{"title":"缓存内存何去何从?","authors":"J. Handy","doi":"10.1109/ELECTR.1991.718220","DOIUrl":null,"url":null,"abstract":"In the span of only five years cache memories, once an arcane method of eking the last ounce of processing power from large mainframe computers, have become a household word. Caches are now offered in most high-end personal computers, as well as in all workstations. Caches offer a means of putting today's CPU architectures to their highest capability, without requiring massive changes in the direction of processing. This does not imply that we have reached a steady state, where the only developments to be expected will be improvements in CPU speed and cache size. The cache will be found to facilitate radical changes in computer architecture without requiring equivalent changes in CPU design. Caches are already being used to allow the implementation of tightly-coupled multiprocessor systems, some of whose throughputs are more than proportional to the number of processors used in the system.","PeriodicalId":339281,"journal":{"name":"Electro International, 1991","volume":"57 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1991-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Where Are Cache Memories Going?\",\"authors\":\"J. Handy\",\"doi\":\"10.1109/ELECTR.1991.718220\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the span of only five years cache memories, once an arcane method of eking the last ounce of processing power from large mainframe computers, have become a household word. Caches are now offered in most high-end personal computers, as well as in all workstations. Caches offer a means of putting today's CPU architectures to their highest capability, without requiring massive changes in the direction of processing. This does not imply that we have reached a steady state, where the only developments to be expected will be improvements in CPU speed and cache size. The cache will be found to facilitate radical changes in computer architecture without requiring equivalent changes in CPU design. Caches are already being used to allow the implementation of tightly-coupled multiprocessor systems, some of whose throughputs are more than proportional to the number of processors used in the system.\",\"PeriodicalId\":339281,\"journal\":{\"name\":\"Electro International, 1991\",\"volume\":\"57 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1991-04-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electro International, 1991\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ELECTR.1991.718220\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electro International, 1991","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ELECTR.1991.718220","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
In the span of only five years cache memories, once an arcane method of eking the last ounce of processing power from large mainframe computers, have become a household word. Caches are now offered in most high-end personal computers, as well as in all workstations. Caches offer a means of putting today's CPU architectures to their highest capability, without requiring massive changes in the direction of processing. This does not imply that we have reached a steady state, where the only developments to be expected will be improvements in CPU speed and cache size. The cache will be found to facilitate radical changes in computer architecture without requiring equivalent changes in CPU design. Caches are already being used to allow the implementation of tightly-coupled multiprocessor systems, some of whose throughputs are more than proportional to the number of processors used in the system.