Interoperable GPU Kernels as Latency Improver for MEC

Haavisto, Juuso; Riekki, Jukka

doi:10.1109/6gsummit49458.2020.9083751

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As result, we mapped 8 key roles to be carried out by a 6G architecture and 72 possible enabling technologies capable of performing these tasks. In addition, based on this literature review, we also mapped 4 architectural DSs, Approach of 6G Requirements [31], [32] x x x [33][34][35][36] x x x [37][38][39] x x [40][41][42] x x [43][44][45] x x x [46][47][48] x x x x [49], [50] x x x [51][52][53][54] x x x x x x x x [55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70] x [71], [72] x x x x x x [73], [74] x x x x x [75][76][77][78]…”

Section: State-of-art On 6gmentioning

confidence: 99%

A Detailed Relevance Analysis of Enabling Technologies for 6G Architectures

Pivoto,

Rezende,

Facina

et al. 2023

IEEE Access

View full text Add to dashboard Cite

As society evolves as a whole, new demands arise with increasingly demanding prerequisites, consequently requiring more significant effort to be met. Such demands cover emerging applications, such as remote surgeries in Smart Health use cases, whose latency and reliability network requirements cannot be met by current communication systems; or simply improving current applications with more challenging requirements to be achieved, such as increasing the transmission rate in a mobile network, offering Quality of Service (QoS), and consequently, better user experience. Therefore, enabling technologies must be chosen to design an appropriate 6G architecture to address such demands. However, the explosion of emerging applications focused on different scopes and requirements to be met makes choosing these enabling technologies extremely complex and unpredictable. Thus, this article aims to create a methodology for analyzing the relevance of enabling technologies and use it to design an optimal architecture capable of meeting the 6G demands. For this purpose, two methods named as Average (AVG) and Analytic Hierarchy Process (AHP) have been selected, whose objective is to determine the relevance of an enabler for the 6G architecture, taking into account different degrees of influencing variables for this analysis, such as adherence to a certain architectural model; popularity in the research area; degree of innovation; synergy with other enablers; and support for requirements. Each of these methods presents a particular result. In the case of the AVG method, the criteria and variables are evaluated independently, and the arithmetic mean is employed to combine the evaluations into a single measure of suitability. In contrast, the AHP method considers the relative importance of criteria and variables in order to classify an optimal set of enabling technologies capable of fulfilling the key roles to be performed by a 6G architecture, and consequently meeting the main 6G demands. Our evaluation provides a unique perspective on 6G enablers, identifying issues and fostering research for future mobile architectures. The results obtained also provide researchers with the necessary information to stay updated on emerging enabling technologies and their suitability for designing new optimized 6G architectures. INDEX TERMS 6G architectures; 6G enabling technologies; 6G requirements; 6G use cases, AHP, relevance analysis. I. INTRODUCTION S INCE the introduction of 5G, the mobile network architecture has undergone profound transformations that range from the separation of the control and data planes and the adoption of a service-based architecture in the Core Network (CN) [1] to the disaggregation of the Radio

show abstract

Section: State-of-art On 6gmentioning

confidence: 99%

A Detailed Relevance Analysis of Enabling Technologies for 6G Architectures

Pivoto,

Rezende,

Facina

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Further, they all rely on vendor-specific APIs (mostly CUDA) or homemade frameworks limiting their adoption. The closest related work is our paper [19] that studied the Vulkan and SPIR-V powered GPGPU paradigm in light of cold-start times and interoperability. This study shows that the time for starting GPGPU programs is on the millisecond scale, which makes Vulkan-powered GPGPU microservice coldstart latency similar to serverless applications and significantly faster than containers.…”

Section: Related Workmentioning

confidence: 99%

Unleashing GPUs for Network Function Virtualization: an open architecture based on Vulkan and Kubernetes

Haavisto

Cholez

Riekki

2022

NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium

Self Cite

View full text Add to dashboard Cite

General-purpose computing on graphics processing units (GPGPU) is a promising way to speed up computationally intensive network functions, such as performing traffic classification based on machine learning at line speed. Recent studies have focused on integrated graphics units and various performance optimizations to address bottlenecks such as latency. However, these approaches tend to produce architecturespecific binaries and lack the orchestration of functions. A complementary effort would be a GPGPU architecture based on standard and open components, which allows the creation of interoperable and orchestrable network functions.This study describes and evaluates such open architecture based on the cross-platform Vulkan API, in which we execute hand-written SPIR-V code as a network function. We also demonstrate a multi-node orchestration approach for our proposed architecture using Kubernetes. We validate our architecture by executing SPIR-V code performing traffic classification with random forest inference. We test this application both on discrete and integrated graphics cards and on x86 and ARM. We find that in all cases the GPUs are faster than the Cython code.

show abstract

Interoperable GPU Kernels as Latency Improver for MEC

Cited by 2 publications

References 9 publications

A Detailed Relevance Analysis of Enabling Technologies for 6G Architectures

A Detailed Relevance Analysis of Enabling Technologies for 6G Architectures

Unleashing GPUs for Network Function Virtualization: an open architecture based on Vulkan and Kubernetes

Contact Info

Product

Resources

About