A programming language for parallel event-driven development

Abstract

Recently, event-oriented programming frameworks have surfaced as a solution to highly scalable network applications. This model as been adopted under many languages resulting in frameworks such as Node.js, Gevent and EventMachine. These frameworks are capable of handling many concurrent requests by using asynchronous IO. However, in order to make use all available cores, parallelism is exploited by creating multiple instances of the same application. Under this solution instances don’t share memory making synchronization mechanisms required. The same problem applies when using the actor model for concurrency. The EVE framework provides support for event-oriented programming under a shared-memory model. It encompasses the EVE language definition, its compiler and a runtime system capable of executing the resulting applications. Using our model, the programmer divides the application logic into tasks and each task indicates what variables it can access. The runtime schedules compatible tasks to multiple cores using a work-stealing algorithm for load balancing. In this work, we present a formal description of the language and it’s runtime, including their operational semantics. Our benchmarks indicate that our solution delivers the best performance on IO heavy problems when compared to existing of-the-shelf solutions and performance comparable to the state-of-the-art architectures for CPU-bounded applications.