To accelerate CNN inference, existing deep learning frameworks focus on optimizing intra-operator parallelization. However, a single operator can no longer fully utilize the available parallelism given the rapid advances in high-performance hardware, resulting in a large gap between the peak performance and the real performance. This performance gap is more severe under smaller batch sizes. In this work, we extensively study the parallelism between operators and propose Inter-Operator Scheduler (IOS) to automatically schedule multiple operators' parallel execution through a novel dynamic programming algorithm. IOS consistently outperforms state-of-the-art libraries (e.g., TensorRT) by 1.1 to 1.5x on modern CNN benchmarks. The code to reproduce each experiment is available at: https://github.com/mit-han-lab/inter-operator-scheduler.
@article{arxiv.2011.01302,
title = {IOS: Inter-Operator Scheduler for CNN Acceleration},
author = {Yaoyao Ding and Ligeng Zhu and Zhihao Jia and Gennady Pekhimenko and Song Han},
journal= {arXiv preprint arXiv:2011.01302},
year = {2021}
}