BTD: Unleashing the Power of Decompilation for x86 Deep Neural Network Executables

Due to their widespread use on heterogeneous hardware devices, deep learning (DL) models are compiled into executables by DL compilers to fully leverage low-level hardware primitives. This approach allows DL computations to be undertaken at low cost across a variety of computing platforms, including CPUs, GPUs, and various hardware accelerators.

In this presentation, we present BTD (Bin to DNN), a decompiler for deep neural network (DNN) executables....

By: Tianxiang Li , Wenqiang Li , Zhibo Liu , Shuai Wang , …

compilers computing cost cpus deep learning devices gpus hardware low network neural network platforms power x86