The LLVM Compiler Infrastructure, Chris Lattner and Vikram Adve, 2004CGO '04: Proceedings of the 2nd Annual IEEE/ACM International Symposium on Code Generation and Optimization (IEEE Computer Society)DOI: 10.1109/CGO.2004.1281665 - 介绍了LLVM IR的设计与动机,这是一种广泛使用的通用IR,是衡量传统IR的标准。
MLIR: A Compiler Infrastructure for the End of Moore's Law, Chris Lattner, Jacques Pienaar, River Riddle, Albert Cohen, Alan Mycroft, Oleksandr Zinenko, Nicolas Vasilache, and Ryan Lee, 2021CGO '21: Proceedings of the 2021 International Symposium on Code Generation and Optimization (Association for Computing Machinery (ACM))DOI: 10.1145/3441776.3448268 - 介绍了MLIR,阐述其多层次、可扩展的设计如何旨在克服传统IR在机器学习等领域专用应用中的局限性。
TVM: An Automated End-to-End Optimizing Compiler for Deep Learning, Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, Arvind Krishnamurthy, 201813th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18) (USENIX Association) - 介绍了TVM,一个深度学习编译器,它解决了本节中讨论的许多挑战,例如张量操作、异构硬件以及优化所需的高级语义信息。