{"title":"Optimization of MPEG-4 GA AAC on general PC","authors":"Do Hyoung Kim, Dong Hyun Kim, Jae-Ho Chung","doi":"10.1109/MWSCAS.2001.986338","DOIUrl":null,"url":null,"abstract":"MPEG-4 General Audio (GA) Encoder/Decoder has inherited MPEG-2 AAC (Advanced Audio Coding) and added TVQ and other algorithms as scalable options. In this paper, the authors deal with the method of optimization of a MPEG-4 AAC scalable encoder. An original MPEG-4 VM source takes 15 times to 30 times the encoding time of the original sample playing time as its options, although this can be changed for varying CPU and memory conditions. The authors mainly used the reduction of unnecessary loop or the loop-unrolling technology to improve the encoder performance. For this work, firstly they performed the profiling based on general PC and checked the frequency or complexity of each function, and then selected the target function to be optimized.","PeriodicalId":403026,"journal":{"name":"Proceedings of the 44th IEEE 2001 Midwest Symposium on Circuits and Systems. MWSCAS 2001 (Cat. No.01CH37257)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 44th IEEE 2001 Midwest Symposium on Circuits and Systems. MWSCAS 2001 (Cat. No.01CH37257)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MWSCAS.2001.986338","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
MPEG-4 General Audio (GA) Encoder/Decoder has inherited MPEG-2 AAC (Advanced Audio Coding) and added TVQ and other algorithms as scalable options. In this paper, the authors deal with the method of optimization of a MPEG-4 AAC scalable encoder. An original MPEG-4 VM source takes 15 times to 30 times the encoding time of the original sample playing time as its options, although this can be changed for varying CPU and memory conditions. The authors mainly used the reduction of unnecessary loop or the loop-unrolling technology to improve the encoder performance. For this work, firstly they performed the profiling based on general PC and checked the frequency or complexity of each function, and then selected the target function to be optimized.