Rethinking Compilers in the Rise of Machine Learning and AI

Recent years have witnessed some influential progresses in Machine Learning (ML) and Artificial Intelligence (AI). The progresses may lead to some significant changes to future programming. Many programs, for instance, may be not code written in some specially designed programming languages, but high-level user intentions expressed in natural languages. Deep Learning-based software, despite the difficulties in interpreting their results, may continue its rapid growth in the software market and its influence in people's everyday life. This talk will first examine the implications of these changes to compiler research, and then discuss the potential opportunities that ML and AI could bring to possibly transform the field of compiler research. Specifically, the talk will focus on the possibilities for ML and AI to help reveal the high-level semantics and attributes of software components that traditional compiler technology cannot do, and hence, open important opportunities for high-level large-scoped code reasoning and optimizations-a direction that has some tremendous potential but has been beyond the reach of traditional compiler technology. The talk will discuss how ML and AI may help break the "abstraction wall"-barriers formed by layers of abstractions in modern software-for program analysis and optimizations, and how ML and AI may transform the way in which high-level user intentions get translated into low-level code implementations. The talk will conclude with a list of grand challenges and possible research directions for future compiler constructions.