{"title":"A 140-MHz CMOS bit-level pipelined multiplier-accumulator using a new dynamic full-adder cell design","authors":"F. Lu, H. Samueli","doi":"10.1109/VLSIC.1990.111126","DOIUrl":null,"url":null,"abstract":"A bit-level pipelined 12-b×12-b two's complement multiplier with a 27-b accumulator has been designed and fabricated in a 1-μm CMOS technology. A novel quasi N-P domino logic structure has been adopted to increase the throughput, and special pipeline structures were used to reduce the latency significantly. The measured maximum clock rate is 140 MHz (i.e. 140 million multiply-accumulate operations per second), and the typical power-speed ratio is 11 mW/MHz. The chip complexity is 10000 transistors and the 68-pad chip area is 2.5 mm×3.7 mm","PeriodicalId":239990,"journal":{"name":"Digest of Technical Papers., 1990 Symposium on VLSI Circuits","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1990-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digest of Technical Papers., 1990 Symposium on VLSI Circuits","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VLSIC.1990.111126","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
A bit-level pipelined 12-b×12-b two's complement multiplier with a 27-b accumulator has been designed and fabricated in a 1-μm CMOS technology. A novel quasi N-P domino logic structure has been adopted to increase the throughput, and special pipeline structures were used to reduce the latency significantly. The measured maximum clock rate is 140 MHz (i.e. 140 million multiply-accumulate operations per second), and the typical power-speed ratio is 11 mW/MHz. The chip complexity is 10000 transistors and the 68-pad chip area is 2.5 mm×3.7 mm
采用1 μ m CMOS技术,设计并制作了一种位级流水线式12b倍12b双补乘法器和27b累加器。采用了一种新颖的准N-P多米诺逻辑结构来提高吞吐量,并采用了特殊的管道结构来显著降低延迟。测量到的最大时钟速率为140 MHz(即每秒1.4亿次乘法累积操作),典型的功率-速度比为11 mW/MHz。芯片的复杂性是10000个晶体管,68个衬垫的芯片面积是2.5 mm乘以3.7 mm