U. A. Kumar, Goli Naga Sandesh, Dhoti Ojusteja, Syed Ershad Ahmed
{"title":"基于下半部分或近似乘法器的误差弹性应用","authors":"U. A. Kumar, Goli Naga Sandesh, Dhoti Ojusteja, Syed Ershad Ahmed","doi":"10.1109/iSES52644.2021.00046","DOIUrl":null,"url":null,"abstract":"Inexact computation is used extensively in image processing applications especially in compact devices where battery (power consumption) and size (area) must be used efficiently. Inexact computation uses accuracy as a design specification to enhance our need for speed and performance with limited resources and time. This paper introduces a novel multiplier that aims to fulfill this need of high performance with minimal hardware. An error correcting module is introduced to improve the accuracy of the proposed multiplier. Experimental results are carried out resulting in an improvement of 30% power consumption with a reduction of 36% area when compared against existing multipliers with acceptable accuracy. A huge improvement in delay can also be observed as a direct consequence of the multiplier design structure.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Lower part OR based Approximate Multiplier for Error Resilient Applications\",\"authors\":\"U. A. Kumar, Goli Naga Sandesh, Dhoti Ojusteja, Syed Ershad Ahmed\",\"doi\":\"10.1109/iSES52644.2021.00046\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Inexact computation is used extensively in image processing applications especially in compact devices where battery (power consumption) and size (area) must be used efficiently. Inexact computation uses accuracy as a design specification to enhance our need for speed and performance with limited resources and time. This paper introduces a novel multiplier that aims to fulfill this need of high performance with minimal hardware. An error correcting module is introduced to improve the accuracy of the proposed multiplier. Experimental results are carried out resulting in an improvement of 30% power consumption with a reduction of 36% area when compared against existing multipliers with acceptable accuracy. A huge improvement in delay can also be observed as a direct consequence of the multiplier design structure.\",\"PeriodicalId\":293167,\"journal\":{\"name\":\"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/iSES52644.2021.00046\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/iSES52644.2021.00046","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Lower part OR based Approximate Multiplier for Error Resilient Applications
Inexact computation is used extensively in image processing applications especially in compact devices where battery (power consumption) and size (area) must be used efficiently. Inexact computation uses accuracy as a design specification to enhance our need for speed and performance with limited resources and time. This paper introduces a novel multiplier that aims to fulfill this need of high performance with minimal hardware. An error correcting module is introduced to improve the accuracy of the proposed multiplier. Experimental results are carried out resulting in an improvement of 30% power consumption with a reduction of 36% area when compared against existing multipliers with acceptable accuracy. A huge improvement in delay can also be observed as a direct consequence of the multiplier design structure.