一句话：提出 TLP，一种用于张量程序调优的深度学习成本模型，旨在缓解特征提取依赖专家知识和跨硬件不可用问题。
张量程序调优是非凸目标优化问题，基于搜索的方法已被证明有效，而成本模型是其核心。现有基于深度学习的成本模型虽优于其他方法，但仍存在两个主要问题：其特征提取严重依赖硬件体系结构方面的专家知识，且提取的特征往往不理想，并需分别考虑 CPU 与 GPU；此外，在一个硬件平台上训练的成本模型通常难以在另一平台上表现良好，即跨硬件不可用。TLP 作为一种基于深度学习的成本模型，针对上述问题展开设计，目标是提升特征提取的自动化程度与跨硬件泛化能力。给定摘要未报告具体网络结构、训练方式和量化实验结果。
Tensor program tuning is a non-convex objective optimization problem, to which search-based approaches have proven to be effective. At the core of the search-based approaches lies the design of the cost model. Though deep learning-based cost models perform significantly better than other methods, they still fall short and suffer from the following problems. First, their feature extraction heavily relies on expert-level domain knowledge in hardware architectures. Even so, the extracted features are often unsatisfactory and require separate considerations for CPUs and GPUs. Second, a cost model trained on one hardware platform usually performs poorly on another, a problem we call cross-hardware unavailability.
@inproceedings{paperbot10048,
title = {TLP: A Deep Learning-Based Cost Model for Tensor Program Tuning},
author = {Yi Zhai and Yu Zhang and Shuo Liu and Xiaomeng Chu and Jie Peng and Jianmin Ji and Yanyong Zhang},
booktitle = {ASPLOS},
year = {2023},
doi = {10.1145/3575693.3575737}
}