TWI635391B - Flash memory and management method thereof - Google Patents

Flash memory and management method thereof Download PDF

Info

Publication number
TWI635391B
TWI635391B TW106104758A TW106104758A TWI635391B TW I635391 B TWI635391 B TW I635391B TW 106104758 A TW106104758 A TW 106104758A TW 106104758 A TW106104758 A TW 106104758A TW I635391 B TWI635391 B TW I635391B
Authority
TW
Taiwan
Prior art keywords
flash memory
page address
buffer
address mapping
written
Prior art date
Application number
TW106104758A
Other languages
Chinese (zh)
Other versions
TW201830244A (en
Inventor
詹伯彥
Original Assignee
點序科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 點序科技股份有限公司 filed Critical 點序科技股份有限公司
Priority to TW106104758A priority Critical patent/TWI635391B/en
Priority to CN201710165000.0A priority patent/CN108446238A/en
Publication of TW201830244A publication Critical patent/TW201830244A/en
Application granted granted Critical
Publication of TWI635391B publication Critical patent/TWI635391B/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/0223User address space allocation, e.g. contiguous or non contiguous base addressing
    • G06F12/023Free address space management
    • G06F12/0238Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory
    • G06F12/0246Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory in block erasable memory, e.g. flash memory
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/0802Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Memory System (AREA)
  • Techniques For Improving Reliability Of Storages (AREA)

Abstract

快閃記憶體及其管理方法。管理方法包括:設置緩衝區,使緩衝區儲存多個寫入資料,其中各寫入資料具有一單位尺寸;以及,計算儲存在緩衝區的寫入資料的總尺寸達到預設臨界值時,將緩衝器中的寫入資料寫入至快閃記憶體的多數個實體記憶頁的其中之一中Flash memory and its management method. The management method includes: setting a buffer so that the buffer stores a plurality of written data, wherein each written data has a unit size; and when the total size of the written data stored in the buffer reaches a preset critical value, The data written in the buffer is written to one of the plurality of physical memory pages of the flash memory.

Description

快閃記憶體以及其管理方法Flash memory and management method thereof

本發明是有關於一種快閃記憶體及其記憶體管理方法,且特別是有關於一種用以降低寫入放大現象的記憶體管理方法。The invention relates to a flash memory and a memory management method thereof, and in particular to a memory management method for reducing a write amplification phenomenon.

在快閃記憶體的效能評估上,針對快閃記憶體進行隨機存取在評估指標中具有一定的重要性,其中,關於寫入放大現象及記憶體空間整合兩者,已是快閃記憶體在使用上存在已久的重要議題。In the performance evaluation of flash memory, random access to flash memory is of certain importance in the evaluation indicators. Among them, the write amplification phenomenon and the integration of memory space are already flash memory. There have been important issues in use for a long time.

然而關於寫入放大現象方面,造成寫入放大現象的因素主要包括兩者:其一在於寫入的資料大小與記憶體轉換層採用的映射方式不對齊,其二為考量壽命及空間的可用性所進行的記憶體空間整合。前述兩者最終衍生出針對快閃記憶體進行重複寫入動作,並進而影響寫入效能。此外,由於隨機寫入具有一定的特性,其寫入資料的特徵資料單位尺寸大多為4K,此時,在記憶體轉換層採用頁或塊映射(尺寸大於4K)時,寫入放大的問題更為明顯。However, regarding the write amplification phenomenon, the factors that cause the write amplification phenomenon mainly include two: one is that the size of the written data is not aligned with the mapping method adopted by the memory conversion layer, and the other is to consider the life and space availability Memory space integration. The foregoing two ultimately result in repeated writing operations on the flash memory, and then affect the writing performance. In addition, because random writing has certain characteristics, the unit size of the characteristic data of the written data is mostly 4K. At this time, when the memory conversion layer uses page or block mapping (size greater than 4K), the problem of write amplification is even more serious. As obvious.

本發明提供一種快閃記憶體及其的管理方法,有效降低寫入放大現象。The invention provides a flash memory and a management method thereof, which can effectively reduce the write amplification phenomenon.

本發明的快閃記憶體的管理方法包括:設置緩衝區,使緩衝區儲存多個寫入資料,其中各寫入資料具有一單位尺寸;以及,計算儲存在緩衝區的寫入資料的總尺寸達到預設臨界值時,將緩衝器中的寫入資料寫入至快閃記憶體的多數個實體記憶頁的其中之一中。The flash memory management method of the present invention includes: setting a buffer so that the buffer stores a plurality of written data, wherein each written data has a unit size; and calculating the total size of the written data stored in the buffer When the preset threshold is reached, the data written in the buffer is written into one of the plurality of physical memory pages of the flash memory.

在本發明的一實施例中,快閃記憶體的管理方法更包括:建立分別對應多數個邏輯頁位址的多數個部份頁位址映射表。其中,各部份頁位址映射表包括多數個部分區域資訊,各部分區域資訊區分為多數個節欄位,各節欄位包括映射實體頁位址以及映射實體記憶組。In an embodiment of the present invention, the flash memory management method further includes: establishing a plurality of partial page address mapping tables corresponding to a plurality of logical page addresses, respectively. The partial page address mapping table includes a plurality of partial area information. Each partial area information is divided into a plurality of section fields, and each section field includes a mapping entity page address and a mapping entity memory group.

本發明的快閃記憶體包括記憶胞模組以及控制器。記憶胞模組包括多數個實體記憶組。各實體記憶組包括多數個實體記憶頁。控制器耦接記憶胞模組,用以:設置緩衝區,使緩衝區儲存多個寫入資料,其中各寫入資料具有單位尺寸;以及,計算儲存在緩衝區的該些寫入資料的總尺寸達到預設臨界值時,將緩衝器中的寫入資料寫入至快閃記憶體的多數個實體記憶頁的其中之一中。The flash memory of the present invention includes a memory cell module and a controller. The memory cell module includes a plurality of physical memory groups. Each physical memory group includes a plurality of physical memory pages. The controller is coupled to the memory cell module for: setting a buffer so that the buffer stores a plurality of written data, each of which has a unit size; and calculating a total of the written data stored in the buffer When the size reaches a predetermined threshold, the data written in the buffer is written into one of the plurality of physical memory pages of the flash memory.

基於上述,本發明提供一緩衝區,並使具有一單位尺寸的寫入資料先寫入緩衝區中,並在緩衝區中的資料總尺寸達到預設臨界值時,再將緩衝區中的多個寫入資料一併寫入至實體記憶頁中。如此一來,快閃記憶體的寫入放大現象可以被降低,有效提升快閃記憶體的使用效率。Based on the above, the present invention provides a buffer, and write data having a unit size is written into the buffer first, and when the total size of the data in the buffer reaches a preset critical value, the data in the buffer is Each written data is written into the physical memory page. In this way, the write amplification phenomenon of the flash memory can be reduced, which effectively improves the use efficiency of the flash memory.

為讓本發明的上述特徵和優點能更明顯易懂,下文特舉實施例,並配合所附圖式作詳細說明如下。In order to make the above features and advantages of the present invention more comprehensible, embodiments are hereinafter described in detail with reference to the accompanying drawings.

請參照圖1,圖1繪示本發明一實施例的快閃記憶體管理方法的流程圖。其中,在步驟S110中,設置緩衝區,並使緩衝區用以儲存多數個寫入資料。其中的各寫入資料具有一單位尺寸。在此,緩衝區具有大於單位尺寸的資料儲存容量。請同步參照圖2繪示的本發明實施例的快閃記憶體的示意圖。在圖2中,緩衝器210具有大於單位尺寸的資料儲存容量,接收寫入資料WD並將寫入資料WD暫存至緩衝器210中。舉例來說明,各筆寫入資料WD所具有的單位尺寸為4K,而緩衝器210的資料儲存容量則可以為各寫入資料WD所具有的單位尺寸的整數倍(例如4倍),也就是說,緩衝器210的資料儲存容量可以為16K。也因此,緩衝器210可以儲存多筆的寫入資料。Please refer to FIG. 1. FIG. 1 is a flowchart of a flash memory management method according to an embodiment of the present invention. In step S110, a buffer is set, and the buffer is used to store a plurality of written data. Each of the written data has a unit size. Here, the buffer has a data storage capacity larger than a unit size. Please refer to FIG. 2 for a schematic diagram of the flash memory according to the embodiment of the present invention. In FIG. 2, the buffer 210 has a data storage capacity larger than a unit size, and receives the written data WD and temporarily stores the written data WD in the buffer 210. For example, the unit size of each write data WD is 4K, and the data storage capacity of the buffer 210 can be an integer multiple (for example, 4 times) of the unit size of each write data WD, that is, In other words, the data storage capacity of the buffer 210 can be 16K. Therefore, the buffer 210 can store multiple write data.

並且,在步驟S120中,透過計算儲存在緩衝區210的寫入資料WD1~WD4的總尺寸,並在當緩衝區210的寫入資料WD1~WD4的總尺寸達到一個預設臨界值時,將緩衝器210中的寫入資料WD1~WD4寫入至快閃記憶體220的多數個實體記憶頁的其中之一221中。具體來說明,快閃記憶體220中單一個實體記憶頁的容量可以等於單一筆寫入資料WD的單位尺寸的N倍,N為大於1的整數。此時的預設臨界值可以設定為N乘以單位尺寸。換句話說,當有N筆的寫入資料被儲存在緩衝器210中時,緩衝器210中的總尺寸可達到預設臨界值,此時,可將緩衝器210中儲存的寫入資料WD1~WD4一次性的寫入至實體記憶頁221中。In step S120, the total size of the written data WD1 to WD4 stored in the buffer 210 is calculated, and when the total size of the written data WD1 to WD4 in the buffer 210 reaches a preset critical value, The writing data WD1 to WD4 in the buffer 210 are written into one of the plurality of physical memory pages 221 of the flash memory 220. Specifically, the capacity of a single physical memory page in the flash memory 220 may be equal to N times the unit size of a single write data WD, where N is an integer greater than 1. The preset critical value at this time can be set to N times the unit size. In other words, when there are N pieces of written data stored in the buffer 210, the total size in the buffer 210 can reach a preset critical value. At this time, the written data WD1 stored in the buffer 210 can be stored. ~ WD4 is written to the physical memory page 221 at one time.

舉例來說明,當實體記憶頁221的儲存容量為16K,而寫入資料WD所具有的單位尺寸為4K時,預設臨界至可以設定為16K,且當緩衝器210存滿4筆寫入資料WD1~WD4時,可將寫入資料WD1~WD4寫入至實體記憶頁221中。For example, when the storage capacity of the physical memory page 221 is 16K, and the unit size of the write data WD is 4K, the default threshold can be set to 16K, and when the buffer 210 is filled with 4 write data When WD1 ~ WD4, write data WD1 ~ WD4 can be written into the physical memory page 221.

由上述說明可以得知,實體記憶頁221中具有的16K的記憶區中用以儲存寫入資料的比例可以最大化,相對的,寫入放大率可以有效的被降低,提升快閃記憶體220的使用效能。From the above description, it can be known that the proportion of the 16K memory area in the physical memory page 221 for storing written data can be maximized. In contrast, the write magnification can be effectively reduced and the flash memory 220 can be improved. Performance.

另外,單一實體記憶頁中所儲存的資料可以分成幾個段落,以具有的16K的實體記憶頁221為範例,可包括4個分段的寫入資料(每個寫入資料的單位尺寸為4K)。In addition, the data stored in a single physical memory page can be divided into several paragraphs. Taking the 16K physical memory page 221 as an example, it can include 4 segments of written data (each written data unit size is 4K ).

值得一提的,儲存在緩衝器210中的多筆寫入資料WD1-WD4對應的邏輯位址可以是連續的,可以是部分連續的,或也可以是不相連續而呈亂數分布的。It is worth mentioning that the logical addresses corresponding to the plurality of write data WD1-WD4 stored in the buffer 210 may be continuous, may be partially continuous, or may be discontinuous and distributed in random numbers.

關於位址映射方面,請參照圖3,圖3繪示本發明一實施例的快閃記憶體映射方式的示意圖。以每筆寫入資料的單位尺寸為4K作為範例,所進行的邏輯位址以及實體位址間的映射關係的建立,可稱為4K的部分頁映射寫入操作,並與習知的全頁映射的方式有所差異。Regarding the address mapping, please refer to FIG. 3. FIG. 3 is a schematic diagram of a flash memory mapping method according to an embodiment of the present invention. Taking the unit size of each write data as 4K as an example, the establishment of the mapping relationship between the logical address and the physical address can be called a 4K partial page mapping write operation, and it is compared with the known full page. The mapping is different.

在圖3中,本發明實施例提供邏輯頁位址映射表301。邏輯頁位址映射表301提供多個邏輯頁位址的頁位址映射的相關資訊。邏輯頁位址映射表301中具有多數個欄位3011、3012。欄位3011、3012分別對應不同的邏輯頁位址。欄位3011中記錄部分寫入旗標F1,且因為欄位3011所記錄的部分寫入旗標F1等於0,表示欄位3011對應的邏輯頁位址是透過全頁位址映射與實體頁位址相映。也因此,欄位3011另透過子欄位MT1紀錄對應的映射實體記憶組等於實體記憶組L。相對的,欄位3012中記錄部分寫入旗標F2,而因為欄位3012所記錄的部分寫入旗標F2等於1,表示欄位3012對應的邏輯頁位址是透過部分位址映射與實體頁位址相映。也因此,欄位3012另透過子欄位MT2紀錄對應的部份頁位址映射表為部份頁位址映射表A。In FIG. 3, an embodiment of the present invention provides a logical page address mapping table 301. The logical page address mapping table 301 provides information about a page address mapping of a plurality of logical page addresses. The logical page address mapping table 301 has a plurality of fields 3011 and 3012. Fields 3011 and 3012 correspond to different logical page addresses. The field write flag F1 is recorded in field 3011, and because the field write flag F1 recorded in field 3011 is equal to 0, it indicates that the logical page address corresponding to field 3011 is mapped to the physical page through the full page address mapping. Address mapping. Therefore, the field 3011 also records the mapping entity memory group corresponding to the entity memory group L through the sub-field MT1. In contrast, the partial write flag F2 recorded in field 3012, and because the partial write flag F2 recorded in field 3012 is equal to 1, it indicates that the logical page address corresponding to field 3012 is mapped to the entity through partial address mapping. Page addresses are mapped. Therefore, the field 3012 also uses the partial page address mapping table corresponding to the sub-field MT2 record as the partial page address mapping table A.

本發明實施例另提供部份頁位址映射表,依據圖3繪示的部份頁位址映射表A 302,部份頁位址映射表A 302包括節欄位SE1~SE4。各節欄位包括記錄映射實體頁位址、映射段以及映射實體記憶組。以節欄位SE1為範例,節欄位SE1中紀錄的映射實體記憶組3021為實體記憶組M,節欄位SE1中紀錄的映射實體頁位址3022為2(表示第2頁),而節欄位SE1中紀錄的映射段3023為1(表示其中的第1分段資料)。The embodiment of the present invention further provides a partial page address mapping table. According to the partial page address mapping table A 302 shown in FIG. 3, the partial page address mapping table A 302 includes section fields SE1 to SE4. Each section field includes a record mapping entity page address, a mapping segment, and a mapping entity memory group. Taking section field SE1 as an example, the mapped entity memory group 3021 recorded in section field SE1 is entity memory group M, and the mapped entity page address 3022 recorded in section field SE1 is 2 (indicating page 2), and the section The mapping segment 3023 recorded in the field SE1 is 1 (indicating the first segment data therein).

透過節欄位SE1~SE4所紀錄的內容,可以得知對應欄位3012的邏輯頁位址中的資料,分別儲存在:(1)實體記憶組M中的第2頁的第1分段;(2)實體記憶組M中的第2頁的第2分段;(3)實體記憶組N中的第0頁的第2分段;(4)實體記憶組N中的第1頁的第4分段。According to the content recorded in the section fields SE1 ~ SE4, the data in the logical page address corresponding to the field 3012 can be obtained, which are respectively stored in: (1) the first segment of the second page in the physical memory group M; (2) The second segment on page 2 in the physical memory group M; (3) The second segment on page 0 in the physical memory group N; (4) The first page on page 1 in the physical memory group N 4 segments.

以下參照圖4,圖4繪示依據本發明圖3實施例的頁位址映射以及實體記憶組的內容示意圖。其中,依據欄位3011,對應欄位3011的邏輯頁位址中的資料,透過全頁位址映射,可得知儲存於實體記憶組L中的第1頁page1中。而對應欄位3012的邏輯頁位址中的四個分段資料則分別儲存在實體記憶組M的第2頁page2中的第1分段(資料401);實體記憶組M的第2頁page2中的第2分段(資料402);實體記憶組N的第0頁page0中的第2分段(資料403);實體記憶組N的第1頁page1中的第4分段(資料404)。Referring to FIG. 4, FIG. 4 is a schematic diagram of the page address mapping and the content of the physical memory group according to the embodiment of FIG. 3 of the present invention. Among them, according to the field 3011, the data in the logical page address corresponding to the field 3011 can be learned from the first page page1 in the physical memory group L through the full page address mapping. The four segmented data in the logical page address corresponding to field 3012 are stored in the first segment (data 401) of page 2 of page 2 of the physical memory group M respectively; page 2 of page 2 of the physical memory group M Subsection 2 (Source 402); Subsection 2 (Page 403) of page 0 of the physical memory group N; Subsection 4 (Page 404) of page 1 of the physical memory group N .

以下請參照圖5,圖5繪示本發明一實施例的快閃記憶體的示意圖。快閃記憶體500包括記憶胞模組520以及控制器510。記憶胞模組520包括多數個記憶胞,記憶胞以陣列方式排列。控制器510耦接至記憶胞模組520,其中,控制器510可設置一緩衝區。並在執行資料寫動動作中,使緩衝區儲存具有一單位尺寸的寫入資料,並在當儲存在緩衝區的寫入資料的總尺寸達到預設臨界值時,將緩衝器中的寫入資料寫入至快閃記憶體的多數個實體記憶頁的其中之一中。其中,緩衝區可以設置在快取記憶體中,或其他本領域具通常知識者所熟知的資料儲存器中,沒有特定的限制。Please refer to FIG. 5 below, which illustrates a schematic diagram of a flash memory according to an embodiment of the present invention. The flash memory 500 includes a memory cell module 520 and a controller 510. The memory cell module 520 includes a plurality of memory cells, and the memory cells are arranged in an array manner. The controller 510 is coupled to the memory cell module 520. The controller 510 can set a buffer. In the data writing operation, the buffer is used to store write data having a unit size, and when the total size of the write data stored in the buffer reaches a preset threshold, the data in the buffer is written. Data is written to one of the many physical memory pages of flash memory. The buffer can be set in a cache memory or other data storage well known to those with ordinary knowledge in the art, and there is no specific limitation.

此外,控制器510並可針對記憶胞模組520執行各種管理動作。而關於控制器510執行記憶胞模組520的頁位址映射以及實體頁位址的有效與否的判斷動作,其相關係節在前述的多個實施例及實施方式中都有詳盡的說明,在此恕不多贅述。In addition, the controller 510 can perform various management actions on the memory cell module 520. Regarding the controller 510 executing the page address mapping of the memory cell module 520 and determining whether the physical page address is valid, the related sections are described in detail in the foregoing multiple embodiments and implementations. I will not repeat them here.

綜上所述,本發明透過設置緩衝區以暫存具有一單位尺寸的多個寫入資料,並在當緩衝區中的寫入資料的總尺寸接近(或等於)一個實體記憶頁的儲存空間時,再將緩衝區中的全部的寫入資料寫入實體記憶頁中。如此一來,寫入放大的情況可以有效的被控制,快閃記憶體的使用效率也可以得到提升。In summary, the present invention temporarily stores multiple written data with a unit size by setting a buffer, and the total size of the written data in the buffer is close to (or equal to) the storage space of a physical memory page. At that time, all the written data in the buffer is written into the physical memory page. In this way, the situation of write amplification can be effectively controlled, and the use efficiency of the flash memory can be improved.

雖然本發明已以實施例揭露如上,然其並非用以限定本發明,任何所屬技術領域中具有通常知識者,在不脫離本發明的精神和範圍內,當可作些許的更動與潤飾,故本發明的保護範圍當視後附的申請專利範圍所界定者為準。Although the present invention has been disclosed as above with the examples, it is not intended to limit the present invention. Any person with ordinary knowledge in the technical field can make some modifications and retouching without departing from the spirit and scope of the present invention. The protection scope of the present invention shall be determined by the scope of the attached patent application.

S110-S120:快閃記憶體管理的步驟 220:快閃記憶體 210:緩衝區 WD、WD1~WD4:寫入資料 221:實體記憶頁 301:邏輯頁位址映射表 3011、3012:欄位 SE1~SE4:節欄位 401~404:資料 3021~3023:映射實體頁位址 F1~F2:部分寫入旗標 MT1、MT2:子欄位映射實體記憶組 Page0-Page2:實體頁位址 500:快閃記憶體 520:記憶胞模組 510:控制器S110-S120: Flash memory management step 220: Flash memory 210: Buffer WD, WD1 ~ WD4: Write data 221: Physical memory page 301: Logical page address mapping table 3011, 3012: Field SE1 ~ SE4: Section field 401 ~ 404: Data 3021 ~ 3023: Map physical page address F1 ~ F2: Partial write flags MT1, MT2: Sub-field mapping physical memory group Page0-Page2: Physical page address 500: Flash memory 520: memory cell module 510: controller

圖1繪示本發明一實施例的快閃記憶體管理方法的流程圖。 圖2繪示的本發明實施例的快閃記憶體的示意圖。 圖3繪示本發明一實施例的快閃記憶體映射方式的示意圖。 圖4繪示依據本發明圖3實施例的頁位址映射以及實體記憶組的內容示意圖。 圖5繪示本發明一實施例的快閃記憶體的示意圖。FIG. 1 is a flowchart of a flash memory management method according to an embodiment of the present invention. FIG. 2 is a schematic diagram of a flash memory according to an embodiment of the present invention. FIG. 3 is a schematic diagram of a flash memory mapping method according to an embodiment of the present invention. FIG. 4 is a schematic diagram of the page address mapping and the content of the physical memory group according to the embodiment of FIG. 3 of the present invention. FIG. 5 is a schematic diagram of a flash memory according to an embodiment of the invention.

Claims (8)

一種快閃記憶體的管理方法,包括:設置一緩衝區,使該緩衝區儲存多個寫入資料,其中各該寫入資料具有一單位尺寸;以及計算儲存在該緩衝區的該些寫入資料的總尺寸達到一預設臨界值時,將該緩衝器中的該些寫入資料寫入至該快閃記憶體的多數個實體記憶頁的其中之一中。A flash memory management method includes: setting a buffer area so that the buffer area stores a plurality of write data, wherein each write data has a unit size; and calculating the writes stored in the buffer area When the total size of the data reaches a preset threshold, the written data in the buffer is written into one of the plurality of physical memory pages of the flash memory. 如申請專利範圍第1項所述的快閃記憶體的管理方法,其中該些寫入資料對應隨機的多數個邏輯位址或對應連續的多數個邏輯位址。The flash memory management method according to item 1 of the scope of the patent application, wherein the written data corresponds to a random majority of logical addresses or a continuous majority of logical addresses. 如申請專利範圍第1項所述的快閃記憶體的管理方法,其中更包括:建立分別對應多數個邏輯頁位址的多數個部份頁位址映射表,其中,各該部份頁位址映射表包括多數個節欄位,各該節欄位包括一映射實體頁位址、一映射段以及一映射實體記憶組。The flash memory management method according to item 1 of the scope of patent application, further comprising: establishing a plurality of partial page address mapping tables corresponding to a plurality of logical page addresses, wherein each of the partial page bits The address mapping table includes a plurality of section fields, and each section field includes a mapped entity page address, a mapped segment, and a mapped entity memory group. 如申請專利範圍第3項所述的快閃記憶體的管理方法,更包括:設置分別對應該些部份頁位址映射表的一邏輯頁位址映射表,其中該邏輯頁位址映射表具有分別對應多數個邏輯頁位址的多數個欄位,各該欄位記錄一部分寫入旗標以及對應的部份頁位址映射表。According to the flash memory management method described in item 3 of the scope of patent application, the method further includes: setting up a logical page address mapping table corresponding to some partial page address mapping tables, wherein the logical page address mapping table There are a plurality of fields corresponding to a plurality of logical page addresses, respectively, each of which records a part of a write flag and a corresponding part of a page address mapping table. 一種快閃記憶體,包括:一記憶胞模組,包括多數個實體記憶組,各該實體記憶組包括多數個實體記憶頁;以及一控制器,耦接該記憶胞模組,用以:設置一緩衝區,使該緩衝區儲存多個寫入資料,其中各該寫入資料具有一單位尺寸;以及計算儲存在該緩衝區的該些寫入資料的總尺寸達到一預設臨界值時,將該緩衝器中的該些寫入資料寫入至該快閃記憶體的多數個實體記憶頁的其中之一中。A flash memory includes: a memory cell module including a plurality of physical memory groups, each of which includes a plurality of physical memory pages; and a controller coupled to the memory cell module for: setting A buffer, so that the buffer stores a plurality of written data, each of which has a unit size; and when the total size of the written data stored in the buffer reaches a preset critical value, The write data in the buffer is written into one of a plurality of physical memory pages of the flash memory. 如申請專利範圍第5項所述的快閃記憶體,其中該些寫入資料對應隨機的多數個邏輯位址或對應連續的多數個邏輯位址。The flash memory according to item 5 of the scope of patent application, wherein the written data corresponds to a random majority of logical addresses or a continuous majority of logical addresses. 如申請專利範圍第5項所述的快閃記憶體,其中該控制器更建立分別對應多數個邏輯頁位址的多數個部份頁位址映射表,其中,各該部份頁位址映射表包括多數個節欄位,各該節欄位包括一映射實體頁位址、一映射段以及一映射實體記憶組。According to the flash memory in item 5 of the scope of patent application, the controller further establishes a plurality of partial page address mapping tables corresponding to a plurality of logical page addresses, wherein each of the partial page address mappings The table includes a plurality of section fields, each of which includes a mapped entity page address, a mapped segment, and a mapped entity memory group. 如申請專利範圍第7項所述的快閃記憶體,其中該控制器更設置分別對應該些部份頁位址映射表的一邏輯頁位址映射表,其中該邏輯頁位址映射表具有分別對應多數個邏輯頁位址的多數個欄位,各該欄位記錄一部分寫入旗標以及對應的部份頁位址映射表。The flash memory according to item 7 of the scope of the patent application, wherein the controller further sets a logical page address mapping table corresponding to some partial page address mapping tables, wherein the logical page address mapping table has Corresponding to a plurality of fields of a plurality of logical page addresses, each of which records a part of a write flag and a corresponding part of a page address mapping table.
TW106104758A 2017-02-14 2017-02-14 Flash memory and management method thereof TWI635391B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
TW106104758A TWI635391B (en) 2017-02-14 2017-02-14 Flash memory and management method thereof
CN201710165000.0A CN108446238A (en) 2017-02-14 2017-03-20 Flash memory and management method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW106104758A TWI635391B (en) 2017-02-14 2017-02-14 Flash memory and management method thereof

Publications (2)

Publication Number Publication Date
TW201830244A TW201830244A (en) 2018-08-16
TWI635391B true TWI635391B (en) 2018-09-11

Family

ID=63190875

Family Applications (1)

Application Number Title Priority Date Filing Date
TW106104758A TWI635391B (en) 2017-02-14 2017-02-14 Flash memory and management method thereof

Country Status (2)

Country Link
CN (1) CN108446238A (en)
TW (1) TWI635391B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6767532B2 (en) 2019-03-11 2020-10-14 ウィンボンド エレクトロニクス コーポレーション Semiconductor storage device
TWI776028B (en) * 2019-03-14 2022-09-01 點序科技股份有限公司 Flash memory management method and flash memory

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW201306034A (en) * 2011-02-28 2013-02-01 Apple Inc Efficient buffering for a system having non-volatile memory
US20150193299A1 (en) * 2014-01-09 2015-07-09 SanDisk Technologies, Inc. Selective copyback for on die buffered non-volatile memory
TW201539188A (en) * 2014-04-09 2015-10-16 Realtek Semiconductor Corp Memory controller and memory control method
TW201635150A (en) * 2014-12-23 2016-10-01 英特爾公司 Speculative reads in buffered memory

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7058784B2 (en) * 2003-07-04 2006-06-06 Solid State System Co., Ltd. Method for managing access operation on nonvolatile memory and block structure thereof
CN101661791A (en) * 2008-08-26 2010-03-03 创惟科技股份有限公司 Memory module and executing method of same
WO2012106362A2 (en) * 2011-01-31 2012-08-09 Fusion-Io, Inc. Apparatus, system, and method for managing eviction of data
CN102298555B (en) * 2011-08-22 2016-04-27 宜兴市华星特种陶瓷科技有限公司 Based on the modularization flash management system of NAND technology
US8799561B2 (en) * 2012-07-27 2014-08-05 International Business Machines Corporation Valid page threshold based garbage collection for solid state drive
CN103425438B (en) * 2013-07-15 2016-08-10 记忆科技(深圳)有限公司 Optimize method and the solid state hard disc thereof of write request of solid state disk
US10013177B2 (en) * 2015-04-20 2018-07-03 Hewlett Packard Enterprise Development Lp Low write amplification in solid state drive

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW201306034A (en) * 2011-02-28 2013-02-01 Apple Inc Efficient buffering for a system having non-volatile memory
US20150193299A1 (en) * 2014-01-09 2015-07-09 SanDisk Technologies, Inc. Selective copyback for on die buffered non-volatile memory
TW201539188A (en) * 2014-04-09 2015-10-16 Realtek Semiconductor Corp Memory controller and memory control method
TW201635150A (en) * 2014-12-23 2016-10-01 英特爾公司 Speculative reads in buffered memory

Also Published As

Publication number Publication date
TW201830244A (en) 2018-08-16
CN108446238A (en) 2018-08-24

Similar Documents

Publication Publication Date Title
US10061704B2 (en) Systems and methods for managing cache of a data storage device
US10162554B2 (en) System and method for controlling a programmable deduplication ratio for a memory system
CN109952565B (en) Memory access techniques
JP2014505297A (en) Memory address conversion
JP5597306B2 (en) Sectorized cache with high storage efficiency
CN102214143A (en) Method and device for managing multilayer unit flash memory, and storage equipment
TWI570559B (en) Flash memory and accessing method thereof
CN110532200B (en) Memory system based on hybrid memory architecture
CN110795363B (en) Hot page prediction method and page scheduling method of storage medium
CN109918316B (en) Method and system for reducing FTL address mapping space
US8423707B2 (en) Data access method for flash memory and storage system and controller using the same
CN103198021B (en) A kind of method improving solid state disk data transmission efficiency
CN105205008B (en) Reduce the method that log blocks mapping table memory source occupies in mixed-use developments algorithm
TWI635391B (en) Flash memory and management method thereof
CN102999441A (en) Fine granularity memory access method
CN111290706B (en) Double-layer read-write wear balancing method based on bloom filter
US8316210B2 (en) Dividing a logical memory space into ranges and sets for address translation
CN106326135B (en) Method and device for translating data of non-volatile memory (NVM)
TW201435586A (en) Flash memory apparatus, and method and device for managing data thereof
CN111143313B (en) Method for improving log block read-write performance of hybrid mapping algorithm
TWI776028B (en) Flash memory management method and flash memory
TW202145000A (en) Flush method for mapping table of solid state drive
TWI835221B (en) Memory device and operation method thereof
TWI559137B (en) Solid storage device with mixed storage mode
TWI551987B (en) Address mapping method for flash memory module