An MLIR-Based Compilation Framework for Control Flow Management on Coarse Grained Reconfigurable Arrays

TL;DR

This paper introduces an MLIR-based compilation framework that effectively manages control flow on CGRAs, enabling broader application support and achieving significant speedups over existing methods.

Contribution

The paper presents a novel, modular compilation framework with transformation passes and a new mapping methodology for control flow on CGRAs, independent of hardware specifics.

Findings

Up to 2.1X speedup over state-of-the-art approaches

Supports arbitrary control flows on abstract CGRA meshes

Enables hardware-agnostic control flow management

Abstract

Coarse Grained Reconfigurable Arrays (CGRAs) present both high flexibility and efficiency, making them well-suited for the acceleration of intensive workloads. Nevertheless, a key barrier towards their widespread adoption is posed by CGRA compilation, which must cope with a multi-dimensional space spanning both the spatial and the temporal domains. Indeed, state-of-the-art compilers are limited in scope as they mostly deal with the data flow of applications, while having little or no support for control flow. Hence, they mostly target the mapping of single loops and/or delegate the management of control flow divergences to ad-hoc hardware units. Conversely, in this paper we show that control flow can be effectively managed and optimized at the compilation level, allowing for a broad set of applications to be targeted while being hardware-agnostic and achieving high performance. We embody our methodology in a modular compilation framework consisting of transformation and optimization passes, enabling support for applications with arbitrary control flows running on abstract CGRA meshes. We also introduce a novel mapping methodology that acts as a compilation back-end, addressing the limitations in available CGRA hardware resources and guaranteeing a feasible solution in the compilation process. Our framework achieves up to 2.1X speedups over state-of-the-art approaches, purely through compilation optimizations.