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⟩
100 Consultations
349 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More