arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.05446cs.AIcs.LGcs.PL
收藏

基于GFlowNets的鲁棒调度

Robust Scheduling with GFlowNets

University of Amsterdam(阿姆斯特丹大学);Qualcomm Technologies Netherlands B.V.(高通技术荷兰有限公司);Qualcomm AI Research(高通人工智能研究院);Qualcomm Technologies, Inc.(高通技术公司)

David W. Zhang, Corrado Rainone, Markus Peschl, Roberto Bondesan

摘要:

在计算图中寻找调度操作的最佳方法是一个经典的NP难问题,这是编译器优化的核心。然而,评估目标硬件上的调度的良好性可能非常耗时。传统方法以及以前的机器学习方法通常会优化代理指标,这些指标评估速度很快,但在目标硬件上测试时可能会导致不良的时间表。在这项工作中,我们提出了一种新的方法,通过采样成比例的代理度量使用一种新的GFlowNet方法调度。我们引入了一种技术来控制在推理时间建议的时间表的多样性和良好性之间的权衡,并根据经验证明,当在目标模型上进行测试时,纯优化基线可以导致我们的方法的性能低于标准。此外,我们表明,条件GFlowNet的计算图,使泛化到看不见的调度问题的合成和现实世界的编译器数据集。

英文摘要:

Finding the best way to schedule operations in a computation graph is a classical NP-hard problem which is central to compiler optimization. However, evaluating the goodness of a schedule on the target hardware can be very time-consuming. Traditional approaches as well as previous machine learning ones typically optimize proxy metrics, which are fast to evaluate but can lead to bad schedules when tested on the target hardware. In this work, we propose a new approach to scheduling by sampling proportionally to the proxy metric using a novel GFlowNet method. We introduce a technique to control the trade-off between diversity and goodness of the proposed schedules at inference time and demonstrate empirically that the pure optimization baselines can lead to subpar performance with respect to our approach when tested on a target model. Furthermore, we show that conditioning the GFlowNet on the computation graph enables generalization to unseen scheduling problems for both synthetic and real-world compiler datasets.

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。

↑