GPU Programming with CUDA Training Course

Introduction

• What is CUDA?
• Comparison of CUDA vs OpenCL vs SYCL
• Overview of CUDA features and architecture
• Setting up the Development Environment

Getting Started

• Creating a new CUDA project in Visual Studio Code
• Exploring the project structure and files
• Compiling and running the program
• Displaying output using printf and fprintf

CUDA API

• Understanding the role of the CUDA API in host programs
• Using the CUDA API to query device information and capabilities
• Using the CUDA API to allocate and deallocate device memory
• Using the CUDA API to transfer data between host and device
• Using the CUDA API to launch kernels and synchronize threads
• Using the CUDA API to handle errors and exceptions

CUDA C/C++

• Understanding the role of CUDA C/C++ in device programs
• Writing kernels in CUDA C/C++ that execute on the GPU and manipulate data
• Using CUDA C/C++ data types, qualifiers, operators, and expressions
• Utilizing CUDA C/C++ built-in functions, such as math, atomic, and warp operations
• Utilizing CUDA C/C++ built-in variables, such as threadIdx, blockIdx, and blockDim
• Leveraging CUDA C/C++ libraries, including cuBLAS, cuFFT, and cuRAND

CUDA Memory Model

• Understanding the differences between host and device memory models
• Using CUDA memory spaces, such as global, shared, constant, and local
• Managing CUDA memory objects, including pointers, arrays, textures, and surfaces
• Applying CUDA memory access modes, such as read-only, write-only, and read-write
• Utilizing the CUDA memory consistency model and synchronization mechanisms

CUDA Execution Model

• Understanding the differences between host and device execution models
• Defining parallelism using CUDA threads, blocks, and grids
• Using CUDA thread functions, such as threadIdx, blockIdx, and blockDim
• Employing CUDA block functions, such as __syncthreads and __threadfence_block
• Utilizing CUDA grid functions, including gridDim, gridSync, and cooperative groups

Debugging

• Identifying common errors and bugs in CUDA programs
• Using the Visual Studio Code debugger to inspect variables, breakpoints, and call stacks
• Debugging CUDA programs on Linux using CUDA-GDB
• Detecting memory errors and leaks with CUDA-MEMCHECK
• Debugging and analyzing CUDA programs on Windows using NVIDIA Nsight

Optimization

• Understanding factors that impact CUDA program performance
• Applying CUDA coalescing techniques to improve memory throughput
• Using CUDA caching and prefetching techniques to reduce memory latency
• Optimizing memory access and bandwidth with CUDA shared and local memory techniques
• Measuring and improving execution time and resource utilization through CUDA profiling and tools