{"title":"使用流水线CTAM的低成本流水线多语种电子词典","authors":"S. K. Ray, Sabyasachi Dutta, A. Saha","doi":"10.1109/ICCTA.2007.11","DOIUrl":null,"url":null,"abstract":"A pipelined multi-lingual electronic dictionary (PMLeD) has been designed and implemented. Architecturally, it is a pipeline of four memory stages of which the first one is itself a pipelined version of a content-to-address-memory (CTAM) while the other three are traditional address-to-content memories (ATCM), namely, RAMs. The PMLeD is potentially capable of providing millions of word-by-word translations per second between an arbitrarily large number of languages but requires a highly expensive fully parallel design of the pipelined CTAM (PCTAM) stages for achieving this high throughput rate. The present design, which has been implemented and tested in the laboratory, has studied a cost-performance trade-off by designing each stage in the PCTAM with a byte-serial approach and implementing it employing a low-cost 8-bit microcontroller. The design has achieved a hefty reduction in cost and complexity at a considerable sacrifice in the throughput rate and marks a novel, simple and low-cost practical design approach to a pipelined associative memory","PeriodicalId":308247,"journal":{"name":"2007 International Conference on Computing: Theory and Applications (ICCTA'07)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Low-Cost Pipelineed Multi-Lingual E-Dictionary Using a Pipelined CTAM\",\"authors\":\"S. K. Ray, Sabyasachi Dutta, A. Saha\",\"doi\":\"10.1109/ICCTA.2007.11\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A pipelined multi-lingual electronic dictionary (PMLeD) has been designed and implemented. Architecturally, it is a pipeline of four memory stages of which the first one is itself a pipelined version of a content-to-address-memory (CTAM) while the other three are traditional address-to-content memories (ATCM), namely, RAMs. The PMLeD is potentially capable of providing millions of word-by-word translations per second between an arbitrarily large number of languages but requires a highly expensive fully parallel design of the pipelined CTAM (PCTAM) stages for achieving this high throughput rate. The present design, which has been implemented and tested in the laboratory, has studied a cost-performance trade-off by designing each stage in the PCTAM with a byte-serial approach and implementing it employing a low-cost 8-bit microcontroller. The design has achieved a hefty reduction in cost and complexity at a considerable sacrifice in the throughput rate and marks a novel, simple and low-cost practical design approach to a pipelined associative memory\",\"PeriodicalId\":308247,\"journal\":{\"name\":\"2007 International Conference on Computing: Theory and Applications (ICCTA'07)\",\"volume\":\"111 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-03-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 International Conference on Computing: Theory and Applications (ICCTA'07)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCTA.2007.11\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 International Conference on Computing: Theory and Applications (ICCTA'07)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCTA.2007.11","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Low-Cost Pipelineed Multi-Lingual E-Dictionary Using a Pipelined CTAM
A pipelined multi-lingual electronic dictionary (PMLeD) has been designed and implemented. Architecturally, it is a pipeline of four memory stages of which the first one is itself a pipelined version of a content-to-address-memory (CTAM) while the other three are traditional address-to-content memories (ATCM), namely, RAMs. The PMLeD is potentially capable of providing millions of word-by-word translations per second between an arbitrarily large number of languages but requires a highly expensive fully parallel design of the pipelined CTAM (PCTAM) stages for achieving this high throughput rate. The present design, which has been implemented and tested in the laboratory, has studied a cost-performance trade-off by designing each stage in the PCTAM with a byte-serial approach and implementing it employing a low-cost 8-bit microcontroller. The design has achieved a hefty reduction in cost and complexity at a considerable sacrifice in the throughput rate and marks a novel, simple and low-cost practical design approach to a pipelined associative memory