arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.09463cs.SEcs.ARcs.PL
收藏

Hardware.jl——一个基于MLIR的Julia高层次综合流程(进行中)

Hardware.jl - An MLIR-based Julia HLS Flow (Work in Progress)

Benedict Short, Ian McInerney, John Wickerson

AI总结:

本文介绍了一个基于MLIR的Julia高层次综合流程Hardware.jl,通过将Julia源码自动综合为Verilog,降低科学算法与硬件加速器协同开发的门槛和复杂度。

摘要:

共同开发科学算法与硬件加速器需要领域特定知识和大量工程资源。这导致开发节奏缓慢、项目复杂度高,从而形成了一道大多数开发者难以跨越的入门门槛。我们正在为Julia语言开发一个可复用的端到端编译器工具链,该工具链完全构建在宽松许可的开源项目之上。它通过将Julia源代码自动综合为高性能Verilog,统一了加速器开发与算法开发。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑