Yongfei Zhang, Rui Fan, Chao Zhang, G. Wang, Zhe Li
{"title":"SIMD acceleration for HEVC encoding on DSP","authors":"Yongfei Zhang, Rui Fan, Chao Zhang, G. Wang, Zhe Li","doi":"10.1109/APSIPA.2017.8282310","DOIUrl":null,"url":null,"abstract":"As the new generation video coding standard, High Efficient Video Coding (HEVC) significantly improves the video compression efficiency, which is however at the cost of a far more computational payload than the capacity of real-time video applications and general purpose processors. In this paper, we focus on the SIMD-based fast implementation of the HEVC encoder over modern TI Digital Signal Processors (DSPs). We first test the DSP-based HEVC encoder and indentify the most time-consuming encoding modules. Then SIMD instructions are exploited to improve the parallel computing capacity of these modules and thus speed up the encoder. The experimental results show that the proposed implementations can significantly improve the encoding speed of the DSP-based HEVC encoder, with a speedup ratio of 8.38-87.32 over the original C-based encoder and 1.59–6.56 over o3-optimization enabled encoder.","PeriodicalId":142091,"journal":{"name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/APSIPA.2017.8282310","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
As the new generation video coding standard, High Efficient Video Coding (HEVC) significantly improves the video compression efficiency, which is however at the cost of a far more computational payload than the capacity of real-time video applications and general purpose processors. In this paper, we focus on the SIMD-based fast implementation of the HEVC encoder over modern TI Digital Signal Processors (DSPs). We first test the DSP-based HEVC encoder and indentify the most time-consuming encoding modules. Then SIMD instructions are exploited to improve the parallel computing capacity of these modules and thus speed up the encoder. The experimental results show that the proposed implementations can significantly improve the encoding speed of the DSP-based HEVC encoder, with a speedup ratio of 8.38-87.32 over the original C-based encoder and 1.59–6.56 over o3-optimization enabled encoder.