Timezone: »

IOS: Inter-Operator Scheduler for CNN Acceleration
Yaoyao Ding · Ligeng Zhu · Zhihao Jia · Gennady Pekhimenko · Song Han

Wed Apr 07 01:30 PM -- 01:50 PM (PDT) @

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.

Author Information

Yaoyao Ding (University of Toronto)
Ligeng Zhu (MIT)
Zhihao Jia (Facebook)
Gennady Pekhimenko (University of Toronto)
Song Han (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors