Video compression deeply relies on motion estima- tion but this crucial step requires power-hungry computational resources. Starting from an existing architecture capable of calculating a high number of Sum of Absolute Differences (SADs), three possible locations for approximate adders are chosen. At each location, different types of approximate adders are implemented and the results are analyzed in terms of error and power saving.
Approximate-Computing Architectures for Motion Estimation in HEVC / Paltrinieri, Alberto; Peloso, Riccardo; Masera, Guido; Shafique, Muhammad; Martina, Maurizio. - ELETTRONICO. - 1(2018), pp. 190-193. ((Intervento presentato al convegno New Generation of CAS (NGCAS) tenutosi a Valletta (Malta) nel 13 dicembre 2019.
Titolo: | Approximate-Computing Architectures for Motion Estimation in HEVC |
Autori: | |
Data di pubblicazione: | 2018 |
Abstract: | Video compression deeply relies on motion estima- tion but this crucial step requires powe...r-hungry computational resources. Starting from an existing architecture capable of calculating a high number of Sum of Absolute Differences (SADs), three possible locations for approximate adders are chosen. At each location, different types of approximate adders are implemented and the results are analyzed in terms of error and power saving. |
ISBN: | 978-1-5386-7681-3 |
Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |
File in questo prodotto:
File | Descrizione | Tipologia | Licenza | |
---|---|---|---|---|
08572080.pdf | Versione editoriale | 2a Post-print versione editoriale / Version of Record | Non Pubblico - Accesso privato/ristretto | Administrator Richiedi una copia |
SAD_NGCAS2018.pdf | versione finale | 2. Post-print / Author's Accepted Manuscript | PUBBLICO - Tutti i diritti riservati | Visibile a tuttiVisualizza/Apri |
http://hdl.handle.net/11583/2722061