Hardware.jl - An MLIR-based Julia HLS Flow (Work in Progress)
By: Benedict Short, Ian McInerney, John Wickerson
Potential Business Impact:
Makes computer chips faster for science programs.
Co-developing scientific algorithms and hardware accelerators requires domain-specific knowledge and large engineering resources. This leads to a slow development pace and high project complexity, which creates a barrier to entry that is too high for the majority of developers to overcome. We are developing a reusable end-to-end compiler toolchain for the Julia language entirely built on permissively-licensed open-source projects. This unifies accelerator and algorithm development by automatically synthesising Julia source code into high-performance Verilog.
Similar Papers
Building Bridges: Julia as an MLIR Frontend
Programming Languages
Lets programmers easily make smart computer programs.
From PyTorch to Calyx: An Open-Source Compiler Toolchain for ML Accelerators
Hardware Architecture
Turns AI code into computer chips.
Towards An Approach to Identify Divergences in Hardware Designs for HPC Workloads
Hardware Architecture
Builds faster computer parts for science and AI.