Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to build efficient numerical integrators using modern C++ techniques in this conference talk from CppCon 2024. Explore how C++23 and C++26 features, including reflection, can be leveraged to create generic, high-performance implementations of Runge-Kutta methods, linear multistep methods, and general linear methods. Discover how to combine algorithmic building blocks to generate diverse numerical integrators from first principles, with practical applications in high-performance computing and scientific simulations. Master parallelization strategies for distributed and heterogeneous computing environments, while examining real-world applications through an N-body cosmology simulation. Gain insights into compiler optimization techniques for selecting optimal integrators based on mathematical properties and deriving new integrators at compile-time. Apply the presented methodology beyond numerical integration to improve software architecture in technical computing contexts, with reproducible code examples that can be immediately implemented in your own projects.
