Primrose: Selecting Container Data Types by their Properties

Container data types are ubiquitous in computer programming, enabling developers to efficiently store and process collections of data with an easy-to-use programming interface. Many programming languages offer a variety of container implementations in their standard libraries based on data structures offering different capabilities and performance characteristics. Choosing the best container for an application is not straightforward, as performance characteristics can change drastically in different scenarios, and real-world performance is not always correlated to theoretical complexity. In this paper, we present Primrose, a language-agnostic tool for selecting the best performing valid container implementation from a set of container data types that satisfy the given properties. Semantic properties allow application developers to specify the expected behaviour of a container as a type refinement, e.g., if the container should only contain unique values (such as a set) or should satisfy the LIFO property of a stack. Semantic properties nicely complement syntactic properties (i.e., traits, interfaces, or type classes), allowing developers to specify a container's programming interface and behaviour without committing to a concrete implementation. Primrose automatically select the set of valid container implementations for which the library specifications, written by the developers of container libraries, satisfies the specified properties. Finally, Primrose ranks the valid library implementations based on their runtime performance. We present our prototype implementation of Primrose that preprocesses annotated Rust code, selecting the best performing container implementation. Primrose is easy to integrate in other programming languages. We encode properties and library specifications into verification conditions in a SMT solver to determine the set of valid container implementations.