CA2161344A1 - Flash memory mass storage architecture - Google Patents
Flash memory mass storage architectureInfo
- Publication number
- CA2161344A1 CA2161344A1 CA002161344A CA2161344A CA2161344A1 CA 2161344 A1 CA2161344 A1 CA 2161344A1 CA 002161344 A CA002161344 A CA 002161344A CA 2161344 A CA2161344 A CA 2161344A CA 2161344 A1 CA2161344 A1 CA 2161344A1
- Authority
- CA
- Canada
- Prior art keywords
- block
- data
- flag
- blocks
- erase
- Prior art date
- Legal status (The legal status 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 status listed.)
- Abandoned
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0238—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory
- G06F12/0246—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory in block erasable memory, e.g. flash memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/0292—User address space allocation, e.g. contiguous or non contiguous base addressing using tables or multilevel address translation means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/10—Providing a specific technical effect
- G06F2212/1032—Reliability improvement, data loss prevention, degraded operation etc
- G06F2212/1036—Life time enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/72—Details relating to flash memory management
- G06F2212/7211—Wear leveling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0662—Virtualisation aspects
- G06F3/0664—Virtualisation aspects at device level, e.g. emulation of a storage device or system
Abstract
A semiconductor mass storage sys-tem (100) and architecture can be substi-tuted for a rotating hard disk. The system and architecture avoid an eras cycle each time information stored in the mass stor-age is changed. Erase cycles are avoided by programming an altered data file into an empty mass storage block (step 202-206) rather than over itself as hard disk would.
Periodically, the mass storage will need to be cleaned up (step 204). Secondly, means are provied for evenly using all blocks in the mass storage (Fig. 7). These advan-tages are achieved through the use of sev-eral flags (200), a map to correlate a logical address of a block to a physical address of tDat block (308, 408) aDd a count regis-ter for each block. ln particular, flags are provided for defective blocks (118), used blocks (112), old version of a block (104, 116), a count to determine the number of times a block has been erased and written and erase inhibit flag (200).
Periodically, the mass storage will need to be cleaned up (step 204). Secondly, means are provied for evenly using all blocks in the mass storage (Fig. 7). These advan-tages are achieved through the use of sev-eral flags (200), a map to correlate a logical address of a block to a physical address of tDat block (308, 408) aDd a count regis-ter for each block. ln particular, flags are provided for defective blocks (118), used blocks (112), old version of a block (104, 116), a count to determine the number of times a block has been erased and written and erase inhibit flag (200).
Description
~094/W69 21 613 ~ ~ PCT~S94/03168 FLASH MEMORY MASS STORAGE ARCHITECTURE
Field of the Invention This invention relates to the field of mass storage for computers. More particularly, this invention relates to an architecture for replacing a hard disk with a semiconductor non-volatile memory and in particular flash memory.
Backqround of the Invention Computers have used rotating magnetic media for mass storage of data, programs and information. Though widely used and commonly accepted, such hard disk drives suffer from a variety of deficiencies. Because of the rotation Gf the disk, there is an inherent latency in extracting information from a hard disk drive.
Other problems are especially dramatic in portable computers. In particular, hard disks are unable to withstand many of the kinds of physical shock that a portable computer will likely sustain. Further, the motor for rotating the disk consumes significant amounts of power decreasing the battery life for portable computers.
~G Solid state memory is an ideal choice f~r replacing a hard disk drive for mass storage because it can resolve the problems cited above. Potential solutions have been proposed for replacing a hard disk drive with a semiconductor memory. For such a system to be truly useful, the memory must be non-volatile and alterable. The inventors have determined that flash memory is preferred for such a replacement. It should be noted that E2 PROM is also suitable as a replacement for a hard disk drive.
Flash memory is a single transistor memory cell which is programmable through hot electron injection and erasable through Fowler-Nordheim tunneling. The programming and erasing of such a memory cell requires current to pass W094l~369 PCT~S94/03168 2~ 3 ~ -2-through the dielectric surrounding a floating gate electrode. Because of this, such types of memory have a finite number of erase-write cycles. Eventually, the dielectric will fail. Manufacturers of flash cell devices specify the limit for the number erase-write cycles as between lO,000 and lO0,000. Accordingly, unlike rotating magnetic media, a flash memory mass storage device does not have an indefinite lifetime.
Another requirement for a semiconductor mass storage device to be successful is that its use in lieu of a rotating media hard disk mass storage device be transparent to the system designer and the user. In other words, the designer of a computer incorporating such a semiconductor mass storage device could simply remove the hard disk and replace it with a semiconductor mass storage. All presently available commercial software should operate on a system employing such a semiconductor hard disk without the necessity of any modification.
SunDisk proposed an architecture for a semiconductor mass storage using flash memory at the Silicon Valley PC
Design Conference July 9, l99l. That mass storage system included read-write block sizes of 512 Bytes (or multiples thereof) just like IBM PC compatible hard disk sector sizes.
(IBM PC is a trademark of IBM Corporation.) During an erase cycle, an entire block is first fully programmed and then erased.
As in conventional hard disks, it appears in the SunDisk architecture that there is an erase-before-write cycle each time data is changed in the mass storage. Thus, if a program or data block is to be changed, the data is written to RAM and appropriately changed, the flash block is fully programmed, then erased and then reprogrammed to the new memory condition. Unlike a hard disk device, in a flash memory device an erase cycle is slow which can significantly W094/~369 ~ PCT~S94/03168 reduce the performance of a system utilizing flash memory as its mass storage.
Though such an architecture provides a workable semiconductor mass storage, there are several inefficiencies. First of all, each time a memory block is changed, there is a delay to the entire system due to the necessary erase-before-write cycle before reprogramming the altered information back into the block. The overhead associated with erase-before-write cycles is costly in terms of system performance.
Secondly, hard disk users typically store both information which is rarely changed and information which is frequently changed. For example, a commercial spread sheet or word processing software programs stored on a user's system are rarely, if ever, changed. However, the spread sheet data files or word processing documents are frequently changed. Thus, different sectors of a hard disk typically have dramatically different usage in terms of the number of times the information stored thereon is changed. While this disparity has no impact on a hard disk because of its insensitivity to data changes, in a flash memory device, this variance can cause sections of the mass storage to wear out and be unusable significantly sooner than other sections of the mass storage.
Summary of the Invention The pres~nt invention discloses two primary algorithms and an associated hardware architecture for a semiconductor mass storage device. It will be understood that data file in this patent document refers to any computer file including commercial software, a user program, word processing software document, spread sheet file and the like. The first algorithm provides means for avoiding an erase-before-write cycle when writing a modified data file W094l~369 ~ 3 ~ PCT~S94/03168 ~ac~ onto the mass storage device. Instead, no erase is performed and the modified data file is written onto an empty portion of the mass storage. In addition, the second algorithm prevents any portion of the mass storage ~rom being erased a substantially larger number of times than any other portion. This prevents any one block of the mass storage from failing and becoming unusable earlier than any other block thereby extending the life of the entire mass storage.
The semiconductor mass storage architecture has blocks sized to conform with commercial hard disk sector sizes.
The blocks are individually erasable. In one embodiment, the semiconductor mass storage of the present invention can be substituted for a rotating hard disk with no impact to the user, so that such a substitution will be transparent.
Means are provided for avoiding the erase-before-write cycle each time information stored in the mass storage is changed.
(The erase cycle is understood to include, fully programming each bit in the block to be erased, and then erasing all the bits in the block.) According to the first algorithm, erase cycles are avoided by programming an altered data file into an empty mass storage block rather than over itself after an erase cycle of that block as done on a conventional hard disk.
This would ordinarily not be possible when using conventional mass storage because the central processor and commercial software available in conventional computer systems are not configured to track continually changing physical locations of data files. The present invention includes a programmable map to maintain a correlation between the logical address 308 and the physical address 408 of the updated information files.
Periodically, the mass storage will fill up because there have been no erase cycles. At such times, the mass W094/~369 PCT~S94/03168 21 6~ 34~
storage needs to be cleaned up with a multi-sector erase as fully described in the detailed description below.
According to the second algorithm, means are provided for evenly using all blocks in the mass storage. A counter tracks the number of times each block is erased. A
programmable maximum value for the counter is also provided.
As the number of erase cycles for a block becomes one less than the maximum, the block is erased one last time and written with another file having a then smallest number of erase cycles. It is also prevented from being erased thereafter by setting its erase inhibit flag. After all blocks approach this maximum, all the erase counters and inhibit flags are cleared and the second algorithm is then repeated. In this way, no block can be erased a substantial number of times more than any other block.
These advantages are achieved through the use of several flags and a count register for each block. In particular, flags are provided for defective blocks, used blocks, old version of a block, a count to determine the number of times a block has been erased and written and an erase inhibit flag.
Brief DescriPtion of the Drawinqs Figure 1 shows an architecture for a semiconductor mass storage.
Figure 2 shows the architecture of Figure 1 wherein the data in one block has been altered and stored in a new physical address.
Figure 3 shows a block diagram of an erase cycle usage according to algorithm 1 of the present invention.
~igure 4 shows a simplified block diagram of the old/new flag system integrally formed with the memory.
Figure 5 shows a flow chart block diagram for PCT~S94/03168 W094/~369 3 ~ -~
algorithm 1.
Figure 6 shows an-additional architecture according to the preferred embodiment of the present invention.
Figure 7 shows a flow chart block diagram of algorithm 2 of the present invention.
Figure 8 shows a flow chart block diagram of a read algorithm according to the present invention.
Detailed Description of the Preferred Embodiment Figure 1 shows an architecture for a semiconductor mass storage according to the present invention. In the preferred embodiment, all of the memory storage is flash EEPROM. It is possible to substitute E2PROM for some or all of the data bits shown. A memory storage 100 is arranged into N blocks of data from zero through N-1. Each of the blocks of data is M Bytes long. In the preferred embodiment, each block is 512 Bytes long to correspond with a sector length in a commercially available hard disk drive.
In addition to the memory data block 102, a flag 104 is directly related to each data block 102. The memory 100 can contain as much memory storage as a user desires. An example of a mass storage device might include 100 MByte of addressable storage.
A non-volatile content addressable memory (CAM) 106 is associated with the memory storage 100. In the preferred embodiment, the CAM 106 is formed of flash memory. The CAM
106 can also be E2PROM. There is one entry in the CAM 106 for every one of the N blocks in the mass storage 100. Each entry includes a number of fields which will be described below. The CAM 106 is also formed of a non-volatile memory because loss of its information would make retrieval of the data files stored in the mass storage 100 impossible.
As described above in the Background of the Invention, conventional computer systems are not configured to track W094l~369 2 I 6 l 3 ~ ~ PCT~S94tO3168 continually changing physical locations of data files.
According to the present invention, each time a data file is changed it is stored into a new physical location in the mass storage. Thus, implementation of the architecture of the present invention requires a mapping of the logical address 308, i.e., the address where the computer system believes the data file is stored to the physical address 408, i.e., the actual location the data file can be found is stored in the mass storage.
The logical address 308 portion of the map 108 and the flags 112, 116 and 118 form part of the CAM 106. It is possible to use other storage means than a CAM to store the address map, such as a look-up table. However, a CAM is the most efficient means known to the inventors. It is not necessary that the physical address 408 portion of the map 108 form part of the CAM. Indeed, the physical address 408 portion of the map 108 can be ordinary flash memory, E2PROM
or even ROM. If ROM is selected for the physical address 408 array of the map 108, a defect in the ROM will prevent the block corresponding to that physical address 408 from ever being addressed. Accordingly, a changeable nonvolatile memory is preferred. Note that any replacement circuit for the CAM should be nonvolatile. Otherwise, loss or removal of power to the system will result in loss of the ability to find the data files in the mass storage.
Assume for example that a user is preparing a word processing document and instructs the computer to save the document. The document will be stored in the mass storage system as shown in Figure 1. The computer system will assign it a logical address 308, for example ~26H. The mass storage system of the present invention will select a physical address 408 of an unused block or blocks in the mass storage 100 for storing the document, e.g. 728H. That map correlating the logical address 308 to the physical WOg4/~36g PCT~S94/03168 ~,~6~
address 408 is stored in the CAM 106. As the data is programmed, the system of the present invention also sets the used/free flag 112 to indicate that this block has been written without being erased. The used/free flag 112 also forms a portion of the CAM 106. One used/free flag 112 is provided for each entry of the CAM 106.
Later, assume the user retrieves the document, makes a -change and again instructs the computer to store the document. To avoid an erase-before-write cycle, the system of the present invention provides means for locating a block having its used/free flag 112 unset (not programmed) which indicates that the associated block is erased. The system then sets the used/free flag for the new block 114 (Figure 2) and then stores the modified document in that new block 114. Next, the system sets the old/new flag 116 of the previous version of the document indicating that this is an old unneeded version of the document. Lastly, the system updates the correlation between the logical address 308 and the actual physical address 408. In this way, the system of the present invention avoids the overhead of an erase cycle which is required in the erase-before-write of conventional systems to store a modified version of a previous document.
The writing to mass storage process outlined above is repeated until the entire mass storage memory 100 has been filled. A full mass storage is indicated by no unset used/free flags 112 in the CAM 106. At that time a multi-sector erase is necessary and those blocks in the memory 100 and their associated CAM 106 entries having an oldlnew flag 116 set are all erased simultaneously. Note that it is not necessary for 100% of the blocks to have a set used/free flag 112 for a multi-sector erase to occur. For example, if a data file requiring three blocks were being written and only two blocks having unset used/free flags 112 were available a multi-sector erase can be run.
W094/~369 2 1 B 1 3 ~ 4 PCT~S94/03168 A simultaneous erase is not needed with prior art implementations because those embodiments utilize an erase-- before-write cycle rather than retaining superseded versions of data files. In such circuits a latch of volatile logic circuits is set to couple the voltage necessary to erase the flash cells in the block. Because of the likely large number of memory blocks in the mass storage 100, if the CAM
106 and mass storage 100 are on the same integrated circuit (chip) coupling the old/new flag 116 to the latches in parallel would typically be very expensive in terms of surface area of the chip and coupling the old/new flags 116 serially to the latches would be expensive in terms of system performance. If the CAM 106 and the mass storage 100 are on separate chips, it is doubtful that either device could have sufficient I/O capability to interconnect the old/new flags 116 to the latches in parallel and thus, the system would suffer from a serial transfer of that information for a multi-sector erase.
Because of these problems it is preferable that no updating of the latches be performed prior to an erase of all blocks having a set old/new flag 116. To avoid this step, a plurality of old/new flag systems 104 are intimately associated with each block in the memory 102 and is programmed by the same sequence of instructions as the old/new flag 116 of the CAM 106.
Figure 4 shows a simplified block diagram of the old/new flag system 104 which includes a non-volatile bit 120 having data which mirrors the old/new flag 116. In addition there is a volatile latch 122 coupled to receive the data in the bit 120 from the latch during an erase cycle. At the time of an erase, the data in each of the bits 120 is simultaneously coupled to each appropriate ones of the latches 122 under control of a load signal coupled to each latch 122 over a load line L. Upon receiving a signal W094/~369 PCT~S94/03168 ~,~6~ o-to perform the eraæe, the latch for every block having its associated bit 120 set then couples the voltage necessary to perform an erase of that block and its associated bit 120.
After the erase is complete and verified, all the latches 122 are individually reset to a predetermined state under control of a reset signal coupled to each latch 122 over a reset line R.
For certain applications of the present invention, especially for low power portable computers, a simultaneous erase of all blocks having their respective old/new flags set may be undesirable. For such applications, the blocks can be segregated into groups of blocks. Each group has a unique control line to load the latches from the nonvolatile bits. In this mode, during an erase cycle, the control lines are sequentially activated and the groups of blocks sequentially erased.
Figure 5 shows algorithm 1 according to the present invention. When the system of the present invention receives an instruction to program data into the mass storage (step 200), then the system attempts to locate a free block (step 202), i.e., a block having an unset ~not programmed) used/free flag. If successful, the system sets the used/free flag for that block and programs the data into that block (step 206).
If on the other hand, the system is unable to locate a block having an unset used/free flag, the system erases the flags (used/free and old/new) and data for all blocks having a set old/new flag (step 204) and then searches for a block having an unset used/free flag (step 202). Such a block has just been formed by step 204. The system then sets the used/free flag for that block and programs the data file into that block (step 206).
If the data file is a modified version of a previously existing file, the system must prevent the superseded w094/~369 2 ~ 6~ PCT~S94/03168 version from being accessed. The system determines whether the data file supersedes a previous data file (step 208).
~ If so, the system sets the old/new flag associated with the superseded block (step 210). If on the other hand, the data file to be stored is a newly created data file, the step of setting the old/new flag (step 210) is skipped because there is no superseded block. Lastly, the map for correlating the logical address 308 to the physical address 408 is updated (step 212).
By following the procedure outlined above, the overhead associated with an erase cycle is avoided for each write to the memory 100 except for periodically. This vastly improves the performance of the overall computer system employing the architecture of the present invention.
In the preferred embodiment of the present invention, the programming of the flash memory follows the procedure commonly understood by those of ordinary skill in the art.
In other words, the program impulses are appropriately applied to the bits to be programmed and then compared to the data being programmed to ensure that proper programming has occurred. In the event that a bit fails to be erased or programmed properly, a defect flag 118 in the CAM 106 is set preventing that block from being used again.
In addition to saving the overhead of the erase cycle all but periodically, utilization of the present invention tends to more evenly distribute the erase cycles amongst certain portions of the blocks of the mass storage. Figure 3 schematically shows the types of information stored in utilizing a mass storage media 150. One portion of the mass storage 150 contains commercial applications software 152 such as word processing, spreadsheet, calendaring, calculators and the like. These portions of the mass storage 150 rarely, if ever, require an erase-reprogram cycle according to the algorithm described above.
W094/~369 PCT~S94/03168 ~6~3 ~ -12-A second section of the mass storage 150 contains user data 154. The user data 154 is frequently altered requiring the information to be reprogrammed into blocks of the free space 156 under the algorithm described above. A third portion of the mass storage 150 contains free space 156 of unprogrammed blocks.
By following the algorithm above, the storage blocks in the portions 154 and 156 of the memory 150 will recycle data files and thus be erased and reprogrammed significantly more often than the commercial applications software portion 152 of the memory 150. Accordingly, the mass storage 150 will wear out more quickly in the user data 154 and the free space 156 sections of the memory requiring earlier replacement than in sections 152 of the mass storage having data files which are rarely changed. As the number of free blocks diminishes providing a smaller number of blocks through which to recycle data files, the r~m~;n;ng blocks become erased more frequently exacerbating the problem.
A second algorithm is provided for leveling erase cycles amongst all the blocks within the entire mass storage device as shown in Figure 6. A counter is provided for each block to count the number of times each block has been erased and reprogrammed. An erase inhibit flag is also provided for each block. Once the erase count has reached the maximum for any block, the erase inhibit flag is set for that block. After that time that block cannot be erased until a clean-out erase is performed. Referring to Figure 3, if only algorithm 1 is used eventually all of the blocks in the user data 154 and the free space 156 portions of the mass storage 150 will reach the maximum count and have their respective erase inhibit flags set. Because of this, a reallocation of the rarely erased data files stored in the memory 152 is made into the memory 154 and/or 156.
In this way, sections of the mass storage which have been W094/~369 2161~ ~ ~ PCT~S94/03168 erased numerous times are programmed with a reallocated data file which is rarely changed thereby allowing all sections of the mass storage to eventually approach parity of erase cycles. Like the multi-sector erase, a clean-out erase can be performed in the event that there is insufficient available storage for a data file presently being performed.
For example, if all but two blocks have their respective erase inhibit flags set, and a three or more block data file is being programmed, a clean-out erase can be performed to provide sufficient storage for the data file.
Once the erase inhibit flag is set for all the blocks, indicating that all the blocks have achieved parity in erase cycles, the erase inhibit and erase count registers are erased and the cycle is repeated. The selection of the maximum count depends upon the system requirements. As the value for the maximum count increases, the disparity between erase count cycles of various blocks can also increase.
However, because data is shifted as a result of achieving maximum erase count this process of smoothing cycles throughout the mass storage of itself introduces additional erase cycles because a block of information is transferred from a physical block having few erases to a block having the maximum number of erases. Accordingly, though low maximum count values reduce the disparity between erase cycles amongst the blocks it also increases the number of erase cycles to which the blocks are subjected.
Accordingly, individual users may select an erase count depending upon the system needs.
In the preferred embodiment, algorithm 2 is merged with algorithm l as shown in Figure 7. An instruction is provided by the computer system to write a data file to the mass storage (step 230) which starts the combined algorithm l and algorithm 2 sequence. It is first determined whether the mass storage is full (step 232). If the mass storage is W094/~36g PCT~S94/03168 ~5~3~4 not full, i.e., it has a block with its used/free flag unset, the algorithm continues and stores the data file into such a block (step 234).
If on the other hand, it is determined that there are no free blocks, then it is next determined whether there are any blocks which have both the old/new flag set AND the erase inhibit flag unset (step 236). If there are no blocks which have both the old/new flag set AND the erase inhibit flag unset (step 236), the system of the present invention erases the data file, used/free flag and old/new flag in each block having its old/new flag set, and erases the counter and erase inhibit flag for every block (step 238).
Step 238 is also performed in the event there are insufficient blocks remaining to store a pending data file.
The algorithm then returns to block (step 232) to detenmine whether the disk is full.
If the system can find a block having both the old/new flag set AND the erase inhibit flag unset (step 236), then the system executes an erase procedure and erases the data 2~ file, used/free flag and old/new flag in each block having its old/new flag set. The counter is incremented and the erase inhibit flag for such blocks is not disturbed.
It is then detenmined whether any block having its used/free flag unset has its counter at the maximum count ~step 242). If not, then the system of the present invention returns to decision step 232 and investigates again whether there is any block having its used/free flag unset (step 232).
On the other hand, if there is a block having its erase count at the maximum value, a data file is copied from another block having the then least count value (step 244) into the location having COUNT = COUNT~. The erase inhibit flag is then set (step 244). Note that a data file will not be copied from a block having its erase count at one less ~941~369 2 I fi 13 ~ ~ PCT~S94103168 than the maximum value, COUNT~-l. Making such a reallocation from a source block having COUNT~X-1 to a destination block having COUNT~X results in having both blocks at COUNT~ and no net gain. Further, the block previously having its erase count at COUNT~-l is erased to no advantage, thus the erase cycle for that block would be wasted.
The old/new flag from the source block is then set (step 246) so that it can be erased during the next execution of an erase step 240. In that way the source block can be used for storage until its erase count reaches maximum and its erase inhibit flag is set. The algorithm then returns to step 242 to determine whether there are now any blocks having an unset used/free flag with an erase count less than COUNT~. It will be understood that each time a data file is programmed or moved according to the algorithm of Figure 7 that the map in the CAM which correlates the logical address 308 to physical address 408 is updated so that the computer system can always access the data files.
The efficiency of these algorithms has been tested by simulation. In the simulation it was assumed that the mass storage was 50% filled with data files that are not changed, 30% with data files that are routinely changed and 20%
empty. Of the 30% of the data files that are routinely changed, ~ are rewritten 70% of the time, ~ are rewritten 25% of the time and ~ are rewritten 5% of the time. The simulation showed that the algorithm l improves the number of cycles until any block has reached failure by between six and seven times and algorithm 2 by approximately two times over the improvement gained using algorithm l alone.
Depending upon the design criterion of a target system, it is possible to utilize either algorithm l, algorithm 2 or the preferred merged algorithm. Algorithm l and the merged W094~3369 PCT~S94J03168 2~C~3~
algorithm have been described above.
In the preferred embodiment, a bit is programmed into the counter for each erase cycle rather than using binary counting. Thus, an eight bit counter register would only ~e able to count to eight. This avoids having to erase the counter and then reprogramming it with an incremented value as would be necessary for binary counting. This is preferred because it avoids having to temporarily store the count value for all of the blocks being erased. By programming a bit for each, the counter registers need not be erased until all the blocks reach maximum count and there is a general erase.
Because the mass storage apparatus of the present invention can ac~ommodate large data storage, it is likely that many blocks will be flagged for a clean-out erase.
Either a temporary volatile storage would be necessary for each block to store the previous count value prior to incrementing and reprogramming or the erase and updating of the counters would have to be done one after the other. One solution requires integrated circuit surface area and the other degrades performance. Note however, that if binary counting is desired the erase counter can be erased each time the block is erased and immediately reprogrammed.
Because this will happen only during the periodic erase cycle described relative to the first algorithm some system designers may find this acceptable.
The read algorithm according to the present invention is shown in Figure 8. A read instruction is received by the mass storage apparatus of the present invention from the computer system (step 270). Concurrent with receiving the read instruction, the system also receives the logical address 308 of the data file needed by the computer system (step 271). The apparatus of the present invention concatenates all the appropriate flags to the logical ~v094l23369 ~ 4 ~ PCT~S94/03168 address 308 including having a set used/free flag, and unset new/old and defect flags (step 272). If a match is found in the CAM (step 273), the data file is read (step 275) otherwise a signal is returned to the computer system that the data file was not found (step 274).
The present invention is described relative to a preferred embodiment. Modifications or improvements which become apparent to one of ordinary skill in the art after reading this disclosure are deemed within the spirit and scope of this invention.
Field of the Invention This invention relates to the field of mass storage for computers. More particularly, this invention relates to an architecture for replacing a hard disk with a semiconductor non-volatile memory and in particular flash memory.
Backqround of the Invention Computers have used rotating magnetic media for mass storage of data, programs and information. Though widely used and commonly accepted, such hard disk drives suffer from a variety of deficiencies. Because of the rotation Gf the disk, there is an inherent latency in extracting information from a hard disk drive.
Other problems are especially dramatic in portable computers. In particular, hard disks are unable to withstand many of the kinds of physical shock that a portable computer will likely sustain. Further, the motor for rotating the disk consumes significant amounts of power decreasing the battery life for portable computers.
~G Solid state memory is an ideal choice f~r replacing a hard disk drive for mass storage because it can resolve the problems cited above. Potential solutions have been proposed for replacing a hard disk drive with a semiconductor memory. For such a system to be truly useful, the memory must be non-volatile and alterable. The inventors have determined that flash memory is preferred for such a replacement. It should be noted that E2 PROM is also suitable as a replacement for a hard disk drive.
Flash memory is a single transistor memory cell which is programmable through hot electron injection and erasable through Fowler-Nordheim tunneling. The programming and erasing of such a memory cell requires current to pass W094l~369 PCT~S94/03168 2~ 3 ~ -2-through the dielectric surrounding a floating gate electrode. Because of this, such types of memory have a finite number of erase-write cycles. Eventually, the dielectric will fail. Manufacturers of flash cell devices specify the limit for the number erase-write cycles as between lO,000 and lO0,000. Accordingly, unlike rotating magnetic media, a flash memory mass storage device does not have an indefinite lifetime.
Another requirement for a semiconductor mass storage device to be successful is that its use in lieu of a rotating media hard disk mass storage device be transparent to the system designer and the user. In other words, the designer of a computer incorporating such a semiconductor mass storage device could simply remove the hard disk and replace it with a semiconductor mass storage. All presently available commercial software should operate on a system employing such a semiconductor hard disk without the necessity of any modification.
SunDisk proposed an architecture for a semiconductor mass storage using flash memory at the Silicon Valley PC
Design Conference July 9, l99l. That mass storage system included read-write block sizes of 512 Bytes (or multiples thereof) just like IBM PC compatible hard disk sector sizes.
(IBM PC is a trademark of IBM Corporation.) During an erase cycle, an entire block is first fully programmed and then erased.
As in conventional hard disks, it appears in the SunDisk architecture that there is an erase-before-write cycle each time data is changed in the mass storage. Thus, if a program or data block is to be changed, the data is written to RAM and appropriately changed, the flash block is fully programmed, then erased and then reprogrammed to the new memory condition. Unlike a hard disk device, in a flash memory device an erase cycle is slow which can significantly W094/~369 ~ PCT~S94/03168 reduce the performance of a system utilizing flash memory as its mass storage.
Though such an architecture provides a workable semiconductor mass storage, there are several inefficiencies. First of all, each time a memory block is changed, there is a delay to the entire system due to the necessary erase-before-write cycle before reprogramming the altered information back into the block. The overhead associated with erase-before-write cycles is costly in terms of system performance.
Secondly, hard disk users typically store both information which is rarely changed and information which is frequently changed. For example, a commercial spread sheet or word processing software programs stored on a user's system are rarely, if ever, changed. However, the spread sheet data files or word processing documents are frequently changed. Thus, different sectors of a hard disk typically have dramatically different usage in terms of the number of times the information stored thereon is changed. While this disparity has no impact on a hard disk because of its insensitivity to data changes, in a flash memory device, this variance can cause sections of the mass storage to wear out and be unusable significantly sooner than other sections of the mass storage.
Summary of the Invention The pres~nt invention discloses two primary algorithms and an associated hardware architecture for a semiconductor mass storage device. It will be understood that data file in this patent document refers to any computer file including commercial software, a user program, word processing software document, spread sheet file and the like. The first algorithm provides means for avoiding an erase-before-write cycle when writing a modified data file W094l~369 ~ 3 ~ PCT~S94/03168 ~ac~ onto the mass storage device. Instead, no erase is performed and the modified data file is written onto an empty portion of the mass storage. In addition, the second algorithm prevents any portion of the mass storage ~rom being erased a substantially larger number of times than any other portion. This prevents any one block of the mass storage from failing and becoming unusable earlier than any other block thereby extending the life of the entire mass storage.
The semiconductor mass storage architecture has blocks sized to conform with commercial hard disk sector sizes.
The blocks are individually erasable. In one embodiment, the semiconductor mass storage of the present invention can be substituted for a rotating hard disk with no impact to the user, so that such a substitution will be transparent.
Means are provided for avoiding the erase-before-write cycle each time information stored in the mass storage is changed.
(The erase cycle is understood to include, fully programming each bit in the block to be erased, and then erasing all the bits in the block.) According to the first algorithm, erase cycles are avoided by programming an altered data file into an empty mass storage block rather than over itself after an erase cycle of that block as done on a conventional hard disk.
This would ordinarily not be possible when using conventional mass storage because the central processor and commercial software available in conventional computer systems are not configured to track continually changing physical locations of data files. The present invention includes a programmable map to maintain a correlation between the logical address 308 and the physical address 408 of the updated information files.
Periodically, the mass storage will fill up because there have been no erase cycles. At such times, the mass W094/~369 PCT~S94/03168 21 6~ 34~
storage needs to be cleaned up with a multi-sector erase as fully described in the detailed description below.
According to the second algorithm, means are provided for evenly using all blocks in the mass storage. A counter tracks the number of times each block is erased. A
programmable maximum value for the counter is also provided.
As the number of erase cycles for a block becomes one less than the maximum, the block is erased one last time and written with another file having a then smallest number of erase cycles. It is also prevented from being erased thereafter by setting its erase inhibit flag. After all blocks approach this maximum, all the erase counters and inhibit flags are cleared and the second algorithm is then repeated. In this way, no block can be erased a substantial number of times more than any other block.
These advantages are achieved through the use of several flags and a count register for each block. In particular, flags are provided for defective blocks, used blocks, old version of a block, a count to determine the number of times a block has been erased and written and an erase inhibit flag.
Brief DescriPtion of the Drawinqs Figure 1 shows an architecture for a semiconductor mass storage.
Figure 2 shows the architecture of Figure 1 wherein the data in one block has been altered and stored in a new physical address.
Figure 3 shows a block diagram of an erase cycle usage according to algorithm 1 of the present invention.
~igure 4 shows a simplified block diagram of the old/new flag system integrally formed with the memory.
Figure 5 shows a flow chart block diagram for PCT~S94/03168 W094/~369 3 ~ -~
algorithm 1.
Figure 6 shows an-additional architecture according to the preferred embodiment of the present invention.
Figure 7 shows a flow chart block diagram of algorithm 2 of the present invention.
Figure 8 shows a flow chart block diagram of a read algorithm according to the present invention.
Detailed Description of the Preferred Embodiment Figure 1 shows an architecture for a semiconductor mass storage according to the present invention. In the preferred embodiment, all of the memory storage is flash EEPROM. It is possible to substitute E2PROM for some or all of the data bits shown. A memory storage 100 is arranged into N blocks of data from zero through N-1. Each of the blocks of data is M Bytes long. In the preferred embodiment, each block is 512 Bytes long to correspond with a sector length in a commercially available hard disk drive.
In addition to the memory data block 102, a flag 104 is directly related to each data block 102. The memory 100 can contain as much memory storage as a user desires. An example of a mass storage device might include 100 MByte of addressable storage.
A non-volatile content addressable memory (CAM) 106 is associated with the memory storage 100. In the preferred embodiment, the CAM 106 is formed of flash memory. The CAM
106 can also be E2PROM. There is one entry in the CAM 106 for every one of the N blocks in the mass storage 100. Each entry includes a number of fields which will be described below. The CAM 106 is also formed of a non-volatile memory because loss of its information would make retrieval of the data files stored in the mass storage 100 impossible.
As described above in the Background of the Invention, conventional computer systems are not configured to track W094l~369 2 I 6 l 3 ~ ~ PCT~S94tO3168 continually changing physical locations of data files.
According to the present invention, each time a data file is changed it is stored into a new physical location in the mass storage. Thus, implementation of the architecture of the present invention requires a mapping of the logical address 308, i.e., the address where the computer system believes the data file is stored to the physical address 408, i.e., the actual location the data file can be found is stored in the mass storage.
The logical address 308 portion of the map 108 and the flags 112, 116 and 118 form part of the CAM 106. It is possible to use other storage means than a CAM to store the address map, such as a look-up table. However, a CAM is the most efficient means known to the inventors. It is not necessary that the physical address 408 portion of the map 108 form part of the CAM. Indeed, the physical address 408 portion of the map 108 can be ordinary flash memory, E2PROM
or even ROM. If ROM is selected for the physical address 408 array of the map 108, a defect in the ROM will prevent the block corresponding to that physical address 408 from ever being addressed. Accordingly, a changeable nonvolatile memory is preferred. Note that any replacement circuit for the CAM should be nonvolatile. Otherwise, loss or removal of power to the system will result in loss of the ability to find the data files in the mass storage.
Assume for example that a user is preparing a word processing document and instructs the computer to save the document. The document will be stored in the mass storage system as shown in Figure 1. The computer system will assign it a logical address 308, for example ~26H. The mass storage system of the present invention will select a physical address 408 of an unused block or blocks in the mass storage 100 for storing the document, e.g. 728H. That map correlating the logical address 308 to the physical WOg4/~36g PCT~S94/03168 ~,~6~
address 408 is stored in the CAM 106. As the data is programmed, the system of the present invention also sets the used/free flag 112 to indicate that this block has been written without being erased. The used/free flag 112 also forms a portion of the CAM 106. One used/free flag 112 is provided for each entry of the CAM 106.
Later, assume the user retrieves the document, makes a -change and again instructs the computer to store the document. To avoid an erase-before-write cycle, the system of the present invention provides means for locating a block having its used/free flag 112 unset (not programmed) which indicates that the associated block is erased. The system then sets the used/free flag for the new block 114 (Figure 2) and then stores the modified document in that new block 114. Next, the system sets the old/new flag 116 of the previous version of the document indicating that this is an old unneeded version of the document. Lastly, the system updates the correlation between the logical address 308 and the actual physical address 408. In this way, the system of the present invention avoids the overhead of an erase cycle which is required in the erase-before-write of conventional systems to store a modified version of a previous document.
The writing to mass storage process outlined above is repeated until the entire mass storage memory 100 has been filled. A full mass storage is indicated by no unset used/free flags 112 in the CAM 106. At that time a multi-sector erase is necessary and those blocks in the memory 100 and their associated CAM 106 entries having an oldlnew flag 116 set are all erased simultaneously. Note that it is not necessary for 100% of the blocks to have a set used/free flag 112 for a multi-sector erase to occur. For example, if a data file requiring three blocks were being written and only two blocks having unset used/free flags 112 were available a multi-sector erase can be run.
W094/~369 2 1 B 1 3 ~ 4 PCT~S94/03168 A simultaneous erase is not needed with prior art implementations because those embodiments utilize an erase-- before-write cycle rather than retaining superseded versions of data files. In such circuits a latch of volatile logic circuits is set to couple the voltage necessary to erase the flash cells in the block. Because of the likely large number of memory blocks in the mass storage 100, if the CAM
106 and mass storage 100 are on the same integrated circuit (chip) coupling the old/new flag 116 to the latches in parallel would typically be very expensive in terms of surface area of the chip and coupling the old/new flags 116 serially to the latches would be expensive in terms of system performance. If the CAM 106 and the mass storage 100 are on separate chips, it is doubtful that either device could have sufficient I/O capability to interconnect the old/new flags 116 to the latches in parallel and thus, the system would suffer from a serial transfer of that information for a multi-sector erase.
Because of these problems it is preferable that no updating of the latches be performed prior to an erase of all blocks having a set old/new flag 116. To avoid this step, a plurality of old/new flag systems 104 are intimately associated with each block in the memory 102 and is programmed by the same sequence of instructions as the old/new flag 116 of the CAM 106.
Figure 4 shows a simplified block diagram of the old/new flag system 104 which includes a non-volatile bit 120 having data which mirrors the old/new flag 116. In addition there is a volatile latch 122 coupled to receive the data in the bit 120 from the latch during an erase cycle. At the time of an erase, the data in each of the bits 120 is simultaneously coupled to each appropriate ones of the latches 122 under control of a load signal coupled to each latch 122 over a load line L. Upon receiving a signal W094/~369 PCT~S94/03168 ~,~6~ o-to perform the eraæe, the latch for every block having its associated bit 120 set then couples the voltage necessary to perform an erase of that block and its associated bit 120.
After the erase is complete and verified, all the latches 122 are individually reset to a predetermined state under control of a reset signal coupled to each latch 122 over a reset line R.
For certain applications of the present invention, especially for low power portable computers, a simultaneous erase of all blocks having their respective old/new flags set may be undesirable. For such applications, the blocks can be segregated into groups of blocks. Each group has a unique control line to load the latches from the nonvolatile bits. In this mode, during an erase cycle, the control lines are sequentially activated and the groups of blocks sequentially erased.
Figure 5 shows algorithm 1 according to the present invention. When the system of the present invention receives an instruction to program data into the mass storage (step 200), then the system attempts to locate a free block (step 202), i.e., a block having an unset ~not programmed) used/free flag. If successful, the system sets the used/free flag for that block and programs the data into that block (step 206).
If on the other hand, the system is unable to locate a block having an unset used/free flag, the system erases the flags (used/free and old/new) and data for all blocks having a set old/new flag (step 204) and then searches for a block having an unset used/free flag (step 202). Such a block has just been formed by step 204. The system then sets the used/free flag for that block and programs the data file into that block (step 206).
If the data file is a modified version of a previously existing file, the system must prevent the superseded w094/~369 2 ~ 6~ PCT~S94/03168 version from being accessed. The system determines whether the data file supersedes a previous data file (step 208).
~ If so, the system sets the old/new flag associated with the superseded block (step 210). If on the other hand, the data file to be stored is a newly created data file, the step of setting the old/new flag (step 210) is skipped because there is no superseded block. Lastly, the map for correlating the logical address 308 to the physical address 408 is updated (step 212).
By following the procedure outlined above, the overhead associated with an erase cycle is avoided for each write to the memory 100 except for periodically. This vastly improves the performance of the overall computer system employing the architecture of the present invention.
In the preferred embodiment of the present invention, the programming of the flash memory follows the procedure commonly understood by those of ordinary skill in the art.
In other words, the program impulses are appropriately applied to the bits to be programmed and then compared to the data being programmed to ensure that proper programming has occurred. In the event that a bit fails to be erased or programmed properly, a defect flag 118 in the CAM 106 is set preventing that block from being used again.
In addition to saving the overhead of the erase cycle all but periodically, utilization of the present invention tends to more evenly distribute the erase cycles amongst certain portions of the blocks of the mass storage. Figure 3 schematically shows the types of information stored in utilizing a mass storage media 150. One portion of the mass storage 150 contains commercial applications software 152 such as word processing, spreadsheet, calendaring, calculators and the like. These portions of the mass storage 150 rarely, if ever, require an erase-reprogram cycle according to the algorithm described above.
W094/~369 PCT~S94/03168 ~6~3 ~ -12-A second section of the mass storage 150 contains user data 154. The user data 154 is frequently altered requiring the information to be reprogrammed into blocks of the free space 156 under the algorithm described above. A third portion of the mass storage 150 contains free space 156 of unprogrammed blocks.
By following the algorithm above, the storage blocks in the portions 154 and 156 of the memory 150 will recycle data files and thus be erased and reprogrammed significantly more often than the commercial applications software portion 152 of the memory 150. Accordingly, the mass storage 150 will wear out more quickly in the user data 154 and the free space 156 sections of the memory requiring earlier replacement than in sections 152 of the mass storage having data files which are rarely changed. As the number of free blocks diminishes providing a smaller number of blocks through which to recycle data files, the r~m~;n;ng blocks become erased more frequently exacerbating the problem.
A second algorithm is provided for leveling erase cycles amongst all the blocks within the entire mass storage device as shown in Figure 6. A counter is provided for each block to count the number of times each block has been erased and reprogrammed. An erase inhibit flag is also provided for each block. Once the erase count has reached the maximum for any block, the erase inhibit flag is set for that block. After that time that block cannot be erased until a clean-out erase is performed. Referring to Figure 3, if only algorithm 1 is used eventually all of the blocks in the user data 154 and the free space 156 portions of the mass storage 150 will reach the maximum count and have their respective erase inhibit flags set. Because of this, a reallocation of the rarely erased data files stored in the memory 152 is made into the memory 154 and/or 156.
In this way, sections of the mass storage which have been W094/~369 2161~ ~ ~ PCT~S94/03168 erased numerous times are programmed with a reallocated data file which is rarely changed thereby allowing all sections of the mass storage to eventually approach parity of erase cycles. Like the multi-sector erase, a clean-out erase can be performed in the event that there is insufficient available storage for a data file presently being performed.
For example, if all but two blocks have their respective erase inhibit flags set, and a three or more block data file is being programmed, a clean-out erase can be performed to provide sufficient storage for the data file.
Once the erase inhibit flag is set for all the blocks, indicating that all the blocks have achieved parity in erase cycles, the erase inhibit and erase count registers are erased and the cycle is repeated. The selection of the maximum count depends upon the system requirements. As the value for the maximum count increases, the disparity between erase count cycles of various blocks can also increase.
However, because data is shifted as a result of achieving maximum erase count this process of smoothing cycles throughout the mass storage of itself introduces additional erase cycles because a block of information is transferred from a physical block having few erases to a block having the maximum number of erases. Accordingly, though low maximum count values reduce the disparity between erase cycles amongst the blocks it also increases the number of erase cycles to which the blocks are subjected.
Accordingly, individual users may select an erase count depending upon the system needs.
In the preferred embodiment, algorithm 2 is merged with algorithm l as shown in Figure 7. An instruction is provided by the computer system to write a data file to the mass storage (step 230) which starts the combined algorithm l and algorithm 2 sequence. It is first determined whether the mass storage is full (step 232). If the mass storage is W094/~36g PCT~S94/03168 ~5~3~4 not full, i.e., it has a block with its used/free flag unset, the algorithm continues and stores the data file into such a block (step 234).
If on the other hand, it is determined that there are no free blocks, then it is next determined whether there are any blocks which have both the old/new flag set AND the erase inhibit flag unset (step 236). If there are no blocks which have both the old/new flag set AND the erase inhibit flag unset (step 236), the system of the present invention erases the data file, used/free flag and old/new flag in each block having its old/new flag set, and erases the counter and erase inhibit flag for every block (step 238).
Step 238 is also performed in the event there are insufficient blocks remaining to store a pending data file.
The algorithm then returns to block (step 232) to detenmine whether the disk is full.
If the system can find a block having both the old/new flag set AND the erase inhibit flag unset (step 236), then the system executes an erase procedure and erases the data 2~ file, used/free flag and old/new flag in each block having its old/new flag set. The counter is incremented and the erase inhibit flag for such blocks is not disturbed.
It is then detenmined whether any block having its used/free flag unset has its counter at the maximum count ~step 242). If not, then the system of the present invention returns to decision step 232 and investigates again whether there is any block having its used/free flag unset (step 232).
On the other hand, if there is a block having its erase count at the maximum value, a data file is copied from another block having the then least count value (step 244) into the location having COUNT = COUNT~. The erase inhibit flag is then set (step 244). Note that a data file will not be copied from a block having its erase count at one less ~941~369 2 I fi 13 ~ ~ PCT~S94103168 than the maximum value, COUNT~-l. Making such a reallocation from a source block having COUNT~X-1 to a destination block having COUNT~X results in having both blocks at COUNT~ and no net gain. Further, the block previously having its erase count at COUNT~-l is erased to no advantage, thus the erase cycle for that block would be wasted.
The old/new flag from the source block is then set (step 246) so that it can be erased during the next execution of an erase step 240. In that way the source block can be used for storage until its erase count reaches maximum and its erase inhibit flag is set. The algorithm then returns to step 242 to determine whether there are now any blocks having an unset used/free flag with an erase count less than COUNT~. It will be understood that each time a data file is programmed or moved according to the algorithm of Figure 7 that the map in the CAM which correlates the logical address 308 to physical address 408 is updated so that the computer system can always access the data files.
The efficiency of these algorithms has been tested by simulation. In the simulation it was assumed that the mass storage was 50% filled with data files that are not changed, 30% with data files that are routinely changed and 20%
empty. Of the 30% of the data files that are routinely changed, ~ are rewritten 70% of the time, ~ are rewritten 25% of the time and ~ are rewritten 5% of the time. The simulation showed that the algorithm l improves the number of cycles until any block has reached failure by between six and seven times and algorithm 2 by approximately two times over the improvement gained using algorithm l alone.
Depending upon the design criterion of a target system, it is possible to utilize either algorithm l, algorithm 2 or the preferred merged algorithm. Algorithm l and the merged W094~3369 PCT~S94J03168 2~C~3~
algorithm have been described above.
In the preferred embodiment, a bit is programmed into the counter for each erase cycle rather than using binary counting. Thus, an eight bit counter register would only ~e able to count to eight. This avoids having to erase the counter and then reprogramming it with an incremented value as would be necessary for binary counting. This is preferred because it avoids having to temporarily store the count value for all of the blocks being erased. By programming a bit for each, the counter registers need not be erased until all the blocks reach maximum count and there is a general erase.
Because the mass storage apparatus of the present invention can ac~ommodate large data storage, it is likely that many blocks will be flagged for a clean-out erase.
Either a temporary volatile storage would be necessary for each block to store the previous count value prior to incrementing and reprogramming or the erase and updating of the counters would have to be done one after the other. One solution requires integrated circuit surface area and the other degrades performance. Note however, that if binary counting is desired the erase counter can be erased each time the block is erased and immediately reprogrammed.
Because this will happen only during the periodic erase cycle described relative to the first algorithm some system designers may find this acceptable.
The read algorithm according to the present invention is shown in Figure 8. A read instruction is received by the mass storage apparatus of the present invention from the computer system (step 270). Concurrent with receiving the read instruction, the system also receives the logical address 308 of the data file needed by the computer system (step 271). The apparatus of the present invention concatenates all the appropriate flags to the logical ~v094l23369 ~ 4 ~ PCT~S94/03168 address 308 including having a set used/free flag, and unset new/old and defect flags (step 272). If a match is found in the CAM (step 273), the data file is read (step 275) otherwise a signal is returned to the computer system that the data file was not found (step 274).
The present invention is described relative to a preferred embodiment. Modifications or improvements which become apparent to one of ordinary skill in the art after reading this disclosure are deemed within the spirit and scope of this invention.
Claims (55)
What is claimed is:
1. A non-volatile semiconductor mass storage device comprising:
a. a plurality of non-volatile storage blocks, wherein each block is selectively programmable and erasable wherein only blocks containing no data are programmed;
b. means for determining whether any unprogrammed blocks remain;
c. means for replacing superseded data with updated data including nonvolatile flag means which are set for temporarily ignoring blocks having superseded data and programming means for storing updated data into a block containing no data; and d. means for periodically erasing all blocks having flag means which are set, whereby an erase cycle is not needed each time updated data replaces superseded data.
a. a plurality of non-volatile storage blocks, wherein each block is selectively programmable and erasable wherein only blocks containing no data are programmed;
b. means for determining whether any unprogrammed blocks remain;
c. means for replacing superseded data with updated data including nonvolatile flag means which are set for temporarily ignoring blocks having superseded data and programming means for storing updated data into a block containing no data; and d. means for periodically erasing all blocks having flag means which are set, whereby an erase cycle is not needed each time updated data replaces superseded data.
2. The device according to claim 1 further comprising means for correlating a logical address assigned the superseded data to a physical address of updated data in the device.
3. The device according to claim 2 wherein the flag and the logical address are formed of nonvolatile content addressable memory.
4. The device according to claim 1 wherein the means for periodically erasing simultaneously erases all blocks having flag means which are set.
5. The device according to claim 4 wherein the means for periodically erasing comprises a plurality of nonvolatile single bit storage cells, one cell for and coupled to each block, each cell for storing an appropriate second flag and a plurality of volatile latches, one for each cell, coupled to receive a logic state of the cell during an erase cycle.
6. The device according to claim 5 wherein all latches simultaneously receive the logic state.
7. The device according to claim 3 further comprising means for ensuring no block is subjected to more than a predetermined number of erase cycles than any other block.
8. The device according to claim 7 wherein the means for ensuring comprises a counter for each block for counting each erase cycle to which that block has been subjected.
9. The device according to claim 8 further comprising means for setting a maximum count value coupled to the block, and an erase inhibit flag coupled to the counter having a set condition and an unset condition for each block for preventing further erases to a block having its erase inhibit flag in the set condition.
10. The device according to claim 9 wherein the counter includes a plurality of bits programmed by binary counting.
11. The device according to claim 9 wherein the counter includes a plurality of bits programmed by sequentially programming each bit, one at a time, wherein each programmed bit represents a count of one.
12. The device according to claim 9 wherein the counter and the erase inhibit flag are formed in the content addressable memory.
13. The device according to claim 9 further comprising a reset means for erasing all counters and all flags for every block at the maximum count value once insufficient blocks remain to store a pending data file.
14. The device according to claim 13 further comprising means for reading the mass storage comprising:
a. means for receiving the logical address of a data file to be read;
b. means for selecting an appropriate physical address which correlates to the logical address of the data file to be read; and c. means for accessing the data file to be read from the appropriate physical address.
a. means for receiving the logical address of a data file to be read;
b. means for selecting an appropriate physical address which correlates to the logical address of the data file to be read; and c. means for accessing the data file to be read from the appropriate physical address.
15. The device according to claim 14 wherein the means for selecting an appropriate physical address comprises coupling the logical address to the content addressable memory.
16. A non-volatile semiconductor mass storage device comprising:
a. a plurality of non-volatile storage blocks, wherein each block is selectively programmable and erasable;
b. a first indicating element to provide a first indicia whether each block has been programmed with a data file;
c. a second indicating element to provide a second indicia whether the data file is superseded; and d. a selecting element to program a new data file into an empty block.
a. a plurality of non-volatile storage blocks, wherein each block is selectively programmable and erasable;
b. a first indicating element to provide a first indicia whether each block has been programmed with a data file;
c. a second indicating element to provide a second indicia whether the data file is superseded; and d. a selecting element to program a new data file into an empty block.
17. The device according to claim 16 further comprising a device to correlate a logical address assigned the superseded data to a physical address of updated data in the device.
18. The device according to claim 17 wherein the first indicating element, the second indicating element and the logical address are formed of nonvolatile content addressable memory.
19. The device according to claim 16 further comprising an erase element to periodically simultaneously erase all blocks having a superseded data file.
20. The device according to claim 19 wherein the erase element include a plurality of nonvolatile single bit storage cells, one cell for and coupled to each block, each cell for storing an appropriate second flag and a plurality of volatile latches, one for each cell, coupled to receive a logic state of the cell during an erase cycle.
21. The device according to claim 20 wherein all latches simultaneously receive the logic state.
22. The device according to claim 18 further comprising a first controller to ensure that no block is subjected to more than a predetermined number of erase cycles than any other block.
23. The device according to claim 22 wherein the first controller includes a counter for each block for counting each erase cycle to which that block has been subjected.
24. The device according to claim 23 wherein the counter includes a plurality of bits programmed by binary counting.
25. The device according to claim 23 wherein the counter includes a plurality of bits programmed by sequentially programming each bit, one at a time, wherein each programmed bit represents a count of one.
26. The device according to claim 23 further comprising a second controller to set a maximum count value coupled to the block, and an erase inhibit flag coupled to the counter having a set condition and an unset condition for each block for preventing further erases to a block having its erase inhibit flag in the set condition.
27. The device according to claim 26 wherein the counter and the erase inhibit flag are formed in the content addressable memory.
28. The device according to claim 26 further comprising a reset element to erase all counters, first indicating element, second element and all flags for every block at the maximum count value once insufficient blocks remain to store a pending data file.
29. The device according to claim 28 further comprising a reading element for the mass storage comprising:
a. a first circuit to receive the logical address of a data file to be read;
b. a second circuit to select an appropriate physical address which correlates to the logical address of the data file to be read; and c. a third circuit to access the data file to be read from the appropriate physical address.
a. a first circuit to receive the logical address of a data file to be read;
b. a second circuit to select an appropriate physical address which correlates to the logical address of the data file to be read; and c. a third circuit to access the data file to be read from the appropriate physical address.
30. The device according to claim 29 wherein the second circuit couples the logical address to the content addressable memory.
31. A non-volatile semiconductor mass storage device comprising:
a. a plurality of non-volatile storage blocks, wherein each block is selectively programmable to store data and is selectively erasable;
b. a plurality of first flags, one first flag for each block, each first flag having a first logic state to indicate that a block has not been programmed with data and a second logic state to indicate that the block has been programmed with data;
c. a selecting element to identify an empty block having a first flag in the first logic state to receive new data;
d. a plurality of second flags that can only be changed in a block having its first flag in the second logic state, one second flag for each block, each second flag having a third logic state to indicate that the data in a block is valid and a fourth logic state to indicate that the data in the block has been superseded; and e. a content addressable memory for correlating a logical address assigned the superseded data to a physical address of updated data in the device.
a. a plurality of non-volatile storage blocks, wherein each block is selectively programmable to store data and is selectively erasable;
b. a plurality of first flags, one first flag for each block, each first flag having a first logic state to indicate that a block has not been programmed with data and a second logic state to indicate that the block has been programmed with data;
c. a selecting element to identify an empty block having a first flag in the first logic state to receive new data;
d. a plurality of second flags that can only be changed in a block having its first flag in the second logic state, one second flag for each block, each second flag having a third logic state to indicate that the data in a block is valid and a fourth logic state to indicate that the data in the block has been superseded; and e. a content addressable memory for correlating a logical address assigned the superseded data to a physical address of updated data in the device.
32. The device according to claim 31 further comprising means for correlating a logical address assigned the superseded data to a physical address of updated data in the device.
33. The device according to claim 31 further comprising means for simultaneously erasing each block having a flag in the fourth logic state.
34. The device according to claim 33 wherein the means for simultaneously erasing comprises a plurality of nonvolatile single bit storage cells, one cell for and coupled to each block, each cell for storing an appropriate second flag and a plurality of volatile latches, one for each cell, coupled to receive a logic state of the cell during an erase cycle.
35. The device according to claim 34 wherein all latches simultaneously receive the logic state.
36. The device according to claim 35 wherein the storage blocks store data in flash memory cells.
37. The device according to claim 36 wherein the flags are stored in flash memory cells.
38. The device according to claim 37 wherein the means for correlating are stored in flash memory cells.
39. The device according to claim 35 wherein the storage blocks store data in E2PROM cells.
40. The device according to claim 39 wherein the flags are stored in E2PROM cells.
41. The device according to claim 40 wherein the means for correlating are stored in E2PROM cells.
42. A non-volatile semiconductor mass storage device comprising:
a. a plurality of non-volatile storage blocks, wherein each block is selectively programmable to store data and is selectively erasable;
b. a plurality of first flags, one flag for each block;
c. means for setting a corresponding first flag to indicate that a corresponding block has been programmed with data;
d. means for selecting a block having an unset first flag for storing a new data;
e. means for programming the new data into the block having an unset first flag;
f. a plurality of second flags, one flag for each block;
g. means for setting a corresponding second flag for a programmed block to indicate that data in the programmed block has been superseded;
h. a content addressable memory having an entry for each block for correlating a logical address assigned the superseded data to a physical address of updated data in the device; and i. means for erasing each block having a set second flag once too few blocks remain for storing a next new data file, including each appropriate content addressable memory entry, first flag and second flag corresponding to each such block.
a. a plurality of non-volatile storage blocks, wherein each block is selectively programmable to store data and is selectively erasable;
b. a plurality of first flags, one flag for each block;
c. means for setting a corresponding first flag to indicate that a corresponding block has been programmed with data;
d. means for selecting a block having an unset first flag for storing a new data;
e. means for programming the new data into the block having an unset first flag;
f. a plurality of second flags, one flag for each block;
g. means for setting a corresponding second flag for a programmed block to indicate that data in the programmed block has been superseded;
h. a content addressable memory having an entry for each block for correlating a logical address assigned the superseded data to a physical address of updated data in the device; and i. means for erasing each block having a set second flag once too few blocks remain for storing a next new data file, including each appropriate content addressable memory entry, first flag and second flag corresponding to each such block.
43. A method of storing data into a non-volatile semiconductor mass storage device having a plurality of non-volatile storage blocks, wherein each block is selectively programmable and erasable wherein only blocks containing no data are programmed, the method comprising the steps of:
a. determining whether any unprogrammed blocks remain;
b. replacing superseded data with updated data including flag means which are set for temporarily ignoring blocks having superseded data and programming means for storing updated data into a block containing no data without erasing the superseded data; and c. periodically erasing all blocks having flag means which are set.
a. determining whether any unprogrammed blocks remain;
b. replacing superseded data with updated data including flag means which are set for temporarily ignoring blocks having superseded data and programming means for storing updated data into a block containing no data without erasing the superseded data; and c. periodically erasing all blocks having flag means which are set.
44. The method according to claim 43 further comprising correlating a logical address assigned the superseded data to a physical address of updated data in the device.
45. The method according to claim 44 wherein the step of periodically erasing simultaneously erases all blocks having flag means which are set.
46. The method according to claim 45 wherein the step of periodically erasing includes the step of simultaneously loading volatile latches from the flag means.
47. The method according to claim 46 further comprising the step of ensuring no block is subjected to more than a predetermined number of erase cycles than any other block.
48. The method according to claim 47 further comprising reading the mass storage comprising the steps of:
a. receiving the logical address of a data file to be read;
b. selecting an appropriate physical address which correlates to the logical address of the data file to be read; and c. accessing the data file to be read from the appropriate physical address.
a. receiving the logical address of a data file to be read;
b. selecting an appropriate physical address which correlates to the logical address of the data file to be read; and c. accessing the data file to be read from the appropriate physical address.
49. A method of storing data into a non-volatile semiconductor mass storage device having a plurality of non-volatile storage blocks, wherein each block is selectively programmable to store data and is selectively erasable, the method comprising:
a. determining whether a block has been programmed with data;
b. providing a first indicia for each block which has been programmed with data;
c. programming new data into a block which has no first indicia; and d. if the new data supersedes old data stored in a block, providing a second indicia to the block storing the old data.
a. determining whether a block has been programmed with data;
b. providing a first indicia for each block which has been programmed with data;
c. programming new data into a block which has no first indicia; and d. if the new data supersedes old data stored in a block, providing a second indicia to the block storing the old data.
50. A method of storing data into a non-volatile semiconductor mass storage device having a plurality of non-volatile storage blocks, wherein each block is selectively programmable to store data and is selectively erasable, the method comprising:
a. setting a corresponding one of a plurality of first flags, one flag for each block, to indicate that a corresponding block has been programmed with data;
b. selecting a block having an unset first flag for storing a new data;
c. programming the new data into the block having an unset first flag;
d. setting a corresponding one of a plurality of second flags, one flag for each block, for a programmed block to indicate that data in the programmed block has been superseded; and e. erasing each block having a set second flag once too few blocks remain for storing a next new data, including the first flag and the second flag corresponding to each such block.
a. setting a corresponding one of a plurality of first flags, one flag for each block, to indicate that a corresponding block has been programmed with data;
b. selecting a block having an unset first flag for storing a new data;
c. programming the new data into the block having an unset first flag;
d. setting a corresponding one of a plurality of second flags, one flag for each block, for a programmed block to indicate that data in the programmed block has been superseded; and e. erasing each block having a set second flag once too few blocks remain for storing a next new data, including the first flag and the second flag corresponding to each such block.
51. A nonvolatile memory integrated circuit device comprising:
a. a plurality of storage cells which are segmented into a plurality of memory blocks of a predetermined size;
b. a plurality of latches, one latch coupled to each block for coupling an erase voltage to the block; and c. a control element to simultaneously set all latches for erasing a predetermined set of the blocks.
a. a plurality of storage cells which are segmented into a plurality of memory blocks of a predetermined size;
b. a plurality of latches, one latch coupled to each block for coupling an erase voltage to the block; and c. a control element to simultaneously set all latches for erasing a predetermined set of the blocks.
52. The memory according to claim 51 further comprising a plurality of nonvolatile memory bits, one memory bit for each block for storing a data bit representative of the predetermined set, each memory bit coupled to one of the latches wherein during an erase cycle a control signal couples each data bit into each appropriate latch.
53. The memory according to claim 52 wherein the memory bit for each latch in a set condition is erased simultaneously with its associated block during the erase cycle.
54. The memory according to claim 53 wherein each memory bit is a flash memory bit.
55. The memory according to claim 53 wherein each memory bit is an E2PROM memory bit.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/037,893 | 1993-03-26 | ||
US08/037,893 US5479638A (en) | 1993-03-26 | 1993-03-26 | Flash memory mass storage architecture incorporation wear leveling technique |
Publications (1)
Publication Number | Publication Date |
---|---|
CA2161344A1 true CA2161344A1 (en) | 1994-10-13 |
Family
ID=21896923
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CA002161344A Abandoned CA2161344A1 (en) | 1993-03-26 | 1994-03-23 | Flash memory mass storage architecture |
Country Status (6)
Country | Link |
---|---|
US (1) | US5479638A (en) |
EP (1) | EP0691008B1 (en) |
AT (1) | ATE228674T1 (en) |
CA (1) | CA2161344A1 (en) |
DE (1) | DE69431795T2 (en) |
WO (1) | WO1994023369A1 (en) |
Families Citing this family (249)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05233426A (en) * | 1992-02-20 | 1993-09-10 | Fujitsu Ltd | Flash memory using method |
JP3464836B2 (en) * | 1995-01-19 | 2003-11-10 | 富士通株式会社 | Memory management device for storage device |
US5778411A (en) * | 1995-05-16 | 1998-07-07 | Symbios, Inc. | Method for virtual to physical mapping in a mapped compressed virtual storage subsystem |
US6081878A (en) * | 1997-03-31 | 2000-06-27 | Lexar Media, Inc. | Increasing the memory performance of flash memory devices by writing sectors simultaneously to multiple flash memory devices |
US6978342B1 (en) | 1995-07-31 | 2005-12-20 | Lexar Media, Inc. | Moving sectors within a block of information in a flash memory mass storage architecture |
US5907856A (en) * | 1995-07-31 | 1999-05-25 | Lexar Media, Inc. | Moving sectors within a block of information in a flash memory mass storage architecture |
US5930815A (en) * | 1995-07-31 | 1999-07-27 | Lexar Media, Inc. | Moving sequential sectors within a block of information in a flash memory mass storage architecture |
US5845313A (en) | 1995-07-31 | 1998-12-01 | Lexar | Direct logical block addressing flash memory mass storage architecture |
US6757800B1 (en) | 1995-07-31 | 2004-06-29 | Lexar Media, Inc. | Increasing the memory performance of flash memory devices by writing sectors simultaneously to multiple flash memory devices |
US6801979B1 (en) | 1995-07-31 | 2004-10-05 | Lexar Media, Inc. | Method and apparatus for memory control circuit |
US6728851B1 (en) | 1995-07-31 | 2004-04-27 | Lexar Media, Inc. | Increasing the memory performance of flash memory devices by writing sectors simultaneously to multiple flash memory devices |
US8171203B2 (en) | 1995-07-31 | 2012-05-01 | Micron Technology, Inc. | Faster write operations to nonvolatile memory using FSInfo sector manipulation |
US5838614A (en) | 1995-07-31 | 1998-11-17 | Lexar Microsystems, Inc. | Identification and verification of a sector within a block of mass storage flash memory |
US5835935A (en) * | 1995-09-13 | 1998-11-10 | Lexar Media, Inc. | Method of and architecture for controlling system data with automatic wear leveling in a semiconductor non-volatile mass storage memory |
US6125435A (en) * | 1995-09-13 | 2000-09-26 | Lexar Media, Inc. | Alignment of cluster address to block addresses within a semiconductor non-volatile mass storage memory |
GB2291991A (en) * | 1995-09-27 | 1996-02-07 | Memory Corp Plc | Disk drive emulation with a block-erasable memory |
US5696929A (en) * | 1995-10-03 | 1997-12-09 | Intel Corporation | Flash EEPROM main memory in a computer system |
US6009537A (en) * | 1996-03-29 | 1999-12-28 | Kabushiki Kaisha Toshiba | Disk wear prevention by relocating data in response to a head slide count |
US5787484A (en) * | 1996-08-08 | 1998-07-28 | Micron Technology, Inc. | System and method which compares data preread from memory cells to data to be written to the cells |
GB2317720A (en) * | 1996-09-30 | 1998-04-01 | Nokia Mobile Phones Ltd | Managing Flash memory |
US5754567A (en) | 1996-10-15 | 1998-05-19 | Micron Quantum Devices, Inc. | Write reduction in flash memory systems through ECC usage |
US5928370A (en) * | 1997-02-05 | 1999-07-27 | Lexar Media, Inc. | Method and apparatus for verifying erasure of memory blocks within a non-volatile memory structure |
US6034897A (en) * | 1999-04-01 | 2000-03-07 | Lexar Media, Inc. | Space management for managing high capacity nonvolatile memory |
US6411546B1 (en) | 1997-03-31 | 2002-06-25 | Lexar Media, Inc. | Nonvolatile memory using flexible erasing methods and method and system for using same |
US6122195A (en) * | 1997-03-31 | 2000-09-19 | Lexar Media, Inc. | Method and apparatus for decreasing block write operation times performed on nonvolatile memory |
KR100251636B1 (en) * | 1997-04-10 | 2000-05-01 | 윤종용 | Memory device for connecting in a accordance with scsi |
JP3718578B2 (en) * | 1997-06-25 | 2005-11-24 | ソニー株式会社 | Memory management method and memory management device |
US6000006A (en) * | 1997-08-25 | 1999-12-07 | Bit Microsystems, Inc. | Unified re-map and cache-index table with dual write-counters for wear-leveling of non-volatile flash RAM mass storage |
US5956743A (en) * | 1997-08-25 | 1999-09-21 | Bit Microsystems, Inc. | Transparent management at host interface of flash-memory overhead-bytes using flash-specific DMA having programmable processor-interrupt of high-level operations |
US5822251A (en) * | 1997-08-25 | 1998-10-13 | Bit Microsystems, Inc. | Expandable flash-memory mass-storage using shared buddy lines and intermediate flash-bus between device-specific buffers and flash-intelligent DMA controllers |
US5937425A (en) * | 1997-10-16 | 1999-08-10 | M-Systems Flash Disk Pioneers Ltd. | Flash file system optimized for page-mode flash technologies |
US5848026A (en) * | 1997-12-08 | 1998-12-08 | Atmel Corporation | Integrated circuit with flag register for block selection of nonvolatile cells for bulk operations |
US6076137A (en) | 1997-12-11 | 2000-06-13 | Lexar Media, Inc. | Method and apparatus for storing location identification information within non-volatile memory devices |
GB9801373D0 (en) | 1998-01-22 | 1998-03-18 | Memory Corp Plc | Memory system |
GB2339044B (en) | 1998-03-02 | 2003-06-04 | Lexar Media Inc | Flash memory card with enhanced operating mode detection and user-friendly interfacing system |
US6040997A (en) * | 1998-03-25 | 2000-03-21 | Lexar Media, Inc. | Flash memory leveling architecture having no external latch |
JP2000122935A (en) * | 1998-10-20 | 2000-04-28 | Sanyo Electric Co Ltd | Address converting device for nonvolatile memory |
US6901457B1 (en) | 1998-11-04 | 2005-05-31 | Sandisk Corporation | Multiple mode communications system |
AU1729100A (en) | 1998-11-17 | 2000-06-05 | Lexar Media, Inc. | Method and apparatus for memory control circuit |
US6624761B2 (en) | 1998-12-11 | 2003-09-23 | Realtime Data, Llc | Content independent data compression method and system |
US6819271B2 (en) | 1999-01-29 | 2004-11-16 | Quickshift, Inc. | Parallel compression and decompression system and method having multiple parallel compression and decompression engines |
US7538694B2 (en) * | 1999-01-29 | 2009-05-26 | Mossman Holdings Llc | Network device with improved storage density and access speed using compression techniques |
US6145069A (en) * | 1999-01-29 | 2000-11-07 | Interactive Silicon, Inc. | Parallel decompression and compression system and method for improving storage density and access speed for non-volatile memory and embedded memory devices |
US6885319B2 (en) * | 1999-01-29 | 2005-04-26 | Quickshift, Inc. | System and method for generating optimally compressed data from a plurality of data compression/decompression engines implementing different data compression algorithms |
US6601104B1 (en) | 1999-03-11 | 2003-07-29 | Realtime Data Llc | System and methods for accelerated data storage and retrieval |
US6141249A (en) * | 1999-04-01 | 2000-10-31 | Lexar Media, Inc. | Organization of blocks within a nonvolatile memory unit to effectively decrease sector write operation time |
EP1228510B1 (en) | 1999-04-01 | 2006-09-20 | Lexar Media, Inc. | Space management for managing high capacity nonvolatile memory |
KR100330164B1 (en) * | 1999-04-27 | 2002-03-28 | 윤종용 | A method for simultaneously programming plural flash memories having invalid blocks |
US6591327B1 (en) * | 1999-06-22 | 2003-07-08 | Silicon Storage Technology, Inc. | Flash memory with alterable erase sector size |
US7872871B2 (en) | 2000-01-06 | 2011-01-18 | Super Talent Electronics, Inc. | Molding methods to manufacture single-chip chip-on-board USB device |
US8625270B2 (en) | 1999-08-04 | 2014-01-07 | Super Talent Technology, Corp. | USB flash drive with deploying and retracting functionalities using retractable cover/cap |
US7830666B2 (en) | 2000-01-06 | 2010-11-09 | Super Talent Electronics, Inc. | Manufacturing process for single-chip MMC/SD flash memory device with molded asymmetric circuit board |
US8102662B2 (en) | 2007-07-05 | 2012-01-24 | Super Talent Electronics, Inc. | USB package with bistable sliding mechanism |
US7466556B2 (en) * | 1999-08-04 | 2008-12-16 | Super Talent Electronics, Inc. | Single chip USB packages with swivel cover |
US7535719B2 (en) * | 1999-08-04 | 2009-05-19 | Super Talent Electronics, Inc. | Single chip USB packages with contact-pins cover |
US7447037B2 (en) * | 1999-08-04 | 2008-11-04 | Super Talent Electronics, Inc. | Single chip USB packages by various assembly methods |
US7318117B2 (en) | 2004-02-26 | 2008-01-08 | Super Talent Electronics, Inc. | Managing flash memory including recycling obsolete sectors |
US7702831B2 (en) * | 2000-01-06 | 2010-04-20 | Super Talent Electronics, Inc. | Flash memory controller for electronic data flash card |
US8141240B2 (en) | 1999-08-04 | 2012-03-27 | Super Talent Electronics, Inc. | Manufacturing method for micro-SD flash memory card |
US7076623B1 (en) * | 1999-10-18 | 2006-07-11 | Matsushita Electric Industrial Co., Ltd. | Information update count managing method, information update count managing apparatus, contents usage count managing method, and content usage count storing apparatus |
US6738884B1 (en) | 1999-12-14 | 2004-05-18 | Genesis Microchip Inc. | Method and apparatus for processing data with semaphores |
US6920543B1 (en) * | 1999-12-14 | 2005-07-19 | Genesis Microchip, Inc. | Method and apparatus for performing distributed processing of program code |
US6775757B1 (en) | 1999-12-14 | 2004-08-10 | Genesis Microchip Inc. | Multi-component processor |
US7702984B1 (en) | 2000-01-06 | 2010-04-20 | Super Talent Electronics, Inc. | High volume testing for USB electronic data flash cards |
US20060161725A1 (en) * | 2005-01-20 | 2006-07-20 | Lee Charles C | Multiple function flash memory system |
US20080286990A1 (en) * | 2003-12-02 | 2008-11-20 | Super Talent Electronics, Inc. | Direct Package Mold Process For Single Chip SD Flash Cards |
US20010047473A1 (en) | 2000-02-03 | 2001-11-29 | Realtime Data, Llc | Systems and methods for computer initialization |
US7102671B1 (en) | 2000-02-08 | 2006-09-05 | Lexar Media, Inc. | Enhanced compact flash memory card |
US6426893B1 (en) | 2000-02-17 | 2002-07-30 | Sandisk Corporation | Flash eeprom system with simultaneous multiple data sector programming and storage of physical block characteristics in other designated blocks |
US6567307B1 (en) | 2000-07-21 | 2003-05-20 | Lexar Media, Inc. | Block management for mass storage |
US7167944B1 (en) | 2000-07-21 | 2007-01-23 | Lexar Media, Inc. | Block management for mass storage |
US7155559B1 (en) | 2000-08-25 | 2006-12-26 | Lexar Media, Inc. | Flash memory architecture with separate storage of overhead and user data |
US6772274B1 (en) | 2000-09-13 | 2004-08-03 | Lexar Media, Inc. | Flash memory system and method implementing LBA to PBA correlation within flash memory array |
US6473845B1 (en) * | 2000-09-28 | 2002-10-29 | Hewlett-Packard Company | System and method for dynamically updating memory address mappings |
US9143546B2 (en) | 2000-10-03 | 2015-09-22 | Realtime Data Llc | System and method for data feed acceleration and encryption |
US8692695B2 (en) | 2000-10-03 | 2014-04-08 | Realtime Data, Llc | Methods for encoding and decoding data |
US6763424B2 (en) * | 2001-01-19 | 2004-07-13 | Sandisk Corporation | Partial block data programming and reading operations in a non-volatile memory |
US7386046B2 (en) | 2001-02-13 | 2008-06-10 | Realtime Data Llc | Bandwidth sensitive data compression and decompression |
JP2002351685A (en) * | 2001-05-22 | 2002-12-06 | Sankyo Seiki Mfg Co Ltd | Data updating method and controller for nonvolatile memory |
US6732221B2 (en) | 2001-06-01 | 2004-05-04 | M-Systems Flash Disk Pioneers Ltd | Wear leveling of static areas in flash memory |
KR100389867B1 (en) | 2001-06-04 | 2003-07-04 | 삼성전자주식회사 | Flash memory management method |
GB0123417D0 (en) | 2001-09-28 | 2001-11-21 | Memquest Ltd | Improved data processing |
GB0123410D0 (en) | 2001-09-28 | 2001-11-21 | Memquest Ltd | Memory system for data storage and retrieval |
GB0123416D0 (en) * | 2001-09-28 | 2001-11-21 | Memquest Ltd | Non-volatile memory control |
GB0123419D0 (en) | 2001-09-28 | 2001-11-21 | Memquest Ltd | Data handling system |
GB0123412D0 (en) | 2001-09-28 | 2001-11-21 | Memquest Ltd | Memory system sectors |
GB0123421D0 (en) | 2001-09-28 | 2001-11-21 | Memquest Ltd | Power management system |
GB0123415D0 (en) | 2001-09-28 | 2001-11-21 | Memquest Ltd | Method of writing data to non-volatile memory |
TWI240861B (en) * | 2002-01-11 | 2005-10-01 | Integrated Circuit Solution In | Data access method and architecture of flash memory |
US6957295B1 (en) | 2002-01-18 | 2005-10-18 | Lexar Media, Inc. | File management of one-time-programmable nonvolatile memory devices |
US6950918B1 (en) | 2002-01-18 | 2005-09-27 | Lexar Media, Inc. | File management of one-time-programmable nonvolatile memory devices |
US7231643B1 (en) | 2002-02-22 | 2007-06-12 | Lexar Media, Inc. | Image rescue system including direct communication between an application program and a device driver |
AU2003211154A1 (en) * | 2002-02-22 | 2003-09-09 | Lexar Media, Inc. | Removable memory media with integral indicator light |
KR100484147B1 (en) * | 2002-07-26 | 2005-04-18 | 삼성전자주식회사 | Flash memory management method |
KR20050103448A (en) * | 2003-02-04 | 2005-10-31 | 마츠시타 덴끼 산교 가부시키가이샤 | Semiconductor memory card and computer readable program |
JP4338989B2 (en) * | 2003-02-20 | 2009-10-07 | パナソニック株式会社 | Memory device |
US6973519B1 (en) | 2003-06-03 | 2005-12-06 | Lexar Media, Inc. | Card identification compatibility |
TWI260497B (en) * | 2003-06-13 | 2006-08-21 | Hon Hai Prec Ind Co Ltd | System and method of flash file |
US8998620B2 (en) * | 2003-12-02 | 2015-04-07 | Super Talent Technology, Corp. | Molding method for COB-EUSB devices and metal housing package |
US7872873B2 (en) | 2003-12-02 | 2011-01-18 | Super Talent Electronics, Inc. | Extended COB-USB with dual-personality contacts |
US8102657B2 (en) | 2003-12-02 | 2012-01-24 | Super Talent Electronics, Inc. | Single shot molding method for COB USB/EUSB devices with contact pad ribs |
US7440286B2 (en) * | 2005-04-21 | 2008-10-21 | Super Talent Electronics, Inc. | Extended USB dual-personality card reader |
WO2005059854A2 (en) | 2003-12-17 | 2005-06-30 | Lexar Media, Inc. | Electronic equipment point-of-sale activation to avoid theft |
US7480760B2 (en) * | 2003-12-17 | 2009-01-20 | Wegener Communications, Inc. | Rotational use of memory to minimize write cycles |
US7631138B2 (en) * | 2003-12-30 | 2009-12-08 | Sandisk Corporation | Adaptive mode switching of flash memory address mapping based on host usage characteristics |
US8504798B2 (en) * | 2003-12-30 | 2013-08-06 | Sandisk Technologies Inc. | Management of non-volatile memory systems having large erase blocks |
US7869219B2 (en) | 2004-01-20 | 2011-01-11 | Super Talent Electronics, Inc. | Flash drive with spring-loaded retractable connector |
US7725628B1 (en) | 2004-04-20 | 2010-05-25 | Lexar Media, Inc. | Direct secondary device interface by a host |
US7370166B1 (en) | 2004-04-30 | 2008-05-06 | Lexar Media, Inc. | Secure portable storage device |
US7594063B1 (en) | 2004-08-27 | 2009-09-22 | Lexar Media, Inc. | Storage capacity status |
US7464306B1 (en) | 2004-08-27 | 2008-12-09 | Lexar Media, Inc. | Status of overall health of nonvolatile memory |
US7284085B2 (en) * | 2004-11-01 | 2007-10-16 | Emulex Design & Manufacturing Corporation | Managing configuration data in a flash configuration space in flash memory within a host interface port |
US7644191B2 (en) * | 2004-11-12 | 2010-01-05 | Emulex Design & Manufacturing Corporation | Legacy-compatible extended command input-output control block |
US7441067B2 (en) * | 2004-11-15 | 2008-10-21 | Sandisk Corporation | Cyclic flash memory wear leveling |
US7721033B2 (en) * | 2004-12-03 | 2010-05-18 | Emulex Design & Manufacturing Corporation | Interrupt notification block |
US20060161733A1 (en) * | 2005-01-19 | 2006-07-20 | Emulex Design & Manufacturing Corporation | Host buffer queues |
US7315917B2 (en) * | 2005-01-20 | 2008-01-01 | Sandisk Corporation | Scheduling of housekeeping operations in flash memory systems |
US20060161724A1 (en) * | 2005-01-20 | 2006-07-20 | Bennett Alan D | Scheduling of housekeeping operations in flash memory systems |
US20060236025A1 (en) * | 2005-04-18 | 2006-10-19 | Intel Corporation | Method and apparatus to control number of erasures of nonvolatile memory |
JP4688584B2 (en) * | 2005-06-21 | 2011-05-25 | 株式会社日立製作所 | Storage device |
KR100827227B1 (en) * | 2005-06-24 | 2008-05-07 | 삼성전자주식회사 | Method and apparatus for managing DRM right object in low-processing power's storage efficiently |
US8321953B2 (en) * | 2005-07-14 | 2012-11-27 | Imation Corp. | Secure storage device with offline code entry |
US8505075B2 (en) * | 2005-07-14 | 2013-08-06 | Marble Security, Inc. | Enterprise device recovery |
US8015606B1 (en) | 2005-07-14 | 2011-09-06 | Ironkey, Inc. | Storage device with website trust indication |
US8438647B2 (en) | 2005-07-14 | 2013-05-07 | Imation Corp. | Recovery of encrypted data from a secure storage device |
US8335920B2 (en) | 2005-07-14 | 2012-12-18 | Imation Corp. | Recovery of data access for a locked secure storage device |
US20070067620A1 (en) * | 2005-09-06 | 2007-03-22 | Ironkey, Inc. | Systems and methods for third-party authentication |
US7644251B2 (en) * | 2005-12-19 | 2010-01-05 | Sigmatel, Inc. | Non-volatile solid-state memory controller |
EP1966701A2 (en) * | 2005-12-21 | 2008-09-10 | Nxp B.V. | Memory with block-erasable locations |
US8639873B1 (en) | 2005-12-22 | 2014-01-28 | Imation Corp. | Detachable storage device with RAM cache |
US8266378B1 (en) | 2005-12-22 | 2012-09-11 | Imation Corp. | Storage device with accessible partitions |
US7594087B2 (en) * | 2006-01-19 | 2009-09-22 | Sigmatel, Inc. | System and method for writing data to and erasing data from non-volatile memory |
US20070300031A1 (en) * | 2006-06-22 | 2007-12-27 | Ironkey, Inc. | Memory data shredder |
JP2008015769A (en) * | 2006-07-05 | 2008-01-24 | Hitachi Ltd | Storage system and writing distribution method |
US20080091871A1 (en) * | 2006-10-12 | 2008-04-17 | Alan David Bennett | Non-volatile memory with worst-case control data management |
US20080091901A1 (en) * | 2006-10-12 | 2008-04-17 | Alan David Bennett | Method for non-volatile memory with worst-case control data management |
KR100791325B1 (en) * | 2006-10-27 | 2008-01-03 | 삼성전자주식회사 | Apparatus and method for managing nonvolatile memory |
TWI326028B (en) | 2006-11-20 | 2010-06-11 | Silicon Motion Inc | Method for flash memory data management |
US8151060B2 (en) | 2006-11-28 | 2012-04-03 | Hitachi, Ltd. | Semiconductor memory system having a snapshot function |
US8074011B2 (en) * | 2006-12-06 | 2011-12-06 | Fusion-Io, Inc. | Apparatus, system, and method for storage space recovery after reaching a read count limit |
CN101622594B (en) | 2006-12-06 | 2013-03-13 | 弗森-艾奥公司 | Apparatus, system, and method for managing data in a request device with an empty data token directive |
US9495241B2 (en) | 2006-12-06 | 2016-11-15 | Longitude Enterprise Flash S.A.R.L. | Systems and methods for adaptive data storage |
US9116823B2 (en) | 2006-12-06 | 2015-08-25 | Intelligent Intellectual Property Holdings 2 Llc | Systems and methods for adaptive error-correction coding |
US7710777B1 (en) * | 2006-12-20 | 2010-05-04 | Marvell International Ltd. | Semi-volatile NAND flash memory |
KR101087308B1 (en) * | 2006-12-27 | 2011-11-25 | 인텔 코오퍼레이션 | Initiative wear leveling for non-volatile memory |
TW200828320A (en) * | 2006-12-28 | 2008-07-01 | Genesys Logic Inc | Method for performing static wear leveling on flash memory |
US8254134B2 (en) | 2007-05-03 | 2012-08-28 | Super Talent Electronics, Inc. | Molded memory card with write protection switch assembly |
US7850468B2 (en) | 2007-06-28 | 2010-12-14 | Super Talent Electronics, Inc. | Lipstick-type USB device |
US8102658B2 (en) | 2007-07-05 | 2012-01-24 | Super Talent Electronics, Inc. | Micro-SD to secure digital adaptor card and manufacturing method |
US20090046512A1 (en) * | 2007-08-17 | 2009-02-19 | Munif Farhan Halloush | Reliability System for Use with Non-Volatile Memory Devices |
US7944702B2 (en) | 2007-08-27 | 2011-05-17 | Super Talent Electronics, Inc. | Press-push flash drive apparatus with metal tubular casing and snap-coupled plastic sleeve |
US7791918B2 (en) * | 2007-09-27 | 2010-09-07 | Intel Corporation | Stack position location identification for memory stacked packages |
US8241047B2 (en) | 2007-10-30 | 2012-08-14 | Super Talent Electronics, Inc. | Flash drive with spring-loaded swivel connector |
US8959307B1 (en) | 2007-11-16 | 2015-02-17 | Bitmicro Networks, Inc. | Reduced latency memory read transactions in storage devices |
US8116083B2 (en) | 2007-12-04 | 2012-02-14 | Super Talent Electronics, Inc. | Lipstick-type USB device with tubular housing |
US7836226B2 (en) | 2007-12-06 | 2010-11-16 | Fusion-Io, Inc. | Apparatus, system, and method for coordinating storage requests in a multi-processor/multi-thread environment |
US8195912B2 (en) * | 2007-12-06 | 2012-06-05 | Fusion-io, Inc | Apparatus, system, and method for efficient mapping of virtual and physical addresses |
US20090259819A1 (en) * | 2008-04-09 | 2009-10-15 | Skymedi Corporation | Method of wear leveling for non-volatile memory |
US9477587B2 (en) | 2008-04-11 | 2016-10-25 | Micron Technology, Inc. | Method and apparatus for a volume management system in a non-volatile memory device |
KR101517185B1 (en) * | 2008-04-15 | 2015-05-04 | 삼성전자주식회사 | Memory system and operating method thereof |
JP4439569B2 (en) * | 2008-04-24 | 2010-03-24 | 株式会社東芝 | Memory system |
US8041886B2 (en) * | 2008-09-15 | 2011-10-18 | Seagate Technology Llc | System and method of managing memory |
US8244959B2 (en) * | 2008-11-10 | 2012-08-14 | Atmel Rousset S.A.S. | Software adapted wear leveling |
US20100125696A1 (en) * | 2008-11-17 | 2010-05-20 | Prasanth Kumar | Memory Controller For Controlling The Wear In A Non-volatile Memory Device And A Method Of Operation Therefor |
US8094500B2 (en) | 2009-01-05 | 2012-01-10 | Sandisk Technologies Inc. | Non-volatile memory and method with write cache partitioning |
US8040744B2 (en) | 2009-01-05 | 2011-10-18 | Sandisk Technologies Inc. | Spare block management of non-volatile memories |
US8700840B2 (en) | 2009-01-05 | 2014-04-15 | SanDisk Technologies, Inc. | Nonvolatile memory with write cache having flush/eviction methods |
US8244960B2 (en) | 2009-01-05 | 2012-08-14 | Sandisk Technologies Inc. | Non-volatile memory and method with write cache partition management methods |
US8312204B2 (en) * | 2009-01-23 | 2012-11-13 | Seagate Technology Llc | System and method for wear leveling in a data storage device |
US8276042B2 (en) | 2009-02-03 | 2012-09-25 | Micron Technology, Inc. | Determining sector status in a memory device |
JP5341584B2 (en) * | 2009-03-17 | 2013-11-13 | 株式会社東芝 | Controller and memory system |
US8176295B2 (en) | 2009-04-20 | 2012-05-08 | Imation Corp. | Logical-to-physical address translation for a removable data storage device |
US8065469B2 (en) | 2009-04-20 | 2011-11-22 | Imation Corp. | Static wear leveling |
US8745365B2 (en) | 2009-08-06 | 2014-06-03 | Imation Corp. | Method and system for secure booting a computer by booting a first operating system from a secure peripheral device and launching a second operating system stored a secure area in the secure peripheral device on the first operating system |
US8683088B2 (en) * | 2009-08-06 | 2014-03-25 | Imation Corp. | Peripheral device data integrity |
JP5342014B2 (en) * | 2009-08-31 | 2013-11-13 | 株式会社日立製作所 | Storage system having multiple flash packages |
US9135190B1 (en) | 2009-09-04 | 2015-09-15 | Bitmicro Networks, Inc. | Multi-profile memory controller for computing devices |
US8665601B1 (en) | 2009-09-04 | 2014-03-04 | Bitmicro Networks, Inc. | Solid state drive with improved enclosure assembly |
US8447908B2 (en) | 2009-09-07 | 2013-05-21 | Bitmicro Networks, Inc. | Multilevel memory bus system for solid-state mass storage |
US8560804B2 (en) * | 2009-09-14 | 2013-10-15 | Bitmicro Networks, Inc. | Reducing erase cycles in an electronic storage device that uses at least one erase-limited memory device |
US9396104B1 (en) | 2010-03-22 | 2016-07-19 | Seagate Technology, Llc | Accessing compressed data of varying-sized quanta in non-volatile memory |
TWI457941B (en) * | 2010-06-25 | 2014-10-21 | Macronix Int Co Ltd | Method and apparatus for high-speed byte-access in block-based flash memory |
KR101131560B1 (en) | 2010-07-15 | 2012-04-04 | 주식회사 하이닉스반도체 | Non-Volitile Memory Device For Performing Wear-Leveling and Method Thereof |
US8850161B2 (en) * | 2010-10-13 | 2014-09-30 | Riverbed Technology, Inc. | Method of improving performance of a data storage device |
US20120203993A1 (en) * | 2011-02-08 | 2012-08-09 | SMART Storage Systems, Inc. | Memory system with tiered queuing and method of operation thereof |
US8909851B2 (en) | 2011-02-08 | 2014-12-09 | SMART Storage Systems, Inc. | Storage control system with change logging mechanism and method of operation thereof |
US8621328B2 (en) | 2011-03-04 | 2013-12-31 | International Business Machines Corporation | Wear-focusing of non-volatile memories for improved endurance |
US8935466B2 (en) | 2011-03-28 | 2015-01-13 | SMART Storage Systems, Inc. | Data storage system with non-volatile memory and method of operation thereof |
US8590050B2 (en) | 2011-05-11 | 2013-11-19 | International Business Machines Corporation | Security compliant data storage management |
US9417894B1 (en) | 2011-06-15 | 2016-08-16 | Ryft Systems, Inc. | Methods and apparatus for a tablet computer system incorporating a reprogrammable circuit module |
US20120324143A1 (en) * | 2011-06-15 | 2012-12-20 | Data Design Corporation | Methods and apparatus for data access by a reprogrammable circuit module |
US9098399B2 (en) | 2011-08-31 | 2015-08-04 | SMART Storage Systems, Inc. | Electronic system with storage management mechanism and method of operation thereof |
US9021319B2 (en) | 2011-09-02 | 2015-04-28 | SMART Storage Systems, Inc. | Non-volatile memory management system with load leveling and method of operation thereof |
US9021231B2 (en) | 2011-09-02 | 2015-04-28 | SMART Storage Systems, Inc. | Storage control system with write amplification control mechanism and method of operation thereof |
US9063844B2 (en) | 2011-09-02 | 2015-06-23 | SMART Storage Systems, Inc. | Non-volatile memory management system with time measure mechanism and method of operation thereof |
US9372755B1 (en) | 2011-10-05 | 2016-06-21 | Bitmicro Networks, Inc. | Adaptive power cycle sequences for data recovery |
US9239781B2 (en) | 2012-02-07 | 2016-01-19 | SMART Storage Systems, Inc. | Storage control system with erase block mechanism and method of operation thereof |
JP5882467B2 (en) * | 2012-03-13 | 2016-03-09 | 株式会社日立製作所 | Storage system having nonvolatile semiconductor memory device including nonvolatile semiconductor memory |
US9298252B2 (en) | 2012-04-17 | 2016-03-29 | SMART Storage Systems, Inc. | Storage control system with power down mechanism and method of operation thereof |
US9043669B1 (en) | 2012-05-18 | 2015-05-26 | Bitmicro Networks, Inc. | Distributed ECC engine for storage media |
US8949689B2 (en) | 2012-06-11 | 2015-02-03 | SMART Storage Systems, Inc. | Storage control system with data management mechanism and method of operation thereof |
US9846641B2 (en) | 2012-06-18 | 2017-12-19 | International Business Machines Corporation | Variability aware wear leveling |
US8750045B2 (en) | 2012-07-27 | 2014-06-10 | Sandisk Technologies Inc. | Experience count dependent program algorithm for flash memory |
US20140115422A1 (en) | 2012-10-24 | 2014-04-24 | Laurence H. Cooke | Non-volatile memory error correction |
US9671962B2 (en) | 2012-11-30 | 2017-06-06 | Sandisk Technologies Llc | Storage control system with data management mechanism of parity and method of operation thereof |
US9430339B1 (en) | 2012-12-27 | 2016-08-30 | Marvell International Ltd. | Method and apparatus for using wear-out blocks in nonvolatile memory |
US9123445B2 (en) | 2013-01-22 | 2015-09-01 | SMART Storage Systems, Inc. | Storage control system with data management mechanism and method of operation thereof |
US9329928B2 (en) | 2013-02-20 | 2016-05-03 | Sandisk Enterprise IP LLC. | Bandwidth optimization in a non-volatile memory system |
US9214965B2 (en) | 2013-02-20 | 2015-12-15 | Sandisk Enterprise Ip Llc | Method and system for improving data integrity in non-volatile storage |
US9183137B2 (en) | 2013-02-27 | 2015-11-10 | SMART Storage Systems, Inc. | Storage control system with data management mechanism and method of operation thereof |
US9470720B2 (en) | 2013-03-08 | 2016-10-18 | Sandisk Technologies Llc | Test system with localized heating and method of manufacture thereof |
US9423457B2 (en) | 2013-03-14 | 2016-08-23 | Bitmicro Networks, Inc. | Self-test solution for delay locked loops |
US9934045B1 (en) | 2013-03-15 | 2018-04-03 | Bitmicro Networks, Inc. | Embedded system boot from a storage device |
US9798688B1 (en) | 2013-03-15 | 2017-10-24 | Bitmicro Networks, Inc. | Bus arbitration with routing and failover mechanism |
US10489318B1 (en) | 2013-03-15 | 2019-11-26 | Bitmicro Networks, Inc. | Scatter-gather approach for parallel data transfer in a mass storage system |
US9400617B2 (en) | 2013-03-15 | 2016-07-26 | Bitmicro Networks, Inc. | Hardware-assisted DMA transfer with dependency table configured to permit-in parallel-data drain from cache without processor intervention when filled or drained |
US9501436B1 (en) | 2013-03-15 | 2016-11-22 | Bitmicro Networks, Inc. | Multi-level message passing descriptor |
US9734067B1 (en) | 2013-03-15 | 2017-08-15 | Bitmicro Networks, Inc. | Write buffering |
US9430386B2 (en) | 2013-03-15 | 2016-08-30 | Bitmicro Networks, Inc. | Multi-leveled cache management in a hybrid storage system |
US9672178B1 (en) | 2013-03-15 | 2017-06-06 | Bitmicro Networks, Inc. | Bit-mapped DMA transfer with dependency table configured to monitor status so that a processor is not rendered as a bottleneck in a system |
US9842024B1 (en) | 2013-03-15 | 2017-12-12 | Bitmicro Networks, Inc. | Flash electronic disk with RAID controller |
US9875205B1 (en) | 2013-03-15 | 2018-01-23 | Bitmicro Networks, Inc. | Network of memory systems |
US9971524B1 (en) | 2013-03-15 | 2018-05-15 | Bitmicro Networks, Inc. | Scatter-gather approach for parallel data transfer in a mass storage system |
US9916213B1 (en) | 2013-03-15 | 2018-03-13 | Bitmicro Networks, Inc. | Bus arbitration with routing and failover mechanism |
US10120694B2 (en) | 2013-03-15 | 2018-11-06 | Bitmicro Networks, Inc. | Embedded system boot from a storage device |
US9720603B1 (en) | 2013-03-15 | 2017-08-01 | Bitmicro Networks, Inc. | IOC to IOC distributed caching architecture |
US9043780B2 (en) | 2013-03-27 | 2015-05-26 | SMART Storage Systems, Inc. | Electronic system with system modification control mechanism and method of operation thereof |
US9170941B2 (en) | 2013-04-05 | 2015-10-27 | Sandisk Enterprises IP LLC | Data hardening in a storage system |
US10049037B2 (en) | 2013-04-05 | 2018-08-14 | Sandisk Enterprise Ip Llc | Data management in a storage system |
US9543025B2 (en) | 2013-04-11 | 2017-01-10 | Sandisk Technologies Llc | Storage control system with power-off time estimation mechanism and method of operation thereof |
US10546648B2 (en) | 2013-04-12 | 2020-01-28 | Sandisk Technologies Llc | Storage control system with data management mechanism and method of operation thereof |
US9898056B2 (en) | 2013-06-19 | 2018-02-20 | Sandisk Technologies Llc | Electronic assembly with thermal channel and method of manufacture thereof |
US9313874B2 (en) | 2013-06-19 | 2016-04-12 | SMART Storage Systems, Inc. | Electronic system with heat extraction and method of manufacture thereof |
US9367353B1 (en) | 2013-06-25 | 2016-06-14 | Sandisk Technologies Inc. | Storage control system with power throttling mechanism and method of operation thereof |
US9244519B1 (en) | 2013-06-25 | 2016-01-26 | Smart Storage Systems. Inc. | Storage system with data transfer rate adjustment for power throttling |
US9146850B2 (en) | 2013-08-01 | 2015-09-29 | SMART Storage Systems, Inc. | Data storage system with dynamic read threshold mechanism and method of operation thereof |
US9361222B2 (en) | 2013-08-07 | 2016-06-07 | SMART Storage Systems, Inc. | Electronic system with storage drive life estimation mechanism and method of operation thereof |
US9448946B2 (en) | 2013-08-07 | 2016-09-20 | Sandisk Technologies Llc | Data storage system with stale data mechanism and method of operation thereof |
US9431113B2 (en) | 2013-08-07 | 2016-08-30 | Sandisk Technologies Llc | Data storage system with dynamic erase block grouping mechanism and method of operation thereof |
US9152555B2 (en) | 2013-11-15 | 2015-10-06 | Sandisk Enterprise IP LLC. | Data management with modular erase in a data storage system |
US9811461B1 (en) | 2014-04-17 | 2017-11-07 | Bitmicro Networks, Inc. | Data storage system |
US10042792B1 (en) | 2014-04-17 | 2018-08-07 | Bitmicro Networks, Inc. | Method for transferring and receiving frames across PCI express bus for SSD device |
US10025736B1 (en) | 2014-04-17 | 2018-07-17 | Bitmicro Networks, Inc. | Exchange message protocol message transmission between two devices |
US10055150B1 (en) | 2014-04-17 | 2018-08-21 | Bitmicro Networks, Inc. | Writing volatile scattered memory metadata to flash device |
US9952991B1 (en) | 2014-04-17 | 2018-04-24 | Bitmicro Networks, Inc. | Systematic method on queuing of descriptors for multiple flash intelligent DMA engine operation |
US10078604B1 (en) | 2014-04-17 | 2018-09-18 | Bitmicro Networks, Inc. | Interrupt coalescing |
US10338817B2 (en) | 2014-12-30 | 2019-07-02 | Sandisk Technologies Llc | Systems and methods for storage recovery |
US10552050B1 (en) | 2017-04-07 | 2020-02-04 | Bitmicro Llc | Multi-dimensional computer storage system |
JP7020989B2 (en) | 2018-04-23 | 2022-02-16 | 株式会社メガチップス | Non-volatile storage device, memory control device, and memory control method |
Family Cites Families (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5945695A (en) * | 1982-09-07 | 1984-03-14 | Fujitsu Ltd | Ic memory |
JPH07109717B2 (en) * | 1986-05-31 | 1995-11-22 | キヤノン株式会社 | Memory write control method |
JP2685173B2 (en) * | 1986-05-31 | 1997-12-03 | キヤノン株式会社 | Memory write control method |
JPH0778997B2 (en) * | 1987-10-30 | 1995-08-23 | 株式会社東芝 | Non-volatile semiconductor memory |
US5053990A (en) * | 1988-02-17 | 1991-10-01 | Intel Corporation | Program/erase selection for flash memory |
US5095344A (en) * | 1988-06-08 | 1992-03-10 | Eliyahou Harari | Highly compact eprom and flash eeprom devices |
US5168465A (en) * | 1988-06-08 | 1992-12-01 | Eliyahou Harari | Highly compact EPROM and flash EEPROM devices |
US5043940A (en) * | 1988-06-08 | 1991-08-27 | Eliyahou Harari | Flash EEPROM memory systems having multistate storage cells |
JPH0283892A (en) * | 1988-09-20 | 1990-03-23 | Fujitsu Ltd | Semiconductor memory device |
US5341368A (en) * | 1992-05-05 | 1994-08-23 | American Tel-A-Systems, Inc. | Digital switching system interconnecting buses with imcompatible protocols |
DE69034191T2 (en) * | 1989-04-13 | 2005-11-24 | Sandisk Corp., Sunnyvale | EEPROM system with multi-chip block erasure |
US5172338B1 (en) * | 1989-04-13 | 1997-07-08 | Sandisk Corp | Multi-state eeprom read and write circuits and techniques |
US5163021A (en) * | 1989-04-13 | 1992-11-10 | Sundisk Corporation | Multi-state EEprom read and write circuits and techniques |
US5065364A (en) * | 1989-09-15 | 1991-11-12 | Intel Corporation | Apparatus for providing block erasing in a flash EPROM |
US5200959A (en) * | 1989-10-17 | 1993-04-06 | Sundisk Corporation | Device and method for defect handling in semi-conductor memory |
US5134589A (en) * | 1989-10-30 | 1992-07-28 | Mitsubishi Denki Kabushiki Kaisha | Semiconductor memory device having a flash write function |
JPH043394A (en) * | 1990-04-20 | 1992-01-08 | Citizen Watch Co Ltd | Semiconductor non-volatile storage device |
US5303198A (en) * | 1990-09-28 | 1994-04-12 | Fuji Photo Film Co., Ltd. | Method of recording data in memory card having EEPROM and memory card system using the same |
EP0489204B1 (en) * | 1990-12-04 | 1995-08-16 | Hewlett-Packard Limited | Reprogrammable data storage device |
GB2251323B (en) * | 1990-12-31 | 1994-10-12 | Intel Corp | Disk emulation for a non-volatile semiconductor memory |
US5272669A (en) * | 1991-02-20 | 1993-12-21 | Sundisk Corporation | Method and structure for programming floating gate memory cells |
US5283882A (en) * | 1991-02-22 | 1994-02-01 | Unisys Corporation | Data caching and address translation system with rapid turnover cycle |
US5270979A (en) * | 1991-03-15 | 1993-12-14 | Sundisk Corporation | Method for optimum erasing of EEPROM |
EP0509184A1 (en) * | 1991-04-18 | 1992-10-21 | STMicroelectronics S.r.l. | Flash memory erasable by sectors and related writing process |
JP2582487B2 (en) * | 1991-07-12 | 1997-02-19 | インターナショナル・ビジネス・マシーンズ・コーポレイション | External storage system using semiconductor memory and control method thereof |
DE69326370T2 (en) * | 1992-03-05 | 2000-01-20 | Toshiba Kawasaki Kk | Non-volatile semiconductor memory device |
US5341330A (en) * | 1992-10-30 | 1994-08-23 | Intel Corporation | Method for writing to a flash memory array during erase suspend intervals |
US5337275A (en) * | 1992-10-30 | 1994-08-09 | Intel Corporation | Method for releasing space in flash EEPROM memory array to allow the storage of compressed data |
JP3641280B2 (en) * | 1992-10-30 | 2005-04-20 | インテル・コーポレーション | Method for determining blocks to be cleaned up in a flash EEPROM array |
US5357475A (en) * | 1992-10-30 | 1994-10-18 | Intel Corporation | Method for detaching sectors in a flash EEPROM memory array |
US5404485A (en) * | 1993-03-08 | 1995-04-04 | M-Systems Flash Disk Pioneers Ltd. | Flash file system |
US5353256A (en) * | 1993-06-30 | 1994-10-04 | Intel Corporation | Block specific status information in a memory device |
-
1993
- 1993-03-26 US US08/037,893 patent/US5479638A/en not_active Expired - Lifetime
-
1994
- 1994-03-23 DE DE69431795T patent/DE69431795T2/en not_active Expired - Lifetime
- 1994-03-23 CA CA002161344A patent/CA2161344A1/en not_active Abandoned
- 1994-03-23 EP EP94912854A patent/EP0691008B1/en not_active Expired - Lifetime
- 1994-03-23 AT AT94912854T patent/ATE228674T1/en not_active IP Right Cessation
- 1994-03-23 WO PCT/US1994/003168 patent/WO1994023369A1/en active IP Right Grant
Also Published As
Publication number | Publication date |
---|---|
DE69431795D1 (en) | 2003-01-09 |
ATE228674T1 (en) | 2002-12-15 |
EP0691008B1 (en) | 2002-11-27 |
EP0691008A1 (en) | 1996-01-10 |
US5479638A (en) | 1995-12-26 |
EP0691008A4 (en) | 1998-03-25 |
WO1994023369A1 (en) | 1994-10-13 |
DE69431795T2 (en) | 2003-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5479638A (en) | Flash memory mass storage architecture incorporation wear leveling technique | |
US5388083A (en) | Flash memory mass storage architecture | |
US5485595A (en) | Flash memory mass storage architecture incorporating wear leveling technique without using cam cells | |
US6912618B2 (en) | Direct logical block addressing flash memory mass storage architecture | |
US8793430B2 (en) | Electronic system having memory with a physical block having a sector storing data and indicating a move status of another sector of the physical block | |
US6223308B1 (en) | Identification and verification of a sector within a block of mass STO rage flash memory | |
US5835935A (en) | Method of and architecture for controlling system data with automatic wear leveling in a semiconductor non-volatile mass storage memory | |
US5907856A (en) | Moving sectors within a block of information in a flash memory mass storage architecture | |
US20050138271A1 (en) | Rotational use of memory to minimize write cycles |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FZDE | Discontinued |