A Distributed Framework for Low-Latency OpenVX over the RDMA NoC of a Clustered Manycore - Université de Rennes Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

A Distributed Framework for Low-Latency OpenVX over the RDMA NoC of a Clustered Manycore

Résumé

OpenVX is a standard proposed by the Khronos group for cross-platform acceleration of computer vision and deep learning applications. OpenVX abstracts the target processor architecture complexity and automates the implementation of processing pipelines through high-level optimizations. While highly efficient OpenVX implementations exist for shared memory multi-core processors, targeting OpenVX to clustered manycore processors appears challenging. Indeed, such processors comprise multiple compute units or clusters, each fitted with an on-chip local memory shared by several cores. This paper describes an efficient implementation of OpenVX that targets clustered manycore processors. We propose a framework that includes computation graph analysis, kernel fusion techniques, RDMA-based tiling into local memories, optimization passes, and a distributed execution runtime. This framework is implemented and evaluated on the 2nd-generation Kalray MPPA (R) clustered manycore processor. Experimental results show that super-linear speed-ups are obtained for multi-cluster execution by leveraging the bandwidth of on-chip memories and the capabilities of asynchronous RDMA engines.
Fichier principal
Vignette du fichier
PID5495673.pdf (161.32 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02049414 , version 1 (08-04-2019)

Identifiants

Citer

Julien Hascoet, Benoît Dupont de Dinechin, Karol Desnos, Jean-Francois Nezan. A Distributed Framework for Low-Latency OpenVX over the RDMA NoC of a Clustered Manycore. IEEE High Performance Extreme Computing Conference (HPEC 2018), Sep 2018, Waltham, MA, United States. ⟨10.1109/hpec.2018.8547736⟩. ⟨hal-02049414⟩
95 Consultations
334 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More