCm Platform, an AMD GPU, and Visual Studio Code.
• Develop a fundamental ROCm application that executes vector addition on the GPU and retrieves the computed results from GPU memory.
• Leverage the ROCm API to query device specifications, manage device memory allocation and deallocation, transfer data between host and device, initiate kernel launches, and synchronize threads.
• Utilize the HIP language to author kernels that run on the GPU and process data effectively.
• Apply HIP built-in functions, variables, and libraries to streamline common tasks and operations.
• Optimize data transfers and memory access patterns by utilizing ROCm and HIP memory spaces, including global, shared, constant, and local memories.
• Manage parallelism by employing ROCm and HIP execution models to control threads, blocks, and grids.
• Conduct debugging and testing of ROCm and HIP applications using specialized tools such as the ROCm Debugger and ROCm Profiler.
• Enhance the performance of ROCm and HIP programs through optimization techniques like coalescing, caching, prefetching, and detailed profiling.

Course Format

• Engaging interactive lectures and discussions.
• Extensive exercises and practical application.
• Hands-on implementation within a live laboratory environment.

Course Customization

• To arrange a customized training session for this course, please reach out to us directly.