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 24 for “"SmartNIC"”.

  1. SNIC-DSM: SmartNIC based DSM Infrastructure for Heterogeneous-ISA Machines

    … high-end x86 servers with attached SmartNICs and SmartSSDs that incorporate general-purpose CPUs, typically of the RISC ISA family (e.g., ARM, RISC-V). To alleviate resource congestion on server computing nodes, application workloads can be scaled-out across server x86 CPUs and …

    vt Repository record for SNIC-DSM: SmartNIC based DSM Infrastructure for Heterogeneous-ISA Machines (opens in a new tab)

  2. VNS: Verilog Network Switch for an open-source FPGA SmartNIC cloud development platform

    Modern cloud providers rely on proprietary SmartNIC architectures, such as Amazon's Nitro system, to offload networking, storage, and security functions from the host CPU. These designs achieve this using technologies like Single-Root I/O Virtualization (SR-IOV) to bypass the hypervisor data path, …

    bu Repository record for VNS: Verilog Network Switch for an open-source FPGA SmartNIC cloud development platform (opens in a new tab)

  3. Software and hardware codesign of SmartNIC-based heterogeneous HPC clusters with machine learning case studies

    … Advanced network interface cards, known as SmartNICs, have emerged to mitigate network challenges in scale-out data centers. The placement of SmartNICs as a network-facing computational component within a node allows them to efficiently manage communication between different parts of the …

    bu Repository record for Software and hardware codesign of SmartNIC-based heterogeneous HPC clusters with machine learning case studies (opens in a new tab)

  4. Traffic Prediction on SmartNICs Using Artificial Intelligence/Machine Learning

    … and memory bandwidth consumption. Emerging SmartNIC technologies present a promising solution for mitigating these issues by intelligently managing network resources through machine learning models. However, SmartNIC deployment introduces resource constraints that challenge the …

    queens Repository record for Traffic Prediction on SmartNICs Using Artificial Intelligence/Machine Learning (opens in a new tab)

  5. Accelerating Networked Systems with Programmable and Tightly-Coupled NICs

    … hardware offloads are limited in flexibility, SmartNIC devices with an integrated system-on-chip (SoC) are fully programmable. However, achieving efficiency improvements using SmartNICs depends on specific architectural features, and efficient interfaces which only some devices provide. …

    washington Repository record for Accelerating Networked Systems with Programmable and Tightly-Coupled NICs (opens in a new tab)

  6. Building Distributed Systems Using Programmable Networks

    … suitable computations to a PNF device (i.e., SmartNIC, reconfigurable switch, or network accelerator), one can reduce request serving latency, save end-host CPU cores, and enable efficient traffic control. In this dissertation, we present three frameworks for building PNF-enabled distributed …

    washington Repository record for Building Distributed Systems Using Programmable Networks (opens in a new tab)

  7. Enhancing Multi-Tenant Disaggregated Storage Systems with H/W Innovations

    … that leverage hardware innovations—specifically, SmartNICs and NVMe SSDs—to improve performance, fairness, and adaptability in disaggregated storage systems. The first part introduces Gimbal, a software storage switch that enables multi-tenant-aware scheduling and congestion control on …

    washington Repository record for Enhancing Multi-Tenant Disaggregated Storage Systems with H/W Innovations (opens in a new tab)

  8. Akcelerace síťových aplikací pomocí RTE Flow

    … síťové funkce pomocí NVIDIA ConnectX SmartNIC a DPDK RTE Flow API. Cíle zahrnují: měření výkonu hardwarových offloadů, dynamickou správu pravidel přes šablony a stavové zpracování pomocí sledování spojení. Byly vyvinuty tři aplikace – vysokorychlostní IP filtr s asynchronní správou …

    brno-tech Repository record for Akcelerace síťových aplikací pomocí RTE Flow (opens in a new tab)

  9. Využití nástrojů a metod řízení rizik v prostředí start-upu

    … na trh inteligentných sieťových adaptérov (SmartNIC).Teoretická časť definuje špecifiká riadenia rizík v deep-tech sektore a metodiku 4T. Analytická časť implementuje nástroje PESTLE, McKinsey 7S a kvantitatívne hodnotenie rizík. Návrhová časť prezentuje komplexný súbor opatrení, ktorý …

    brno-tech Repository record for Využití nástrojů a metod řízení rizik v prostředí start-upu (opens in a new tab)

  10. Architecting Offloading at Scale for Key-Value Systems

    … that provisions live migration management on SmartNIC hardware to significantly lower migration time and avoid user performance interference. PYROCUMULUS answers the question of how to migrate for highly optimized key-value systems with a SmartNIC-friendly data consistency algorithm and …

    toronto-retro Repository record for Architecting Offloading at Scale for Key-Value Systems (opens in a new tab)

  11. UniNet: accelerating the container network data plane in IaaS clouds

    … To address this, we present UniNet, a SmartNIC-based solution that offloads container-level network tunneling. We designed UniNet to be compatible with leading Container Network Interfaces (CNIs). This approach involves three key elements: (1) transforming VF-based NICs into a container …

    uiuc Repository record for UniNet: accelerating the container network data plane in IaaS clouds (opens in a new tab)

  12. Taming latency in data center applications

    … DYAD defines the abstraction needed from the SmartNIC and the operations performed on the application running on the host processor. With the resulting consensus mechanism, the host processor handles only the client requests on the host processor in the normal case and the disappropriate …

    gatech Repository record for Taming latency in data center applications (opens in a new tab)

  13. End-to-end Support for In-network Acceleration of Dynamically Chained Parametric Tasks

    … linked libraries to containerized microservices— SmartNICs allocate dedicated hardware-accelerator resources per tenant, evoking the preDLL era where common functions were duplicated in every program. This wastes precious hardware resources in multi-tenant environments where applications often …

    gatech Repository record for End-to-end Support for In-network Acceleration of Dynamically Chained Parametric Tasks (opens in a new tab)

  14. DWT in P4 : periodicity detection in the data plane

    … the algorithm, utilizing the Netronome NFP-4000 SmartNIC, and demonstrates minimal throughput overhead, with less than 1% impact on average-sized packets, while operating within the constraints of limited data plane resources. In addition to the implementation, we showcase a practical application …

    brazil-ufrgs Repository record for DWT in P4 : periodicity detection in the data plane (opens in a new tab)

  15. Online learning on the programmable dataplane

    … (non-neural) approaches to take advantage of the SmartNIC compute model and make use of rich device local state. I show that data-driven solutions still require great care to correctly design, but with the right domain expertise they can improve on pathological cases in DDoS defence, such as …

    glasgow Repository record for Online learning on the programmable dataplane (opens in a new tab) Download PDF for Online learning on the programmable dataplane (opens in a new tab)

  16. Segurança de DNS com alto desempenho: uma abordagem baseada em eBPF/XDP

    … função hash FNV-1a; e (v) XDP com offload para SmartNIC utilizando DJB2. A abordagem diferencia-se de trabalhos anteriores por adotar uma estratégia determinística baseada em consulta eficiente a listas de domínios maliciosos, privilegiando a previsibilidade de desempenho, em contraste com …

    brazil-ufrgs Repository record for Segurança de DNS com alto desempenho: uma abordagem baseada em eBPF/XDP (opens in a new tab)

Page 1 of 2