{"title":"基于15T SRAM单元的全数字内存计算宏,支持高并行性和细粒度同时读、写、MAC操作","authors":"Hao Guo;Jiawei Chen;Hailong Jiao","doi":"10.1109/LSSC.2025.3567840","DOIUrl":null,"url":null,"abstract":"A 15-transistor (15T) SRAM cell-based fully-digital computing-in-memory (CIM) macro is proposed for artificial intelligence accelerations. The CIM macro not only supports simultaneous read + write + multiply-accumulate (MAC) operations, but also supports ultrawide-range voltage scaling, digital design flow, and cell-wise bit interleaving. A fine-grained weight update scheme is introduced to perform write and MAC operations simultaneously. A specialized two’s complement processing strategy is proposed to enable efficient signed MAC operations without in-array sign extension. Fabricated in a 55-nm CMOS technology, the proposed fully-digital CIM macro enhances the peak energy efficiency by up to <inline-formula> <tex-math>$3.46\\times $ </tex-math></inline-formula> compared with the state-of-the-art digital CIM schemes.","PeriodicalId":13032,"journal":{"name":"IEEE Solid-State Circuits Letters","volume":"8 ","pages":"153-156"},"PeriodicalIF":2.0000,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A 15T SRAM Cell-Based Fully-Digital Computing-in-Memory Macro Supporting High Parallelism and Fine-Grained Simultaneous Read + Write + MAC Operations\",\"authors\":\"Hao Guo;Jiawei Chen;Hailong Jiao\",\"doi\":\"10.1109/LSSC.2025.3567840\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A 15-transistor (15T) SRAM cell-based fully-digital computing-in-memory (CIM) macro is proposed for artificial intelligence accelerations. The CIM macro not only supports simultaneous read + write + multiply-accumulate (MAC) operations, but also supports ultrawide-range voltage scaling, digital design flow, and cell-wise bit interleaving. A fine-grained weight update scheme is introduced to perform write and MAC operations simultaneously. A specialized two’s complement processing strategy is proposed to enable efficient signed MAC operations without in-array sign extension. Fabricated in a 55-nm CMOS technology, the proposed fully-digital CIM macro enhances the peak energy efficiency by up to <inline-formula> <tex-math>$3.46\\\\times $ </tex-math></inline-formula> compared with the state-of-the-art digital CIM schemes.\",\"PeriodicalId\":13032,\"journal\":{\"name\":\"IEEE Solid-State Circuits Letters\",\"volume\":\"8 \",\"pages\":\"153-156\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2025-03-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Solid-State Circuits Letters\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10990287/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Solid-State Circuits Letters","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10990287/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
A 15T SRAM Cell-Based Fully-Digital Computing-in-Memory Macro Supporting High Parallelism and Fine-Grained Simultaneous Read + Write + MAC Operations
A 15-transistor (15T) SRAM cell-based fully-digital computing-in-memory (CIM) macro is proposed for artificial intelligence accelerations. The CIM macro not only supports simultaneous read + write + multiply-accumulate (MAC) operations, but also supports ultrawide-range voltage scaling, digital design flow, and cell-wise bit interleaving. A fine-grained weight update scheme is introduced to perform write and MAC operations simultaneously. A specialized two’s complement processing strategy is proposed to enable efficient signed MAC operations without in-array sign extension. Fabricated in a 55-nm CMOS technology, the proposed fully-digital CIM macro enhances the peak energy efficiency by up to $3.46\times $ compared with the state-of-the-art digital CIM schemes.