{"title":"通过减少位翻转来提高PCM存储器的寿命","authors":"Bhukya Krishna Priya","doi":"10.1109/AISP53593.2022.9760521","DOIUrl":null,"url":null,"abstract":"Memory technology has been growing at a very fast rate in these past few years and the recent trend of replacing Volatile memories such as DRAM, with NonVolatile Memory (NVM) technologies such as Phase change Memory (PCM) and Spin Transfer Torque RAM(STT-RAM) is becoming more prevalent. But their drawback of not having a lifetime comparable to that of their Volatile counterparts, has still kept the idea of NVMs as cache, still a challenge. Apart from this, the information wm resist in the memory even though power is off and this may lead to data threats. Hence, to protect sensitive data, the Advanced Encryption Standard Counter Mode (AES-CTR) algorithm is used to encrypt the information, which is have a huge number of bit flips to be written on the memory. This paper deals with one such method to have the higher lifetime of NVM, namely PCM by having lesser the bit transitions to be written on the memory. The proposed architecture is implemented in Gem5 simulator and also synthesized and implemented using Xilinx ISE 14.7. The model has also been simulated using Parsec and iSim using standardized test vectors and the result shows that 5% improvement in lifetime is observed, 21% and 25% of the hardware components are utilized for read and write phase.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"142 1","pages":"1-7"},"PeriodicalIF":0.0000,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhance the Lifetime of PCM Memory by Reducing the Bit Flips\",\"authors\":\"Bhukya Krishna Priya\",\"doi\":\"10.1109/AISP53593.2022.9760521\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Memory technology has been growing at a very fast rate in these past few years and the recent trend of replacing Volatile memories such as DRAM, with NonVolatile Memory (NVM) technologies such as Phase change Memory (PCM) and Spin Transfer Torque RAM(STT-RAM) is becoming more prevalent. But their drawback of not having a lifetime comparable to that of their Volatile counterparts, has still kept the idea of NVMs as cache, still a challenge. Apart from this, the information wm resist in the memory even though power is off and this may lead to data threats. Hence, to protect sensitive data, the Advanced Encryption Standard Counter Mode (AES-CTR) algorithm is used to encrypt the information, which is have a huge number of bit flips to be written on the memory. This paper deals with one such method to have the higher lifetime of NVM, namely PCM by having lesser the bit transitions to be written on the memory. The proposed architecture is implemented in Gem5 simulator and also synthesized and implemented using Xilinx ISE 14.7. The model has also been simulated using Parsec and iSim using standardized test vectors and the result shows that 5% improvement in lifetime is observed, 21% and 25% of the hardware components are utilized for read and write phase.\",\"PeriodicalId\":6793,\"journal\":{\"name\":\"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)\",\"volume\":\"142 1\",\"pages\":\"1-7\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-02-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AISP53593.2022.9760521\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AISP53593.2022.9760521","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
在过去的几年里,存储技术一直在以非常快的速度增长,最近的趋势是用非易失性存储器(NVM)技术(如相变存储器(PCM)和自旋传递扭矩RAM(STT-RAM))取代易失性存储器(如DRAM),这一趋势正变得越来越普遍。但是它们的缺点是寿命不能与Volatile相媲美,这使得nvm作为缓存的想法仍然是一个挑战。除此之外,即使电源关闭,信息也会在内存中抵抗,这可能导致数据威胁。因此,为了保护敏感数据,采用AES-CTR (Advanced Encryption Standard Counter Mode)算法对信息进行加密,这些信息有大量的位翻转需要写入内存。本文讨论了一种具有更高NVM寿命的方法,即PCM,通过减少写入存储器的位转换。所提出的架构在Gem5模拟器中实现,并使用Xilinx ISE 14.7进行合成和实现。采用标准化测试向量,利用Parsec和iSim对该模型进行了仿真,结果表明,该模型的使用寿命提高了5%,读写阶段分别利用了21%和25%的硬件组件。
Enhance the Lifetime of PCM Memory by Reducing the Bit Flips
Memory technology has been growing at a very fast rate in these past few years and the recent trend of replacing Volatile memories such as DRAM, with NonVolatile Memory (NVM) technologies such as Phase change Memory (PCM) and Spin Transfer Torque RAM(STT-RAM) is becoming more prevalent. But their drawback of not having a lifetime comparable to that of their Volatile counterparts, has still kept the idea of NVMs as cache, still a challenge. Apart from this, the information wm resist in the memory even though power is off and this may lead to data threats. Hence, to protect sensitive data, the Advanced Encryption Standard Counter Mode (AES-CTR) algorithm is used to encrypt the information, which is have a huge number of bit flips to be written on the memory. This paper deals with one such method to have the higher lifetime of NVM, namely PCM by having lesser the bit transitions to be written on the memory. The proposed architecture is implemented in Gem5 simulator and also synthesized and implemented using Xilinx ISE 14.7. The model has also been simulated using Parsec and iSim using standardized test vectors and the result shows that 5% improvement in lifetime is observed, 21% and 25% of the hardware components are utilized for read and write phase.