Rammer: Enabling Holistic Deep Learning Compiler ... - USENIX

This paper is included in the Proceedings of the 14th USENIX Symposium on Operating Systems Design and ImplementationNovember 4 6, 2020978-1-939133-19-9 Open access to the Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation is sponsored by USENIXR ammer: Enabling Holistic Deep Learning Compiler Optimizations with rTask sLingxiao Ma, Peking University and Microsoft Research; Zhiqiang Xie, ShanghaiTech University and Microsoft Research; Zhi Yang, Peking University; Jilong Xue, Youshan Miao, Wei Cui, Wenxiang Hu, Fan Yang, Lintao Zhang, and Lidong Zhou, Microsoft : Enabling Holistic Deep Learning Compiler Optimizations withrTasksLingxiao Ma Zhiqiang Xie Zhi Yang Jilong Xue Youshan Miao Wei Cui Wenxiang Hu Fan Yang Lintao Zhang Lidong Zhou Peking University ShanghaiTech University Microsoft ResearchAbstractPerforming Deep Neural Network (DNN) computation onhardware accelerators efficiently is challenging.

software compiler, RAMMER redefines a DNN operator as an rTask-operator or rOperator.An rOperator consists of multiple independent, homogeneous rTasks, each is a mini-mum schedulable unit runs on a single execution unit of an accelerator (e.g., a streaming multiprocessor SM in a GPU). Thus, rTask as the fine-grained intra-operator information is

Loading..

Tags:

  Unit, Software

Information

Related search queries