{"title":"Low Cost VLSI Architecture for Sample Adaptive Offset Encoder in HEVC","authors":"Sayed El Gendy, A. Shalaby, M. Sayed","doi":"10.1109/ISVLSI.2016.78","DOIUrl":null,"url":null,"abstract":"Sample Adaptive Offset (SAO) has been adopted as a new in-loop filtering block in High Efficiency Video Coding (HEVC). It can significantly increase compression efficiency especially for sequences that contain computer graphics content up to 23%. To get the optimum SAO parameters, exhaustive operations are required because of the huge amount of samples which the encoder has to study. In this work, a low cost high throughput VLSI implementation for the parameter estimation (encoding) phase is proposed. The proposed novel architecture reduces the cost in terms of gates count by 47% in comparison with prior work. The proposed design is prototyped using 65 nm CMOS technology. It has 89.3 Kgates, 8832 bits SRAM, and a maximum clock frequency of 426 MHz. It can support real time 8K×4K@120fps videos at 378 MHz.","PeriodicalId":140647,"journal":{"name":"2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"971 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISVLSI.2016.78","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Sample Adaptive Offset (SAO) has been adopted as a new in-loop filtering block in High Efficiency Video Coding (HEVC). It can significantly increase compression efficiency especially for sequences that contain computer graphics content up to 23%. To get the optimum SAO parameters, exhaustive operations are required because of the huge amount of samples which the encoder has to study. In this work, a low cost high throughput VLSI implementation for the parameter estimation (encoding) phase is proposed. The proposed novel architecture reduces the cost in terms of gates count by 47% in comparison with prior work. The proposed design is prototyped using 65 nm CMOS technology. It has 89.3 Kgates, 8832 bits SRAM, and a maximum clock frequency of 426 MHz. It can support real time 8K×4K@120fps videos at 378 MHz.