GPU Programming with C++ and CUDA
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
GPU Programming with C++ and CUDA
Included with
Ask Coursera
Recommended experience
Recommended experience
What you'll learn
Accelerate real-world tasks using GPU parallelism
Optimize performance with CUDA streams and custom C++ solutions
Create and share GPU libraries with Python integration
Skills you'll gain
Tools you'll learn
Details to know
March 2026
10 assignments
See how employees at top companies are mastering in-demand skills
There are 10 modules in this course
In this course, you’ll master GPU programming using C++ and CUDA to significantly enhance your software's performance. By focusing on parallelism, you’ll learn to leverage the full power of GPUs for high-performance computing applications.
You will acquire practical knowledge on managing GPU devices, optimizing GPU resource usage, and integrating GPU code with Python to build scalable and efficient applications. This course emphasizes real-world strategies for optimizing performance and building reusable libraries. This course combines fundamental theory with hands-on applications to help you solve complex performance challenges. You'll not only understand the core concepts but also implement them in real-world projects, such as creating libraries for Python integration. Ideal for C++ developers with experience in basic programming concepts, this course will take you through advanced topics, from parallel algorithms to multi-GPU usage. A background in operating systems is recommended for tackling more complex concepts. Based on the book, GPU Programming with C++ and CUDA, by Paulo Motta.
In this section, we explore parallelism in software, its importance, and the differences between CPU and GPU architectures to build a foundation for GPU programming.
What's included
2 videos4 readings1 assignment
2 videos•Total 2 minutes
- Introduction - Overview Video•1 minute
- Introduction to Parallel Programming - Overview Video•1 minute
4 readings•Total 40 minutes
- Introduction•10 minutes
- Why Is Parallelism Important?•10 minutes
- An Overview of GPU Architecture•10 minutes
- Memory Management and Access•10 minutes
1 assignment•Total 10 minutes
- Parallel Programming Fundamentals•10 minutes
In this section, we configure a GPU environment using Docker, locate official Linux documentation, and install the CUDA toolkit on Ubuntu 20.04 or 22.04 for AI and machine learning workflows.
What's included
1 video3 readings1 assignment
1 video•Total 1 minute
- Setting Up Your Development Environment - Overview Video•1 minute
3 readings•Total 30 minutes
- Introduction•10 minutes
- Docker at a Glance•10 minutes
- Readying Our Development Environment•10 minutes
1 assignment•Total 10 minutes
- Docker and CUDA Setup Fundamentals•10 minutes
In this section, we introduce GPU programming fundamentals, including kernel execution, device inspection, and setting up a working environment for CUDA development.
What's included
1 video4 readings1 assignment
1 video•Total 1 minute
- Hello CUDA - Overview Video•1 minute
4 readings•Total 50 minutes
- Introduction•10 minutes
- A First Running Program•10 minutes
- Consulting Devices•10 minutes
- VS Code Configuration•20 minutes
1 assignment•Total 10 minutes
- Introduction to CUDA and Dev Containers•10 minutes
In this section, we explore SIMD execution, data movement, and parallel vector addition for GPU programming.
What's included
1 video5 readings1 assignment
1 video•Total 1 minute
- Hello Again, but in Parallel - Overview Video•1 minute
5 readings•Total 50 minutes
- Introduction•10 minutes
- Not-So-Parallel Prime Number Verification•10 minutes
- A Kernel to Test for Prime Numbers•10 minutes
- How to Measure Execution Time on the GPU•10 minutes
- Vector Addition•10 minutes
1 assignment•Total 10 minutes
- Parallel Computing Fundamentals•10 minutes
In this section, we explore GPU thread, block, and grid configurations, asynchronous data transfer, streams, events, and shared memory to optimize performance in parallel computing.
What's included
1 video5 readings1 assignment
1 video•Total 1 minute
- A Closer Look into the World of GPUs - Overview Video•1 minute
5 readings•Total 70 minutes
- Introduction•20 minutes
- Putting It All Together•10 minutes
- Asynchronous Data Transfers•10 minutes
- Parallelizing with Streams•20 minutes
- Following the Events•10 minutes
1 assignment•Total 10 minutes
- Exploring GPU Architecture and Optimization Techniques•10 minutes
In this section, we explore parallel algorithm design, focusing on matrix operations, reduction, and workload balancing for efficient GPU execution.
What's included
1 video8 readings1 assignment
1 video•Total 1 minute
- Parallel Algorithms with CUDA - Overview Video•1 minute
8 readings•Total 80 minutes
- Introduction•10 minutes
- Understanding How to Spot and Exploit Parallelism•10 minutes
- Balancing the Workloads•10 minutes
- Computing Matrix Addition and Multiplication•10 minutes
- Calculating Numerical Integrals•10 minutes
- Reducing from Many•10 minutes
- Sorting Data•10 minutes
- Processing Sensor Data with a Convolution•10 minutes
1 assignment•Total 10 minutes
- Data Management and Parallel Execution•10 minutes
In this section, we explore GPU optimization and profile with NVIDIA Nsight Compute.
What's included
1 video5 readings1 assignment
1 video•Total 1 minute
- Performance Strategies - Overview Video•1 minute
5 readings•Total 100 minutes
- Introduction•10 minutes
- Profiling with NVIDIA Nsight Compute•20 minutes
- Optimizing to Speed Up Our Code•20 minutes
- Using the Release Configuration•20 minutes
- Using Loop Unroll for Further Improvements•30 minutes
1 assignment•Total 10 minutes
- Performance Strategies in Software Development•10 minutes
In this section, we explore debugging CUDA code with VS Code, using CUDA streams to overlap memory and kernel operations, and configuring multiple GPUs for parallel processing.
What's included
1 video4 readings1 assignment
1 video•Total 1 minute
- Overlaying Multiple Operations - Overview Video•1 minute
4 readings•Total 80 minutes
- Introduction•20 minutes
- Using CUDA Streams to Overlay Operations•10 minutes
- Measuring Our Limits•30 minutes
- Running Multiple GPUs Together•20 minutes
1 assignment•Total 10 minutes
- Multi-GPU and CUDA Stream Fundamentals•10 minutes
In this section, we explore methods to integrate C++ GPU code with Python, focusing on Ctypes, custom wrappers, and performance analysis for efficient cross-language execution.
What's included
1 video4 readings1 assignment
1 video•Total 1 minute
- Exposing Your Code to Python - Overview Video•1 minute
4 readings•Total 80 minutes
- Introduction•20 minutes
- Creating the C++ Library•20 minutes
- Using Ctypes•20 minutes
- Passing NumPy Arrays to Your Library•20 minutes
1 assignment•Total 10 minutes
- Integrating C++ with Python for High-Performance Computing•10 minutes
In this section, we explore GPU development using cuBLAS and Thrust, optimize code for memory and thread efficiency, and test with GTest and Pytest to ensure reliability and performance.
What's included
1 video5 readings1 assignment
1 video•Total 1 minute
- Exploring Existing GPU Models - Overview Video•1 minute
5 readings•Total 50 minutes
- Exploring Existing GPU Models•10 minutes
- Using Thrust to Write GPU Code•10 minutes
- Moving Sequential Code to the GPU•10 minutes
- Testing Your Code with GTest and Pytest•10 minutes
- Using Pytest with Our Code•10 minutes
1 assignment•Total 10 minutes
- GPU Programming Fundamentals•10 minutes
Instructor
Why people choose Coursera for their career
Frequently asked questions
Yes, you can preview the first video and view the syllabus before you enroll. You must purchase the course to access content not included in the preview.
If you decide to enroll in the course before the session start date, you will have access to all of the lecture videos and readings for the course. You’ll be able to submit assignments once the session starts.
Once you enroll and your session begins, you will have access to all videos and other resources, including reading items and the course discussion forum. You’ll be able to view and submit practice assessments, and complete required graded assignments to earn a grade and a Course Certificate.
More questions
Financial aid available,