Efficient Embedded Software Migration towards Clusterized Distributed-Memory Architectures

Rafael Garibotti 1 Anastasiia Butko 1 Luciano Ost 2 Abdoulaye Gamatié 1 Gilles Sassatelli 1 Chris Adeniyi-Jones 3
1 ADAC - ADAptive Computing
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
2 University of Leicester
3 ARM - ARM Ltd [Cambridge]
Abstract : A large portion of existing multithreaded embedded software has been programmed according to symmetric shared memory platforms where a monolithic memory block is shared by all cores. Such platforms accommodate popular parallel programming models such as POSIX threads and OpenMP. However with the growing number of cores in modern manycore embedded architectures, they present a bottleneck related to their centralized memory accesses. This paper proposes a solution tailored for an efficient execution of applications defined with shared-memory programming models onto on-chip distributed-memory multicore architectures. It shows how performance, area and energy consumption are significantly improved thanks to the scalability of these architectures. This is illustrated in an open-source realistic design framework, including tools from ASIC to microkernel.
Keywords : Instruction sets Coherence Hardware Programming Multicore processing
Document type :
Journal articles
Complete list of metadatas
https://hal-lirmm.ccsd.cnrs.fr/lirmm-01385656
Contributor : Abdoulaye Gamatié <>
Submitted on : Friday, October 21, 2016 - 5:36:19 PM
Last modification on : Saturday, November 9, 2019 - 1:30:02 PM

Links full text

openaccess

Identifiers

Collections

LIRMM | CNRS | LIRMM_MIC | MIC | MIPS | UNIV-MONTPELLIER | ADAC

Citation

Rafael Garibotti, Anastasiia Butko, Luciano Ost, Abdoulaye Gamatié, Gilles Sassatelli, et al.. Efficient Embedded Software Migration towards Clusterized Distributed-Memory Architectures. IEEE Transactions on Computers, Institute of Electrical and Electronics Engineers, 2015, 65 (8), pp.2645-2651. ⟨10.1109/TC.2015.2485202⟩. ⟨lirmm-01385656⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

247

Contact

Informations

CCSD