PLMar 20
Is It a Good Idea to Build an HLS Tool on Top of MLIR? Experience from Building the Dynamatic HLS Compiler
arXiv:2603.1985666.3h-index: 2Has Code
AI Analysis
This addresses compiler infrastructure choices for HLS tool developers, but it appears incremental as it evaluates an existing framework rather than introducing new methods.
The paper investigates whether MLIR is an effective compiler infrastructure for high-level synthesis (HLS) by sharing experiences from building the Dynamatic HLS compiler, but it does not provide concrete results or numbers.
When the MLIR project was first introduced, it promised to address the issues that the HLS community had with the LLVM project. But is this really the case, and is MLIR the "right"/"best" compiler infrastructure for HLS? We here share our experiences based on the development of Dynamatic (github.com/EPFL-LAP/dynamatic).