Skip to Main content Skip to Navigation

Méthodologie de placement d'algorithmes de traitement d'images sur architecture massivement parallèle

Abstract : In industries, the curse of image sensors for higher definitions increases the amount of data to be processed in the image processing domain. The concerned algorithms, applied to embedded solutions, also have to frequently accept real-time constraints. So, the main issues are to moderate power consumption, to attain high performance computings and high memory bandwidth for data delivery.The massively parallel conception of GPUs is especially well adapted for this kind of tasks. However, this achitecture is complex to handle. Some reasons are its multiple memory and computation hierachical levels or the usage of this accelerator inside a global heterogeneous architecture. Therefore, mapping algorithms on GPUs, while exploiting high performance capacities of this architecture, aren’t trivial operations.In this thesis, we have developped a mapping methodology for sequential algorithms and designed it for GPUs. This methodology is made up of code analysis phases, mapping criteria verifications, code transformations and a final code generation phase. Part of the defined mapping criteria has been designed to assure the mapping legality, by considering GPU hardware specifities, whereas the other part are used to improve runtimes. In addition, we have studied GPU memories performances and the capacity of GPU to efficiently support coarse grain parallellism. This complementary work is a foundation for further improvments of GPU resources exploitation inside this mapping methodology.Last, the experimental results have revealed the functional reliability of the codes mapped on GPU and a speedup on the runtime of many C and C++ image processing applications used in industry.
Document type :
Complete list of metadata

Cited literature [295 references]  Display  Hide  Download
Contributor : ABES STAR :  Contact
Submitted on : Friday, October 16, 2020 - 12:07:08 PM
Last modification on : Wednesday, November 17, 2021 - 12:31:57 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02969012, version 1


Florian Gouin. Méthodologie de placement d'algorithmes de traitement d'images sur architecture massivement parallèle. Traitement des images [eess.IV]. Université Paris sciences et lettres, 2019. Français. ⟨NNT : 2019PSLEM075⟩. ⟨tel-02969012⟩



Record views


Files downloads