A Dynamically Scheduled HLS Flow in MLIR

In High-Level Synthesis (HLS), we consider abstractions that span from software to hardware and target heterogeneous architectures. Therefore, managing the complexity introduced by this is key to implementing good, maintainable, and extendible HLS compilers. Traditionally, HLS flows have been built on top of software compilation infrastructure such as LLVM, with hardware aspects of the flow existing peripherally to the core of the compiler. Through this work, we aim to show that MLIR, a compiler infrastructure with a focus on domain-specific intermediate representations (IR), is a better infrastructure for HLS compilers. Using MLIR, we define HLS and hardware abstractions as first-class citizens of the compiler, simplifying analysis, transformations, and optimization. To demonstrate this, we present a C-to-RTL, dynamically scheduled HLS flow. We find that our flow generates circuits comparable to those of an equivalent LLVM-based HLS compiler. Notably, we achieve this while lacking key optimization passes typically found in HLS compilers and through the use of an experimental front-end. To this end, we show that significant improvements in the generated RTL are but low-hanging fruit, requiring engineering effort to attain. We believe that our flow is more modular and more extendible than comparable open-source HLS compilers and is thus a good candidate as a basis for future research. Apart from the core HLS flow, we provide MLIR-based tooling for C-to-RTL cosimulation and visual debugging, with the ultimate goal of building an MLIR-based HLS infrastructure that will drive innovation in the field.