Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 20 for “"In-network Computing"”.
-
Towards practical in-network computing
In-network computing is an emerging computing paradigm that promises significant potentials in continuing to accelerate datacenter applications in the post-Dennard scaling era. With the emergence of various programmable NICs and switches, a plethora of ideas have been proposed to offload functions …
-
Accelerating Audio Data Analysis with In-Network Computing
… massive connections and massive data handling. This will imply a growing demand for computing in communication networks due to network softwarization. Moreover, digital transformation will host very sensitive verticals, requiring high end-to-end reliability and low latency. Accordingly, the …
-
In-network computing : overcoming constraints, failures, and configuration challenges
Programmable switches are networking forwarding devices that allow customized, stateful functionalities to run at line rate. Unlike fixed-functionality switches, pro grammable switches offer higher versatility and innovation potential. The advan tages of programmable switches have led researchers …
-
In-network computing : overcoming constraints, failures, and configuration challenges
Programmable switches are networking forwarding devices that allow customized, stateful functionalities to run at line rate. Unlike fixed-functionality switches, programmable switches offer higher versatility and innovation potential. The advantages of programmable switches have led researchers to …
-
An Ontology-Based Model for In-Network Computing Components Description and Discovery
In-Network Computing (INC) refers to the process that enables the distribution of computing tasks across the network instead of computing on servers outside the network. Advances in programmable hardware allow computations directly within network devices, such as switches and Smart Network …
-
A hybrid NFV/In-Network Computing MANO Architecture for provisioning Holographic Applications
The emergence of innovative holographic applications, such as holographic concerts, have requirements on network infrastructure such as high bandwidth and ultra-low latency. As demonstrated in recent research, for efficient provisioning of these types of applications, we require a Hybrid Network …
-
Towards in-network machine learning on programmable network devices
<p>Machine learning (ML) services have entered various aspects of our daily lives and industrial production, with most of these services being delivered over networks. The escalating demand for ML services has resulted in increased processing requirements and a growing volume of data. This poses …
-
Architectures and Algorithms for Content Delivery in Future Networks
Traditional Content Delivery Networks (CDNs) built with traditional Internet technology are less and less able to cope with today’s tremendous content growth. Enhancing infrastructures with storage and computation capabilities may help to remedy the situation. Information-Centric Networks (ICNs), a …
-
A cross-stack, network-centric architectural design for next-generation datacenters
… cross-layer datacenter architecture based on in-network computing and near-memory processing paradigms. The proposed datacenter architecture is built atop two principles: (1) utilizing commodity, off-the-shelf hardware (i.e., processor, DRAM, and network devices) with minimal changes to their …
-
On the Design of Future Communication Systems with Coded Transport, Storage, and Computing
Communication systems are experiencing a fundamental change. There are novel applications that require an increased performance not only of throughput but also latency, reliability, security, and heterogeneity support from these systems. To fulfil the requirements, future systems understand …
-
LINCE : a terabit-scale hybrid virtualization engine for distributed applications
The rise of data-intensive, latency-sensitive applications necessitates a shift towards InNetwork Computing (INC). However, a significant gap persists: existing academic FPGAbased platforms lack terabit-scale performance, while commercial ASICs lack the flexibility and virtualization required for …
-
Accelerating distributed neural network training with network-centric approach
Distributed training of Deep Neural Networks (DNN) is an important technique to reduce the training time of large DNNs for a wide range of applications. In existing distributed training approaches, however, the communication time to periodically exchange parameters (i.e., weights) and gradients …
-
Traffic Prediction on SmartNICs Using Artificial Intelligence/Machine Learning
In high-performance computing (HPC) systems, fluctuations in network traffic can degrade application performance, leading to costly re-transmissions and memory bandwidth consumption. Emerging SmartNIC technologies present a promising solution for mitigating these issues by intelligently managing …
-
Network Utility Maximization for Resource Scheduling and Learning
Network Utility Maximization (NUM) serves as a theoretical control framework for resource allocation problems in modern communication systems, ranging from cellular downlinks to heterogeneous multi-hop wireless networks. NUM frameworks mainly seek to maximize global utility functions subject to …
-
Efficient Interconnection Network Design for Heterogeneous Architectures
The onset of big data and deep learning applications, mixed with conventional general-purpose programs, have driven computer architecture to embrace heterogeneity with specialization. With the ever-increasing interconnected chip components, future architectures are required to operate under a …
-
Design of Energy-Efficient and High-Throughput Reconfigurable Systems through Cross-Layer Approximation
… performance, and throughput have long driven computing design, but the slowdown of technology scaling and microarchitectural gains has made conventional approaches insufficient. Approximate Computing, particularly Cross-Layer Approximation, leverages the error tolerance of many modern …
-
Scaling Up The Performance of Distributed Key-ValueStores Using Emerging Technologies for Big DataApplications
The explosion in the amount of data with the development of the internet and cloud computing prompted much research to develop systems that are able to store and process this data efficiently. As data is generated by different sources with un-unified structures, NoSQL databases emerged as a …
-
Communication-centric cross-stack acceleration for distributed machine learning
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-04-12 without embargo terms