{"title":"用于超高清H.264/AVC编码器的1991 Mpixels/s帧内预测架构","authors":"Gang He, Dajiang Zhou, Jinjia Zhou, S. Goto","doi":"10.5281/ZENODO.43025","DOIUrl":null,"url":null,"abstract":"This paper presents an H.264/AVC intra prediction design for Super Hi-Vision (SHV) video. Due to huge throughput requirements, design challenges such as data dependency and complexity become even more critical. To solve these problems, we first propose an interlaced block reordering scheme together with a coarse-to-fine mode decision (CFMD) strategy to resolve the data dependency between intra mode decision and reconstruction. Circuits area is reduced in the meantime with CFMD. We also propose a probability-based reconstruction scheme to solve the problem from long pipeline latency. As a result, hardware complexity in terms of the product of area and frequency is reduced by 74%. The maximum throughput reaches 1991Mpixels/s for 7680×4320p 60fps video. Total logic gate count is 451.5k in 65nm library.","PeriodicalId":201182,"journal":{"name":"2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A 1991 Mpixels/s intra prediction architecture for Super Hi-Vision H.264/AVC encoder\",\"authors\":\"Gang He, Dajiang Zhou, Jinjia Zhou, S. Goto\",\"doi\":\"10.5281/ZENODO.43025\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents an H.264/AVC intra prediction design for Super Hi-Vision (SHV) video. Due to huge throughput requirements, design challenges such as data dependency and complexity become even more critical. To solve these problems, we first propose an interlaced block reordering scheme together with a coarse-to-fine mode decision (CFMD) strategy to resolve the data dependency between intra mode decision and reconstruction. Circuits area is reduced in the meantime with CFMD. We also propose a probability-based reconstruction scheme to solve the problem from long pipeline latency. As a result, hardware complexity in terms of the product of area and frequency is reduced by 74%. The maximum throughput reaches 1991Mpixels/s for 7680×4320p 60fps video. Total logic gate count is 451.5k in 65nm library.\",\"PeriodicalId\":201182,\"journal\":{\"name\":\"2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)\",\"volume\":\"14 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-10-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5281/ZENODO.43025\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5281/ZENODO.43025","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A 1991 Mpixels/s intra prediction architecture for Super Hi-Vision H.264/AVC encoder
This paper presents an H.264/AVC intra prediction design for Super Hi-Vision (SHV) video. Due to huge throughput requirements, design challenges such as data dependency and complexity become even more critical. To solve these problems, we first propose an interlaced block reordering scheme together with a coarse-to-fine mode decision (CFMD) strategy to resolve the data dependency between intra mode decision and reconstruction. Circuits area is reduced in the meantime with CFMD. We also propose a probability-based reconstruction scheme to solve the problem from long pipeline latency. As a result, hardware complexity in terms of the product of area and frequency is reduced by 74%. The maximum throughput reaches 1991Mpixels/s for 7680×4320p 60fps video. Total logic gate count is 451.5k in 65nm library.