本文關鍵詞：采用流水化偽隨機編碼算法的相變存儲器壽命延長方法　出處：《計算機研究與發(fā)展》2017年06期 　論文類型：期刊論文

  更多相關文章： 相變存儲器件 差分寫入 偽隨機編碼算法 編碼方向模式 星型生成規(guī)則

【摘要】：相變存儲器(phase change memory,PCM)是一種頗具前景的新型存儲器件,具有非易失性、靜態(tài)功耗低和存儲密度高的優(yōu)點.然而,該類器件的低寫入壽命是其在實用化中亟待克服的關鍵問題之一.一般來說,通過每次寫入時僅寫入相異位的策略,可以減少產生的平均寫入量,從而延長PCM的寫入壽命.然而,應用這一差異式的寫入策略通常又會以降低讀寫速度為代價.為此,提出了一種兼具高效和快速特點的寫入量減少方法 FEBRE(a fast and efficient bit-flipping reduction technique to extend PCM lifetime).該方法在差分寫入階段前,設計并使用了一種快速的一對多映射,將待寫入的數(shù)據(jù)并行映射為多個編碼向量,從而增加了從其中找到一個與已有數(shù)據(jù)最近的向量的可能性.此外,還提出了一種流水化的偽隨機編碼算法,用以加速一對多映射中的編碼過程,從而降低寫入開銷.實驗表明,與目前領先的PRES(pseudo-random encoding scheme)方法相比,FEBRE方法在寫入操作中,平均減少了5%以上的寫入量,提升了2倍以上的編碼速度;在讀取操作中,減少了45%以上的解碼操作次數(shù).
[Abstract]:Phase change memory (change) is a promising new type of memory device with the advantages of non-volatile, low static power consumption and high storage density. The low writing lifetime of this kind of devices is one of the key problems that need to be overcome in practical application. Generally speaking, the average amount of writing can be reduced by the strategy of only writing ectopic in each write. This extends the write life of PCM. However, the application of this differential write strategy usually comes at the expense of reading and writing speed. In this paper, a fast and efficient write reduction method, FEBREE, is proposed. A fast and efficient bit-flipping reduction technique to extend PCM. Lifetime). The method is prior to the differential write phase. A fast one-to-many mapping is designed and used to map the data to multiple encoding vectors in parallel, which increases the possibility of finding a vector closest to the existing data. A income pseudorandom coding algorithm is also proposed to speed up the coding process in one-to-many mapping, thus reducing the write overhead. Compared with the current leading PRES(pseudo-random encoding schememethod, the FEBRE method is in the write operation. The average amount of writing is reduced by more than 5%, and the coding speed is increased by more than 2 times. In the read operation, the number of decoding operations is reduced by more than 45%.
【作者單位】： 清華大學計算機科學與技術系;清華大學信息技術研究院;
【基金】：國家重點研發(fā)計劃(2016YFB1000303) 國家自然科學基金項目(61373025)~~
【分類號】：TP333
【正文快照】： This work was supported by the National Key Research and Development Plan of China(2016YFB1000303)and the NationalNatural Science Foundation of China(61373025).(gaopeng1982@gmail.com)隨著軟硬件技術的發(fā)展,現(xiàn)代計算機系統(tǒng)對高速、大容量、低功耗的內存系統(tǒng)產生

【相似文獻】

相關期刊論文 前3條

1 李世軍;;JPEG圖像壓縮編碼算法的DSP優(yōu)化實現(xiàn)[J];微計算機信息;2012年09期

2 胡國興;沈海斌;;低翻轉率的SoC總線組合編碼算法[J];電子器件;2006年04期

3 ;[J];;年期

相關碩士學位論文 前2條

1 王全明;H.264編碼算法在雙核DSP上的實現(xiàn)方法研究[D];華中科技大學;2007年

2 葛力雅;AC-3編碼算法研究與DSP上的實現(xiàn)[D];天津大學;2007年

，

本文編號：1391665