S. Kala, N. Sivanandan, B. R. Jose, J. Mathew, M. Ottavi
{"title":"Two dimensional FFT architecture based on radix-43 algorithm with efficient output reordering","authors":"S. Kala, N. Sivanandan, B. R. Jose, J. Mathew, M. Ottavi","doi":"10.1109/DTIS.2018.8368562","DOIUrl":null,"url":null,"abstract":"In this paper we present a 64 × 64-point 2D FFT architecture using a parallel unrolled radix-4<sup>3</sup> (R4<sup>3</sup>) FFT as the basic block. Our R4<sup>3</sup> architecture is a memory optimized parallel architecture which computes 64-point FFT, with least execution time. Here we use row-column decomposition of two R4<sup>3</sup> blocks to compute a 2D FFT. Proposed architecture has been implemented in UMC 40nm CMOS technology with clock frequency of 500 MHz, area of 0.841mm<sup>2</sup> and power consumption of 358 mW. Computation time of 64 × 64 FFT is 8.19μs. ASIC results shows better performance of our FFT in terms of computation time when compared with state-of-art implementation.","PeriodicalId":328650,"journal":{"name":"2018 13th International Conference on Design & Technology of Integrated Systems In Nanoscale Era (DTIS)","volume":"221 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 13th International Conference on Design & Technology of Integrated Systems In Nanoscale Era (DTIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DTIS.2018.8368562","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
In this paper we present a 64 × 64-point 2D FFT architecture using a parallel unrolled radix-43 (R43) FFT as the basic block. Our R43 architecture is a memory optimized parallel architecture which computes 64-point FFT, with least execution time. Here we use row-column decomposition of two R43 blocks to compute a 2D FFT. Proposed architecture has been implemented in UMC 40nm CMOS technology with clock frequency of 500 MHz, area of 0.841mm2 and power consumption of 358 mW. Computation time of 64 × 64 FFT is 8.19μs. ASIC results shows better performance of our FFT in terms of computation time when compared with state-of-art implementation.