Výsledky vyhledávání - "static mapping"

Task Mapping and Scheduling for OpenVX Applications on Heterogeneous Multi/Many-Core Architectures

Autor: Francesco Lumpp, Nicola Bombieri, Stefano Aldegheri, Hiren D. Patel

Publikováno v: IEEE Transactions on Computers. 70:1148-1159

Computer vision applications have stringent performance constraints that must be satisfied when they are run at the edge on programmable low-power embedded devices. OpenVX has emerged as the de-facto reference standard to develop such applications. O

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4b870d2bfc5c7ade87680b22f31f7fcb
https://doi.org/10.1109/tc.2021.3059528

Zobrazit plný text záznamu

Dynamic Analysis for Concurrency Optmisation

Autor: Orton, Indigo

Modern software engineering is, broadly, a continuous activity – many pieces of industrial software are constantly developed, they are never “finished”. This process of constant improvement necessitates small, incremental changes to ensure stab

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0d17b40e12c72e55fdb81badbf1a3d26

Zobrazit plný text záznamu

Placement des tâches temps-réel dur sur des architectures multi-coeurs en réseau sur puce

Autor: Benchehida, Chawki

Publikováno v: Embedded Systems. Université de Lille; Université d'Oran 1, 2021. English. ⟨NNT : ⟩
Embedded Systems. Université de Lille; Université d'Oran 1, 2021. English
Programming Languages [cs.PL]. Université de Lille; Université Oran 1 (Algérie), 2021. English. ⟨NNT : 2021LILUB016⟩

The increasing complexity of modern Cyber-Physical Systems (CPS) requires the usage of powerful embedded computing systems to satisfy their timing constraints. Typically, the system monitors a physical environment using sensors, process and react to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7a79723743c75ffb5ad9af26c3baadd0
https://cnrs.hal.science/tel-03514023

Zobrazit plný text záznamu

Online MPI Process Mapping for Coordinating Locality and Memory Congestion on NUMA Systems

Autor: Mulya Agung, Ryusuke Egawa, Hiroyuki Takizawa, Muhammad Alfian Amrizal

Publikováno v: Supercomputing Frontiers and Innovations. 7

Mapping MPI processes to processor cores, called process mapping, is crucial to achieving the scalable performance on multi-core processors. By analyzing the communication behavior among MPI processes, process mapping can improve the communication lo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::dc2a2165eb4e4f8852a1a9cb6ec63503
https://doi.org/10.14529/jsfi200104

Zobrazit plný text záznamu

On the Task Mapping and Scheduling for DAG-based Embedded Vision Applications on Heterogeneous Multi/Many-core Architectures

Autor: Nicola Bombieri, Stefano Aldegheri, Hiren D. Patel

Publikováno v: DATE

In this work, we show that applying the heterogeneous earliest finish time (HEFT) heuristic for the task scheduling of embedded vision applications can improve the system performance up to 70% w.r.t. the scheduling solutions at the state of the art.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::719fad38f90ceddc2baa2d3f58cda2c3
http://hdl.handle.net/11562/1003226

Zobrazit plný text záznamu

Load balancing-based multi-controller coordinated deployment strategy in software defined optical networks

Autor: Hua Wang, Qi Shao, Xinfeng Fu, Chuan Liu, Jie Zhang, Yongli Zhao

Publikováno v: Optical Fiber Technology. 46:198-204

In software defined optical networks (SDON), a single controller can hardly manage all the optical devices especially in the large-scale networks, while multiple controllers deployed in the network can solve it. Recently, more and more attention has

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2c61b2d66737c07105ce9364f8fb91ee
https://doi.org/10.1016/j.yofte.2018.10.012

Zobrazit plný text záznamu

Run-time mapping algorithm for dynamic workloads using association rule mining

Autor: Sima Sinaei, Omid Fatemi

Publikováno v: Journal of Systems Architecture. 91:1-10

Task mapping exploration plays an important role in the high performance achieved by heterogeneous multi-processor system-on-chip (MPSoC) platforms. The dynamic of application workloads in modern MPSoC-based embedded systems are consistently growing.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::71f69a9aace9174268961b4f39ec32b9
https://doi.org/10.1016/j.sysarc.2018.09.005

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání