{"title":"行进记忆(MM)简介","authors":"Tadao Nakamura","doi":"10.1109/3DIC48104.2019.9058887","DOIUrl":null,"url":null,"abstract":"Today's computer systems rather have a “big issue,” which is what is called the memory bottleneck, especially as their scale has been growing with nanotechnology year by year toward EXA-scale supercomputing for scientific calculations and deep learning in neural-networking. To solve the issue, we must be back to the origin of computer system design pursuing what memory in computer systems should be. We are developing Marching Memory (MM), and can show how the features of it suit the solution with reasonable conditions such as higher speed with no latency under lower power consumption than SRAM.","PeriodicalId":440556,"journal":{"name":"2019 International 3D Systems Integration Conference (3DIC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Introduction to Marching Memory (MM)\",\"authors\":\"Tadao Nakamura\",\"doi\":\"10.1109/3DIC48104.2019.9058887\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Today's computer systems rather have a “big issue,” which is what is called the memory bottleneck, especially as their scale has been growing with nanotechnology year by year toward EXA-scale supercomputing for scientific calculations and deep learning in neural-networking. To solve the issue, we must be back to the origin of computer system design pursuing what memory in computer systems should be. We are developing Marching Memory (MM), and can show how the features of it suit the solution with reasonable conditions such as higher speed with no latency under lower power consumption than SRAM.\",\"PeriodicalId\":440556,\"journal\":{\"name\":\"2019 International 3D Systems Integration Conference (3DIC)\",\"volume\":\"34 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 International 3D Systems Integration Conference (3DIC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/3DIC48104.2019.9058887\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International 3D Systems Integration Conference (3DIC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/3DIC48104.2019.9058887","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Today's computer systems rather have a “big issue,” which is what is called the memory bottleneck, especially as their scale has been growing with nanotechnology year by year toward EXA-scale supercomputing for scientific calculations and deep learning in neural-networking. To solve the issue, we must be back to the origin of computer system design pursuing what memory in computer systems should be. We are developing Marching Memory (MM), and can show how the features of it suit the solution with reasonable conditions such as higher speed with no latency under lower power consumption than SRAM.