AMD GPU Programming Training Course

Introduction

• Defining ROCm.
• Defining HIP.
• Comparing ROCm, CUDA, and OpenCL.
• Overview of ROCm and HIP features and architecture.
• Setting up the Development Environment.

Getting Started

• Creating a new ROCm project using Visual Studio Code.
• Exploring the project structure and constituent files.
• Compiling and executing the program.
• Displaying output using printf and fprintf.

ROCm API

• Understanding the role of the ROCm API in host-level programming.
• Querying device information and capabilities via the ROCm API.
• Allocating and deallocating device memory using the ROCm API.
• Copying data between host and device with the ROCm API.
• Launching kernels and synchronizing threads through the ROCm API.
• Managing errors and exceptions using the ROCm API.

HIP Language

• Understanding the role of the HIP language in device-level programming.
• Writing HIP kernels that execute on the GPU and manipulate data.
• Utilizing HIP data types, qualifiers, operators, and expressions.
• Using HIP built-in functions, variables, and libraries for common tasks and operations.

ROCm and HIP Memory Model

• Distinguishing between host and device memory models.
• Utilizing ROCm and HIP memory spaces, including global, shared, constant, and local.
• Working with ROCm and HIP memory objects, such as pointers, arrays, textures, and surfaces.
• Applying ROCm and HIP memory access modes, such as read-only, write-only, and read-write.
• Implementing ROCm and HIP memory consistency models and synchronization mechanisms.

ROCm and HIP Execution Model

• Distinguishing between host and device execution models.
• Defining parallelism using ROCm and HIP threads, blocks, and grids.
• Utilizing ROCm and HIP thread functions, such as hipThreadIdx_x, hipBlockIdx_x, and hipBlockDim_x.
• Applying ROCm and HIP block functions, such as __syncthreads and __threadfence_block.
• Using ROCm and HIP grid functions, such as hipGridDim_x, hipGridSync, and cooperative groups.

Debugging

• Identifying common errors and bugs in ROCm and HIP programs.
• Inspecting variables, breakpoints, and call stacks using the Visual Studio Code debugger.
• Debugging ROCm and HIP programs on AMD devices using the ROCm Debugger.
• Analyzing ROCm and HIP programs on AMD devices using the ROCm Profiler.

Optimization

• Understanding the factors impacting the performance of ROCm and HIP programs.
• Applying ROCm and HIP coalescing techniques to enhance memory throughput.
• Using ROCm and HIP caching and prefetching techniques to reduce memory latency.
• Leveraging ROCm and HIP shared and local memory techniques to optimize memory access and bandwidth.
• Employing ROCm and HIP profiling tools to measure and improve execution time and resource utilization.

Summary and Next Steps