SubFlow: A dynamic induced-subgraph strategy toward real-time DNN inference and training
We introduce SubFlow-a dynamic adaptation and execution strategy for a deep neural
network (DNN), which enables real-time DNN inference and training. The goal of SubFlow is …
network (DNN), which enables real-time DNN inference and training. The goal of SubFlow is …
Pipelined data-parallel CPU/GPU scheduling for multi-DNN real-time inference
Deep neural networks (DNNs) have been showing significant success in various
applications, such as autonomous driving, mobile devices, and Internet of Things. Although …
applications, such as autonomous driving, mobile devices, and Internet of Things. Although …
Blastnet: Exploiting duo-blocks for cross-processor real-time dnn inference
In recent years, Deep Neural Network (DNN) has been increasingly adopted by a wide
range of time-critical applications running on edge platforms with heterogeneous …
range of time-critical applications running on edge platforms with heterogeneous …
Dynamic adaptive DNN surgery for inference acceleration on the edge
Recent advances in deep neural networks (DNNs) have substantially improved the accuracy
and speed of a variety of intelligent applications. Nevertheless, one obstacle is that DNN …
and speed of a variety of intelligent applications. Nevertheless, one obstacle is that DNN …
Zeus: Understanding and optimizing {GPU} energy consumption of {DNN} training
Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training Page 1 This
paper is included in the Proceedings of the 20th USENIX Symposium on Networked Systems …
paper is included in the Proceedings of the 20th USENIX Symposium on Networked Systems …
Dynamic-ofa: Runtime dnn architecture switching for performance scaling on heterogeneous embedded platforms
Mobile and embedded platforms are increasingly required to efficiently execute
computationally demanding DNNs across heterogeneous processing elements. At runtime …
computationally demanding DNNs across heterogeneous processing elements. At runtime …
Cavs: An efficient runtime system for dynamic neural networks
Recent deep learning (DL) models are moving more and more to dynamic neural network
(NN) architectures, where the NN structure changes for every data sample. However …
(NN) architectures, where the NN structure changes for every data sample. However …
Inference time optimization using branchynet partitioning
RG Pacheco, RS Couto - 2020 IEEE Symposium on Computers …, 2020 - ieeexplore.ieee.org
Deep Neural Network (DNN) inference requires high computation power, which generally
involves a cloud infrastructure. However, sending raw data to the cloud can increase the …
involves a cloud infrastructure. However, sending raw data to the cloud can increase the …
Aspen: Breaking operator barriers for efficient parallelization of deep neural networks
Abstract Modern Deep Neural Network (DNN) frameworks use tensor operators as the main
building blocks of DNNs. However, we observe that operator-based construction of DNNs …
building blocks of DNNs. However, we observe that operator-based construction of DNNs …
Towards real-time cooperative deep inference over the cloud and edge end devices
Deep neural networks (DNNs) have been widely used in many intelligent applications such
as object recognition and automatic driving due to their superior performance in conducting …
as object recognition and automatic driving due to their superior performance in conducting …