Parallel Implementation of Discrete Cosine Transform (DCT) Methods on GPU for HEVC

Basit Öğe Kaydı
dc.contributor.authorKaplan, Mücahit
dc.contributor.authorAkman, Ali
dc.date.accessioned2024-04-22T12:30:26Z
dc.date.available2024-04-22T12:30:26Z
dc.date.issued2024en_US
dc.departmentFakülteler, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.description.abstractThe High-Efficiency Video Coding (HEVC) standard represents a significant advancement in video compression technology, offering superior compression efficiency compared to its predecessors. This study investigates into the parallel implementation and efficacy of the Discrete Cosine Transform (DCT) process, a pivotal component of the HEVC standard’s transform step, when executed on GPU hardware. To enhance the performance of DCT, two distinct methods were introduced and implemented, making efficient use of shared memory resources within the GPU. A comprehensive analysis was conducted by measuring the execution times of these methods using a standardized test image. The study rigorously compared the performance of these methods across various scenarios and meticulously assessed their impact. In summary, this research contributes valuable insights into optimizing the DCT process within the HEVC standard through the parallel implementation on GPU hardware. The proposed methods exhibit promising results, demonstrating the potential to enhance the efficiency of HEVC’s transform step.en_US
dc.identifier.doi10.1007/978-3-031-52760-9_20en_US
dc.identifier.endpage293en_US
dc.identifier.scopus2-s2.0-85189536466en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage281en_US
dc.identifier.urihttps://hdl.handle.net/11467/7250
dc.identifier.urihttps://doi.org/10.1007/978-3-031-52760-9_20
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Science and Business Media Deutschland GmbHen_US
dc.relation.ispartofEAI/Springer Innovations in Communication and Computing - 2nd International Congress of Electrical and Computer Engineering, ICECENG 2023 Bandirma 22 November 2023 through 25 November 2023en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/restrictedAccessen_US
dc.subjectDCT; GPU; HEVCen_US
dc.titleParallel Implementation of Discrete Cosine Transform (DCT) Methods on GPU for HEVCen_US
dc.typeConference Objecten_US

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.56 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu