Model for partitioning slip patterns at triple junctions of grains
Sign Up to like & getrecommendations! Published in 2017 at "International Journal of Engineering Science"
DOI: 10.1016/j.ijengsci.2017.02.007
Abstract: Abstract A rate insensitive model based on interfacial compatibility of plastic strains is formulated to predict partitioning slip patterns in interaction of polyhedral grains at triple junctions. The model imposes macroscopic deformation on a skeleton… read more here.
Keywords: slip; slip patterns; model partitioning; triple junctions ... See more keywords
Resource Aware Deep Learning Model Partitioning and Allocation for Inference Task in Clusters With Heterogeneous Graphics Processing Units
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Cloud Computing"
DOI: 10.1109/tcc.2025.3626959
Abstract: Deep learning (DL) models have rapidly evolved, and their scales have become larger. Pipeline parallelism is used to execute a large-scale DL model. In pipeline parallelism, DL models are partitioned and allocated graphics processing units… read more here.
Keywords: resource; clusters heterogeneous; service; model ... See more keywords
Distributed DNN Inference With Fine-Grained Model Partitioning in Mobile Edge Computing Networks
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Mobile Computing"
DOI: 10.1109/tmc.2024.3357874
Abstract: Model partitioning is a promising technique for improving the efficiency of distributed inference by executing partial deep neural network (DNN) models on edge servers (ESs) or Internet-of-Things (IoT) devices. However, due to heterogeneous resources of… read more here.
Keywords: dnn inference; fine grained; inference; model partitioning ... See more keywords