OSDI '23 - Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning

OSDI '23 - Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning

Chen Zhang, Tsinghua University, Lingxiao Ma, Microsoft Research, Jilong Xue, Microsoft Research, Yining Shi, Peking University & Microsoft Research, Ziming Miao, Microsoft Research, Fan Yang, Microsoft Research, Jidong Zhai, Tsinghua University, Zhi Yang, Peking University, Mao Yang, Microsoft Research

With the growing complexity of deep neural networks (DNNs), developing DNN programs with intricate control flow logic (e.g., loops, branches, and recursion) has become increasingly essential. However, executing …

amp chen control deep learning dynamic fan flow microsoft research shi tsinghua university university