{"title":"矢量矩阵乘法的数字内存随机计算体系结构","authors":"Shady O. Agwa, T. Prodromakis","doi":"10.3389/fnano.2023.1147396","DOIUrl":null,"url":null,"abstract":"The applications of the Artificial Intelligence are currently dominating the technology landscape. Meanwhile, the conventional Von Neumann architectures are struggling with the data-movement bottleneck to meet the ever-increasing performance demands of these data-centric applications. Moreover, The vector-matrix multiplication cost, in the binary domain, is a major computational bottleneck for these applications. This paper introduces a novel digital in-memory stochastic computing architecture that leverages the simplicity of the stochastic computing for in-memory vector-matrix multiplication. The proposed architecture incorporates several new approaches including a new stochastic number generator with ideal binary-to-stochastic mapping, a best seeding approach for accurate-enough low stochastic bit-precisions, a hybrid stochastic-binary accumulation approach for vector-matrix multiplication, and the conversion of conventional memory read operations into on-the-fly stochastic multiplication operations with negligible overhead. Thanks to the combination of these approaches, the accuracy analysis of the vector-matrix multiplication benchmark shows that scaling down the stochastic bit-precision from 16-bit to 4-bit achieves nearly the same average error (less than 3%). The derived analytical model of the proposed in-memory stochastic computing architecture demonstrates that the 4-bit stochastic architecture achieves the highest throughput per sub-array (122 Ops/Cycle), which is better than the 16-bit stochastic precision by 4.36x, while still maintaining a small average error of 2.25%.","PeriodicalId":34432,"journal":{"name":"Frontiers in Nanotechnology","volume":null,"pages":null},"PeriodicalIF":4.1000,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Digital in-memory stochastic computing architecture for vector-matrix multiplication\",\"authors\":\"Shady O. Agwa, T. Prodromakis\",\"doi\":\"10.3389/fnano.2023.1147396\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The applications of the Artificial Intelligence are currently dominating the technology landscape. Meanwhile, the conventional Von Neumann architectures are struggling with the data-movement bottleneck to meet the ever-increasing performance demands of these data-centric applications. Moreover, The vector-matrix multiplication cost, in the binary domain, is a major computational bottleneck for these applications. This paper introduces a novel digital in-memory stochastic computing architecture that leverages the simplicity of the stochastic computing for in-memory vector-matrix multiplication. The proposed architecture incorporates several new approaches including a new stochastic number generator with ideal binary-to-stochastic mapping, a best seeding approach for accurate-enough low stochastic bit-precisions, a hybrid stochastic-binary accumulation approach for vector-matrix multiplication, and the conversion of conventional memory read operations into on-the-fly stochastic multiplication operations with negligible overhead. Thanks to the combination of these approaches, the accuracy analysis of the vector-matrix multiplication benchmark shows that scaling down the stochastic bit-precision from 16-bit to 4-bit achieves nearly the same average error (less than 3%). The derived analytical model of the proposed in-memory stochastic computing architecture demonstrates that the 4-bit stochastic architecture achieves the highest throughput per sub-array (122 Ops/Cycle), which is better than the 16-bit stochastic precision by 4.36x, while still maintaining a small average error of 2.25%.\",\"PeriodicalId\":34432,\"journal\":{\"name\":\"Frontiers in Nanotechnology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2023-07-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Nanotechnology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/fnano.2023.1147396\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Nanotechnology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fnano.2023.1147396","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
Digital in-memory stochastic computing architecture for vector-matrix multiplication
The applications of the Artificial Intelligence are currently dominating the technology landscape. Meanwhile, the conventional Von Neumann architectures are struggling with the data-movement bottleneck to meet the ever-increasing performance demands of these data-centric applications. Moreover, The vector-matrix multiplication cost, in the binary domain, is a major computational bottleneck for these applications. This paper introduces a novel digital in-memory stochastic computing architecture that leverages the simplicity of the stochastic computing for in-memory vector-matrix multiplication. The proposed architecture incorporates several new approaches including a new stochastic number generator with ideal binary-to-stochastic mapping, a best seeding approach for accurate-enough low stochastic bit-precisions, a hybrid stochastic-binary accumulation approach for vector-matrix multiplication, and the conversion of conventional memory read operations into on-the-fly stochastic multiplication operations with negligible overhead. Thanks to the combination of these approaches, the accuracy analysis of the vector-matrix multiplication benchmark shows that scaling down the stochastic bit-precision from 16-bit to 4-bit achieves nearly the same average error (less than 3%). The derived analytical model of the proposed in-memory stochastic computing architecture demonstrates that the 4-bit stochastic architecture achieves the highest throughput per sub-array (122 Ops/Cycle), which is better than the 16-bit stochastic precision by 4.36x, while still maintaining a small average error of 2.25%.