More Speed and Simplicity - Practical Data-Oriented Design in C++

Learn Data-Oriented Design (DOD) principles in this comprehensive conference talk that demonstrates how prioritizing data layout over traditional object-oriented approaches can deliver significant performance improvements and code simplification. Follow along as Vittorio Romeo guides you through a step-by-step refactoring process, transforming conventional OOP design into a data-first approach that leverages cache efficiency for better performance. Discover how data access patterns directly influence execution speed and explore key techniques including Structure-of-Arrays (SoA) versus Array-of-Structures (AoS) implementations through practical benchmarks and performance measurements. Examine how DOD can complement rather than replace object-oriented programming, while learning to create robust C++ abstractions that maintain both complexity management and performance optimization. Understand the pragmatic trade-offs between DOD's strengths in performance and data logic simplicity against its potential limitations, and master C++ techniques for building safe, expressive APIs that handle both aspects effectively. Gain insights into making data processing loops more direct and conceptually clearer while maintaining code readability and maintainability in modern C++ development.