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 2602.19762cs.PLcs.AI
收藏

Hexagon-MLIR:一种面向高通神经处理单元(NPUs)的AI编译栈

Hexagon-MLIR: An AI Compilation Stack For Qualcomm's Neural Processing Units (NPUs)

Qualcomm Technologies International, Ltd.(英伟达技术国际有限公司);Qualcomm Technologies, Inc.(英伟达技术公司);Qualcomm India Private Limited(英伟达印度私人有限公司)
Mohammed Javed Absar, Muthu Baskaran, Abhikrant Sharma, Abhilash Bhandari, Ankit Aggarwal, Arun Rangasamy, Dibyendu Das, Fateme Hosseini, Franck Slama, Iulian B… 展开作者

Mohammed Javed Absar, Muthu Baskaran, Abhikrant Sharma, Abhilash Bhandari, Ankit Aggarwal, Arun Rangasamy, Dibyendu Das, Fateme Hosseini, Franck Slama, Iulian Brumar, Jyotsna Verma, Krishnaprasad Bindumadhavan, Mitesh Kothari, Mohit Gupta, Ravishankar Kolachana, Richard Lethin, Samarth Narang, Sanjay Motilal Ladwa, Shalini Jain, Snigdha Suresh Dalvi, Tasmia Rahman, Venkat Rasagna Reddy Komatireddy, Vivek Vasudevbhai Pandya, Xiyue Shi, Zachary Zipper

AI总结:

Hexagon-MLIR是一种基于MLIR框架的开源编译栈,用于加速NPU上的AI工作负载,通过生成mega内核优化数据局部性,减少带宽瓶颈。

摘要:

本文介绍了Hexagon-MLIR,一个面向高通Hexagon神经处理单元(NPU)的开源编译栈,提供了统一的支持,用于将Triton内核和PyTorch模型进行下放。该编译器基于MLIR框架,通过一系列结构化的传递过程,利用NPU架构特性来加速AI工作负载。它使新的Triton内核(手写或来自PyTorch 2.0的子图)能够更快地部署到目标上,通过提供从内核到二进制的自动化编译。通过摄入Triton内核,我们生成了mega内核,以最大化NPU的紧密耦合内存(TCM)中的数据局部性,从而减少基于库方法固有的带宽瓶颈。这一举措通过提供一个基于MLIR的开源编译栈补充了我们的商业工具链,使开发人员能够通过更灵活的方法提升AI编译能力。Hexagon-MLIR仍处于进行中,我们继续在这一努力中添加许多更多的优化和功能。

英文摘要:

In this paper, we present Hexagon-MLIR,an open-source compilation stack that targets Qualcomm Hexagon Neural Processing Unit (NPU) and provides unified support for lowering Triton kernels and PyTorch models . Built using the MLIR framework, our compiler applies a structured sequence of passes to exploit NPU architectural features to accelerate AI workloads. It enables faster deployment of new Triton kernels (hand-written or subgraphs from PyTorch 2.0), for our target by providing automated compilation from kernel to binary. By ingesting Triton kernels, we generate mega-kernels that maximize data locality in the NPU's Tightly Coupled Memory (TCM), reducing the bandwidth bottlenecks inherent in library-based approaches. This initiative complements our commercial toolchains by providing developers with an open-source MLIR-based compilation stack that gives them a path to advance AI compilation capabilities through a more flexible approach. Hexagon-MLIR is a work-in-progress, and we are continuing to add many more optimizations and capabilities in this effort.

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。

↑