US20160224243A1 - Memory device for reducing a write fail, a system including the same, and a method thereof - Google Patents
Memory device for reducing a write fail, a system including the same, and a method thereof Download PDFInfo
- Publication number
- US20160224243A1 US20160224243A1 US15/096,920 US201615096920A US2016224243A1 US 20160224243 A1 US20160224243 A1 US 20160224243A1 US 201615096920 A US201615096920 A US 201615096920A US 2016224243 A1 US2016224243 A1 US 2016224243A1
- Authority
- US
- United States
- Prior art keywords
- write
- command
- memory
- data
- memory device
- 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
Images
Classifications
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C8/00—Arrangements for selecting an address in a digital store
- G11C8/08—Word line control circuits, e.g. drivers, boosters, pull-up circuits, pull-down circuits, precharging circuits, for word lines
-
- 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
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/14—Handling requests for interconnection or transfer
- G06F13/16—Handling requests for interconnection or transfer for access to memory bus
- G06F13/1605—Handling requests for interconnection or transfer for access to memory bus based on arbitration
- G06F13/1642—Handling requests for interconnection or transfer for access to memory bus based on arbitration with request queuing
-
- 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
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
-
- 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
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0659—Command handling arrangements, e.g. command buffers, queues, command scheduling
-
- 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
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0673—Single storage device
- G06F3/0674—Disk device
- G06F3/0676—Magnetic disk device
-
- 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
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0673—Single storage device
- G06F3/068—Hybrid storage device
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/21—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements
- G11C11/34—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices
- G11C11/40—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors
- G11C11/401—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors forming cells needing refreshing or charge regeneration, i.e. dynamic cells
- G11C11/4063—Auxiliary circuits, e.g. for addressing, decoding, driving, writing, sensing or timing
- G11C11/407—Auxiliary circuits, e.g. for addressing, decoding, driving, writing, sensing or timing for memory cells of the field-effect type
- G11C11/4076—Timing circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C7/00—Arrangements for writing information into, or reading information out from, a digital store
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C7/00—Arrangements for writing information into, or reading information out from, a digital store
- G11C7/10—Input/output [I/O] data interface arrangements, e.g. I/O data control circuits, I/O data buffers
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C7/00—Arrangements for writing information into, or reading information out from, a digital store
- G11C7/10—Input/output [I/O] data interface arrangements, e.g. I/O data control circuits, I/O data buffers
- G11C7/1048—Data bus control circuits, e.g. precharging, presetting, equalising
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Definitions
- the present inventive concept relates to a memory device, and more particularly, to a method of writing data to a memory device.
- the increased degree of integration of semiconductor devices has reduced elements in size and a gap between elements.
- dynamic random access memory (DRAM) device decreases in size, contact resistance and bit line resistance of a DRAM write path, thereby increasing a write time through the DRAM write path.
- DRAM dynamic random access memory
- the size of cell transistors is reduced to increase the degree of integration of semiconductor devices, the driving performance of the cell transistors decreases. Accordingly, semiconductor devices may need more time for a write operation.
- a memory system includes a memory device and a memory controller.
- the memory device includes a plurality of memory cells.
- the memory controller is configured to continuously perform a plurality of write commands on the memory device.
- the memory device perfoms a first write operation corresponding to a last write command of the plurality of write commands, performs a precharge operation and then performs a second write operation corresponding to the last write command after the precharge operation.
- the first write operation and the second write operation write a same data to memory cells of plurality of memory cells having a same address.
- the precharge operation may be performed in response to a precharge command issued from the memory controller or an internally generated precharge command in the memory device.
- a method of writing data to a memory device is provided.
- a word line in a memory bank is activated in response to an active command.
- a plurality of data sets is continuously written to memory cells associated with the word line in response to a corresponding write command of a plurality of write commands.
- the word line is precharged after a last write command of the plurality of write commands is performed.
- the last data set is written to the memory cells after the precharging.
- the precharging maybe performed in response to a precharge command issued from a memory controller or an internally generated precharge command in the memory device.
- a method of writing data to a memory device is provided.
- a plurality of write requests and a plurality of data sets are received from a host.
- a sequence of a plurality of write commands from the plurality of write requests is generated according to a predetermined scheduling method and the sequence is applied to a memory device between an active command and a precharge command.
- a last write command of the plurality of write commands is applied to the memory device after the precharge command.
- a memory controller includes an arbiter.
- the arbiter is configured to generate an active command, a precharge command, and a plurality of write commands having a common row address and configured to continuously issue the plurality of write commands between the active command and the precharge command, wherein the precharge command is issued after a first write operation is performed in response to a last write command of the plurality of write commands , the last write command is issued for a second write operation after the precharge command, and wherein the first write operation and the second write operation write a same data set to memory cells of plurality of memory cells having a same column address.
- FIG. 1 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept
- FIG. 2 is a block diagram of a memory controller according to an exemplary embodiment of the inventive concept
- FIG. 3 is a block diagram of a memory device according to an exemplary embodiment of the inventive concept
- FIG. 4 is a block diagram of a memory cell illustrated in FIG. 3 according to an exemplary embodiment of the inventive concept
- FIG. 5 is a circuit diagram conceptually showing a data write path to the memory cell illustrated in FIG. 4 ;
- FIG. 6 is a flowchart of a method of writing data to a memory device according to an exemplary embodiment of the inventive concept
- FIG. 7 is a diagram of a command queue and an execution sequence according to an exemplary embodiment of the inventive concept
- FIGS. 8A and 8B are signal timing charts illustrating a data write operation according to an exemplary embodiment of the inventive concept
- FIGS. 9A through 9C are signal timing charts illustrating a data write operation according to an exemplary embodiment of the inventive concept
- FIG. 10 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept.
- FIG. 11 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept.
- FIGS. 12A through 12C are diagrams for explaining a method of scheduling a write operation according to an exemplary embodiment of the inventive concept
- FIG. 13 is a diagram for explaining a method of scheduling a write operation according to an exemplary embodiment of the inventive concept
- FIG. 14 is a block diagram of a module including a plurality of memory devices according to an exemplary embodiment of the inventive concept
- FIG. 15 is a block diagram of a module including a plurality of memory devices according to an exemplary embodiment of the inventive concept
- FIG. 16 is a block diagram of a data processing system including the memory device illustrated in FIG. 1 according to an exemplary embodiment of the inventive concept;
- FIG. 17 is a block diagram of a data processing system including the memory device illustrated in FIG. 1 according to an exemplary embodiment of the inventive concept;
- FIG. 18 is a block diagram of a data processing system including the memory device illustrated in FIG. 1 according to an exemplary embodiment of the inventive concept;
- FIG. 19 is a diagram of a multi-chip package including the semiconductor memory device illustrated in FIG. 1 according to an exemplary embodiment of the inventive concept.
- FIG. 20 is a three-dimensional conceptual diagram of an example of the multi-chip package illustrated in FIG. 19 according to an exemplary embodiment of the inventive concept.
- FIG. 1 is a block diagram of a memory system 10 according to an exemplary embodiment of the inventive concept.
- FIG. 2 is a block diagram of a memory controller 100 according to an exemplary embodiment of the inventive concept.
- FIG. 3 is a block diagram of a memory device 200 according to an exemplary embodiment of the inventive concept. Referring to FIGS. 1 through 3 , the memory system 10 includes the memory controller 100 and the memory device 200 .
- the memory controller 100 includes an arbiter 110 , a command queue, a transaction processing unit 140 , and a memory interface 150 .
- the command queue includes a write queue 130 and a read queue 120 , as illustrated in FIG. 2 .
- the write queue 130 and the read queue 120 may be integrated into a single queue.
- the arbiter 110 receives a write request and a read request and generates a write command from the write request and a read command from the read request, sequentially storing the read command to the read queue 120 and the write command to the write queue 130 .
- the read queue 120 may store a read command and an address.
- the write queue 130 may store a write command, an address, and write data.
- the write data may be stored in a memory (e.g., a data queue or buffer (not shown)) while the write command and the address are stored in the write queue 130 .
- the arbiter 100 schedules or re-orders the sequence of the read and/or write commands stored in the queues 120 and 130 according to a predetermined scheduling algorithm and stores the commands.
- the memory controller 100 generates and executes other commands to control the operations of the memory device 200 .
- the arbiter 110 also generates an active command and a precharge command to open and close each row to execute a read or write request from the host.
- the arbiter 110 schedules commands from the requests received from the host 20 and the active and precharge commands according to a predetermined scheduling method.
- the arbiter 110 transmits the commands including an active command, a read/write command, and a precharge command according to the scheduling method to the memory device 200 via the memory interface 150 to control the operations of the memory device 200 .
- the transaction processing unit 140 prepares the memory device 200 to execute the commands CMD output from the arbiter 110 .
- the transaction processing unit 140 may serve to provide data to the host 20 without accessing the memory device 200 .
- the memory controller 100 may read the data from the write queue 130 and transmit it to the host 20 without accessing the memory device 200 .
- the memory controller 100 may execute a read command prior to any other commands before a write command among multiple read or write requests received from the host 20 .
- the memory controller 100 stores a write command in the write queue 130 and then schedules an execution sequence of commands stored in the write queue 130 according to a predetermined scheduling method. For example, a write command stored in the write queue 130 may be executed according to the priority determined by the scheduling method of the memory controller 100 and then the write command may be erased from the write queue 130 .
- a pointer designating a write command entry in the write queue 130 may be sequentially increased. For instance, once a write command designated by a pointer in the write queue 130 is executed, the pointer may be shifted to a next write command entry. However, after a write command (e.g., a write command right before a precharge command) is executed at a last write cycle in which a write recovery time (tWR in FIGS. 8A and 9B ) is not sufficient, the memory controller 100 does not shift the pointer to a next entry but controls the write command to be executed again.
- a write command e.g., a write command right before a precharge command
- the memory controller 100 when a write command entry corresponds to data written right before the precharge of the memory device 200 and the memory controller does not have sufficient time to write the data, the memory controller 100 re-executes the write command by retaining the write command entry in the write queue 130 instead of erasing it after the write command corresponding to the entry is executed.
- the memory controller 100 may execute the write command entry after execution of any other command following the precharge.
- the precharge may be performed in response to a precharge command issued from the memory controller 100 or an internally generated precharge command in the memory device 200 .
- an auto-precharge operaion may be performed by an internally generated precharge command without a precharge command issued from the memory controller 100 .
- the memory device 200 includes a memory cell array 210 , a row decoder 220 , a sense amplifier 230 , a column decoder 240 , a control logic 250 , and a data input/output circuit 260 .
- the operations of the memory device 200 will be described later.
- the memory cell array 210 is a data storage area in which memory cells are arranged in a row direction and a column direction.
- the sense amplifier 230 senses and amplifies data in the memory cells and stores data in the memory cells.
- the memory cell array 210 illustrated in FIG. 3 may include a plurality of (e.g., 4 or 8) memory banks, but the inventive concept is not restricted to the 4 or 8 memory banks.
- Data DQ input through the data input/output circuit 260 , is written to the memory cell array 210 based on an address signal ADD.
- the data DQ read from the memory cell array 210 based on the address signal ADD is output through the data input/output circuit 260 .
- the address signal ADD is input to an address buffer (not shown) to designate a memory cell to or from which data will be written or read.
- the address buffer temporarily stores the address signal ADD.
- the row decoder 220 decodes a row address in the address signal ADD output from the address buffer to designate a word line connected to a memory cell to or from which data will be input or output. For example, the row decoder 220 decodes a row address output from the address buffer and enables a word line in a data write or read mode.
- the column decoder 240 decodes a column address in the address signal ADD output from the address buffer to designate a bit line connected to a memory cell to or from which data will be input or output.
- the memory cell array 210 outputs data from or writes data to a memory cell designated by a row address and a column address.
- the control logic 250 receives and decodes an external command signal CMD, and generates a decoded command signal.
- the control logic 250 may include a mode register set/extended mode register set (MRS/EMRS) circuit (not shown) which sets an operation mode.
- MRS/EMRS mode register set/extended mode register set
- the MRS/EMRS circuit sets an internal mode register in response to an MRS/EMRS command for setting the operation mode of the memory device 200 and/or the address signal ADD.
- the memory device 200 may also include a clock circuit that generates a clock signal and a power circuit that receives an external power supply voltage and generates or distributes an internal voltage.
- FIG. 4 is a block diagram of a memory cell 210 according to an exemplary embodiment of the inventive concept.
- the memory cell 210 includes an access transistor TA connected to a word line WL and a bit line BL and a memory cell MC selectively connected by the access transistor TA to the bit line BL.
- the memory cell MC may include a cell capacitor.
- FIG. 5 is a circuit diagram showing a data write path to the memory cell MC illustrated in FIG. 4 . Referring to FIG. 5 , data is written to the memory cell MC through the bit line BL and the access transistor TA.
- the data write path includes bit line resistance Rbl of the bit line BL and contact resistance Rc between the access transistor TA and the memory cell (or cell capacitor) MC.
- bit line resistance Rbl increases.
- the contact resistance Rc increases. Therefore, current Ids flowing to the memory cell MC through the bit line BL decreases as the degree of integration of the memory cell 210 increases. As a result, it takes more time to write data to the memory cell MC through the increased resistance of the data write path. For example, the write recovery time (tWR) needs more clock cycles to correctly write data in the memory cell 210 , which will decrease write performance.
- FIG. 6 is a flowchart of a method of writing data to the memory device 200 according to an exemplary embodiment of the inventive concept.
- a write command and write data are received from a host in operation S 110 .
- the write command is stored in the write queue 130 and the write data is stored in the data queue in operation S 120 .
- the write command and an address are stored in the write queue 130 .
- the address may include a bank address, a row address, and a column address.
- the memory controller 100 generates a sequence of commands (e.g., an active command, a write command, and a precharge command) for writing the data to the memory device 200 and applies the sequence of commands to the memory device 200 in operation S 130 .
- the memory controller 100 after having issued the precharge command, applies the write command again to correctly write the data to the memory device 200 in operation S 140 .
- the repeated write command is interchangeably used as a rewrite command.
- the memory controller 100 stores the data till the execution of the rewrite command. For example, after the execution of the rewrite command is completed, the memory controller 100 may erase the write command and data.
- FIG. 7 is a diagram of a command queue and an execution sequence according to an exemplary embodiment of the inventive concept.
- FIGS. 8A and 8B are signal timing charts illustrating a data write operation according to an exemplary embodiment of the inventive concept.
- FIG. 8 illustrates the burst write operation of double data rate (DDR) DRAM with a clock write latency (CWL) of 5 and a burst length (BL) of 8.
- DDR double data rate
- CWL clock write latency
- BL burst length
- write commands “write (a, m, n)” and “write (a, m, p)” are sequentially stored in a write queue as shown in table T 3 .
- data is written to memory cells whose address information includes a bank address of “a”, a row address of “m”, and a column address of “n”.
- write command “write (a, m, p)” data is written to memory cells whose address information includes a bank address of “a”, a row address of “m”, and a column address of “p”.
- the arbiter 110 To execute the write commands (e.g., “write (a, m, n)” and “write (a, m, p)” stored in the write queue), the arbiter 110 generates a sequence of commands (or a command sequence) to be applied to the memory device 200 .
- the arbiter 110 may generate a sequence of commands such as an active command “Active (a, m)”, a first write command “write (a, m, n)”, a second write command “write (a, m, p)”, and a precharge command “Precharge (a)” and apply the sequence of commands to the memory device 200 as illustrated in table T 4 of FIG. 7 .
- the command sequence (or an execution sequence) generated by the memory controller 100 may be applied to the memory device 200 in the order of an active command Active, a first write command Write1 at T 0 , a second write command Write2 at T 4 , and a precharge command PRE at Tm in synchronization with the clock signal CLK.
- a no-operation command NOP may be placed between commands (e.g., between the first write command Write1 and the second write command Write2 or the second write command Write2 and the precharge command PRE).
- a corresponding word line WL in a corresponding bank is enabled.
- the first write command Writel enables a data write path including a corresponding bit line to write data DQ. Since the clock write latency is 5, the data DQ is written to the memory device 200 at T 5 five clock cycles after the first write command Write1 at T 0 .
- the data DQ may be written to memory cells associated with the word line WL and the bit line BL before the precharge command PRE is issued at Tm.
- a data write path is enabled and second burst data Dset 2 is written to the memory device 200 at T 9 .
- the second burst data Dset 2 has insufficient write recovery time (tWR).
- the word line WL that has been enabled is disabled in response to the precharge command PRE.
- a second write period tD 2 of second burst data Dset 2 is a time period measured between the first data D 0 at T 9 and the precharge command PRE at Tm.
- a first write period tD 1 of first burst data Dset 1 is a time period measured between the first data D 0 at T 5 and the precharge command PRE at Tm.
- the second write period tD 2 is shorter than the first write period tDl.
- time given to write the second burst data Dset 2 is shorter than time given to write the first burst data Dset 1 .
- the second burst data Dset 2 written right before the precharge command PRE may not be properly written due to insufficient write recovery time (tWR).
- the arbiter 110 controls the data Dset 2 of the last write cycle to be rewritten thereafter (e.g., after the precharge command).
- data in the last cycle indicates the data Dset 2 written right before the precharge.
- data received from the host 20 is temporarily stored in the data queue in the memory controller 100 .
- the data corresponding to the last write cycle may be insufficiently written in the memory device 200 when there is insufficient write recovery time for the data, Therefore, the memory controller 100 does not erase the data for the last write cycle from the write queue 130 or the data queue but retains the data and rewrites the data to the same address in the memory device 200 after the precharge command.
- the arbiter 110 regenerates the write command “write (a, m, p)” as shown in FIG. 7 and applies the write command to the memory device 200 .
- the active command “active (a, m)” is applied to the memory device 200 first to enable a bank and a word line corresponding to the write command “write (a, m, p)”.
- the arbiter 110 regenerates and applies a sequence of commands “active (a, m)” and “write (a, m, p)” to the memory device 200 to execute the write command “write (a, m, p)” executed right before the precharge, so that the rewrite operation is executed as illustrated in FIG.
- FIGS. 9A through 9C are signal timing charts illustrating a data writing operation according to an exemplary embodiment of the inventive concept.
- FIGS. 9A through 9C also illustrate the burst write operation of DDR DRAM with a CWL of 5 and a BL of 8.
- FIGS. 9A through 9C show a case where data is written to a word line WLn, then data is read from another word line WLn+1, and then last data is rewritten to the word line WLn.
- the word line WLn is precharged by a precharge command at Tm before the wordline WLn+1 is enabled.
- the wordline WLn+1 is required to be enabled after a row precharge time (tRP).
- the row precharge time (tRP) is the number of clock cycles needed to terminate access to the enabled wordline WLn, and open access to the next wordline WLn+1.
- the word line WLn+1 is activated and then a read command Read is applied to the word line WLn+1 after a time tRCD (i.e., the number of cycles from the active command to a read/write command). Then, data is read from the word line WLn+1 a time tAA (i.e., the number of clock cycles from the read command to first data) after the read command is applied. Therefore, latency of the read command executed after the precharge is “tRP+tRCD+tAA”.
- the data Dset 2 that has been written to the word line WLn before the precharge of the word line WLn is rewritten as illustrated in FIG. 9C .
- the operations are performed in order of FIG. 9A , FIG. 9B , and FIG. 9C in time domain.
- FIG. 10 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept.
- the memory system includes a memory controller 100 a and a memory device 200 a.
- the memory device 200 a includes a write queue 270 .
- the structure of the memory controller 100 a may be similar to that of the memory controller 100 illustrated in FIG. 2 .
- the memory device 200 a includes the write queue 270 in addition to the structure of the memory device 200 illustrated in FIG. 3 .
- FIG. 10 shows a memory device 200 a including the write queue 270 for storing a write command and an address and a separate storage space for storing relevant data.
- the memory device 200 a stores write commands received from the memory controller 100 a in the write queue 270 .
- the memory device 200 a may sequentially execute the write commands stored in the write queue 270 and erase a write command entry that has been executed from the write queue 270 .
- the memory device 200 a may retain a write command entry for data that has been written right before a precharge command even after the execution of the write command entry. For example, when the precharge command is issued before the data is correctly written into the memory device 200 a, the memory device 200 a retains the write command entry for the rewriting of the data after the precharge command.
- the memory device 200 a may execute at least one read or write command after the precharge command and before the rewriting of the data. For example, after the precharge command and before the rewriting of the data, a different command or operation may be performed.
- the memory device 200 a may execute a rewrite command for rewriting the same data as that written before without intervention of the memory controller 100 a. While writing data to a memory cell in response to a write command stored in the write queue 270 , the memory device 200 a may send a state signal WT indicating “under a write operation” to the memory controller 100 a.
- the state signal WT is transmitted using a separate signal line between the memory controller 100 a and the memory device 200 a.
- a special signal line for the state signal WT is provided between the memory controller 100 a and the memory device 200 a.
- the state signal WT may be transmitted using one of the existing signal lines.
- the memory controller 100 a accesses the memory device 200 a based on the state signal WT output from the memory device 200 a.
- FIG. 11 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept.
- the memory system includes a memory controller 100 b and a memory device 200 b.
- the memory device 200 b includes an event detector 280 .
- the structure of the memory controller 100 b may be similar to that of the memory controller 100 illustrated in FIG. 2 .
- the memory device 200 b includes the event detector 280 in addition to the structure of the memory device 200 illustrated in FIG. 3 .
- the event detector 280 detects whether a precharge command is performed on a page after a write command is executed on the page.
- the page is interchangeably used as an enabled wordline.
- the event detector 280 sends an alarm signal AT to the memory controller 100 b.
- the alarm signal AT informs the memory controller 100 b that the write command has not been properly executed.
- the memory controller 100 b Upon receiving the alarm signal AT from the memory device 200 b, the memory controller 100 b considers that an operation (e.g., a write operation right before precharge) corresponding to the alarm signal AT has not been performed and performs the operation thereafter.
- the memory controller 100 b may apply a rewrite command to the memory device 200 b in response to the alarm signal AT received from the memory device 200 b so that relevant data is rewritten.
- the alarm signal AT is transmitted using a separate signal line between the memory controller 100 b and the memory device 200 b.
- a special signal line for the alarm signal AT is provided between the memory controller 100 b and the memory device 200 b .
- the alarm signal AT may be transmitted using one of the existing signal lines.
- FIGS. 12A through 12C are diagrams for explaining a method of scheduling a write operation according to an exemplary embodiment of the inventive concept.
- a memory system schedules write operations using a write queue to reduce the number of active and precharge commands and improve performance of a memory system.
- a write queue may be included within the memory controller 100 or the memory device 200 , as described above. It is assumed that there are write commands A through H as shown in FIG. 12A . As shown in FIG. 12A , each of the write commands A through H includes a bank address BA, a row address RA and a column address CA. Each of the write commands A through H is for writing data to a certain address.
- the memory controller 100 may schedule them so that they are sequentially executed as shown in FIG. 12B .
- the memory controller 100 may schedule them referring to address information as shown in FIG. 12C .
- the write commands A through H may be scheduled so that write commands having the same row address RA may be executed sequentially.
- the write commands C, E, and G having the same row address RA as the write command A may be scheduled to be sequentially executed.
- the write command B is executed and then write commands D, F, and H having the same row address RA as the write command B may be scheduled to be sequentially executed.
- tRP denotes a precharge command period or a precharge-to-active delay
- tRRD denotes an active-to-active command period
- tAA denotes an internal read command-to-first data delay
- tCCD denotes a write-to-write delay
- tRCD denotes an active-to-internal read delay or an active-to-write delay.
- a total execution time is much longer in a case shown in FIG. 12B than in a case shown in FIG. 12C . Consequently, the total execution time can be reduced by the schedule of a plurality of write commands.
- FIG. 13 is a diagram for explaining a method of scheduling a write operation according to an exemplary embodiment of the inventive concept.
- write commands having the same bank address BA and the same row address RA are sequentially executed.
- no addresses include the same bank address BA and the same row address RA
- write commands having the same bank address BA are sequentially executed.
- a memory device e.g., DRAM
- a case where write commands having the same bank address BA but different row addresses RA are sequentially executed may be prevented.
- the deterioration of system performance is prevented.
- FIG. 14 is a block diagram of a module 500 including a plurality of memory devices 550 - 1 through 550 - 4 according to an exemplary embodiment of the inventive concept.
- the module 500 includes a memory controller 510 , an input/output (IO) interface 511 , and the memory devices 550 - 1 through 550 - 4 .
- the memory controller 510 and the I 0 interface 511 are disposed between a host and the memory devices 550 - 1 through 550 - 4 , communicating with the host.
- the memory controller 510 and the IO interface 511 may be integrated in a single chip.
- Each of the memory devices 550 - 1 through 550 - 4 may communicate data with the host through the integrated chip.
- the IO interface 511 may include an optical interface.
- the IO interface 511 may include an IO controller (not shown) controlling the input and output operations of the memory devices 550 - 1 through 550 - 4 and a signal converter (not shown) converting an input or output signal into an optical signal.
- the IO interface 511 may transfer data using an optical fiber or a waveguide.
- the data is suitable for the transmission of high-speed signals, for example, complying with serial advantage technology attachment (SATA) standards and may be transmitted using wavelength division multiplexing (WDM).
- SATA serial advantage technology attachment
- WDM wavelength division multiplexing
- FIG. 15 is a block diagram of a module 600 including a plurality of memory devices 610 - 1 through 610 - 5 according to an exemplary embodiment of the inventive concept.
- One (e.g., 610 - 3 ) of the memory devices 610 - 1 through 610 - 5 is directly connected to and communicates with a memory controller 620 .
- the memory devices 610 - 1 through 610 - 5 may be serially connected in a chain with one other.
- the memory devices 610 - 1 , 610 - 2 , 610 - 4 , and 610 - 5 that are not directly connected to the memory controller 620 communicate with a host indirectly through the chain.
- the memory controller 620 controlling the operation of the memory devices 610 - 1 through 610 - 5 may implemented within the module 600 or may be stacked on the memory devices 610 - 1 through 610 - 5 .
- FIG. 16 is a block diagram of a data processing system 800 including the memory device illustrated in FIG. 1 according to an exemplary embodiment of the inventive concept.
- the data processing system 800 may be implemented as a personal computer (PC), a tablet PC, a net-book, an e-reader, a personal digital assistant (PDA), a portable multimedia player (PMP), an MP3 player, or an MP4 player.
- PC personal computer
- PDA personal digital assistant
- PMP portable multimedia player
- MP3 player an MP3 player
- MP4 player an MP4 player
- the data processing system 800 includes the memory device 840 and a memory controller 850 controlling the data processing operations of the memory device 840 .
- the memory controller 850 may correspond to the memory controller 100 , 100 a or 100 b according to an exemplary embodiment of the inventive concept
- the memory device 840 may correspond to the memory device 200 , 200 a, or 200 b according to an exemplary embodiment of the inventive concept
- a processor 820 may display data stored in the memory device 840 through a display 810 according to data input through an input device 830 .
- the input device 830 may be implemented by a pointing device such as a touch pad or a computer mouse, a keypad, or a keyboard.
- the processor 820 may control the overall operation of the data processing system 800 and the operations of the memory controller 850 .
- FIG. 17 is a block diagram of a data processing system 900 including the memory device 950 illustrated in FIG. 1 according to an exemplary embodiment of the inventive concept.
- the data processing system 900 may be implemented as a cellular phone, a smart phone, a tablet personal computer (PC), a personal digital assistant (PDA) or a radio communication system.
- PC personal computer
- PDA personal digital assistant
- the data processing system 900 includes the memory device 950 and a memory controller 960 controlling the operations of the memory device 950 .
- the memory controller 960 may control the data access operations, e.g., a write operation, and a read operation, of the memory device 950 according to the control of a processor 940 .
- the data stored in the memory device 950 may be displayed through a display 930 according to the control of the processor 940 and/or the memory controller 960 .
- a radio transceiver 910 transmits or receives radio signals through an antenna ANT.
- the radio transceiver 910 may convert radio signals received through the antenna ANT into signals that are processed by the processor 940 .
- the processor 940 may process the signals output from the radio transceiver 910 and may transmit the processed signals to the memory controller 960 or the display 930 .
- the memory controller 960 may transmit the signals processed by the processor 940 to the memory device 950 .
- the radio transceiver 910 may also convert signals output from the processor 940 into radio signals and may output the radio signals to an external device through the antenna ANT.
- An input device 920 enables control signals for controlling the operation of the processor 940 or data to be processed by the processor 940 to be input to the data processing system 900 .
- the input device 920 may be implemented by a pointing device such as a touch pad or a computer mouse, a keypad, or a keyboard.
- the processor 940 may control the operation of the display 930 to display data output from the memory controller 960 , data output from the radio transceiver 910 , or data output from the input device 920 .
- the memory controller 960 may correspond to the memory controller 100 , 100 a or 100 b according to an exemplary embodiment of the inventive concept, and the memory device 950 may correspond to the memory device 200 , 200 a, or 200 b according to an exemplary embodiment of the inventive concept.
- FIG. 18 is a block diagram of a data processing system 1000 including the memory device illustrated in FIG. 1 according to an exemplary embodiment of the inventive concept.
- the data processing system 1000 may be implemented as an image processor such as a digital camera, a cellular phone equipped with a digital camera, a smart phone equipped with a digital camera, or a tablet PC equipped with a digital camera.
- the data processing system 1000 includes the memory device 1040 and a memory controller 1050 controlling the data processing operations, such as a write operation, and a read operation, of the memory device 1040 .
- An image sensor 1010 included in the data processing system 1000 converts optical images into digital signals and outputs the digital signals to a processor 1020 or the memory controller 1050 .
- the digital signals may be controlled by the processor 1020 to be displayed through a display 1030 or stored in the memory device 1040 through the memory controller 1050 .
- Data stored in the memory device 1040 may be displayed through the display 1030 according to the control of the processor 1020 or the memory controller 1050 .
- the memory controller 1050 may control the operations of the memory device 1040 .
- the memory controller 1050 may correspond to the memory controller 100 , 100 a or 100 b according to an exemplary embodiment of the inventive concept, and the memory device 1040 may correspond to the memory device 200 , 200 a, or 200 b according to an exemplary embodiment of the inventive concept.
- FIG. 19 is a diagram of a multi-chip package 1300 including the semiconductor memory device illustrated in FIG. 1 according to an exemplary embodiment of the inventive concept.
- the multi-chip package 1300 includes a plurality of semiconductor devices, e.g., first through third chips 1330 , 1340 , and 1350 which are sequentially stacked on a package substrate 1310 .
- Each of the semiconductor devices 1330 through 1350 may include a memory controller and/or a semiconductor memory device according to an exemplary embodiment.
- a through-silicon via (TSV) (not shown), a bonding wire (not shown), a bump (not shown), or a solder ball 1320 may be used to electrically connect the semiconductor devices 1330 through 1350 with one other.
- TSV through-silicon via
- bonding wire not shown
- a bump not shown
- solder ball 1320 may be used to electrically connect the semiconductor devices 1330 through 1350 with one other.
- the first semiconductor device 1330 may include a logic device die including an input/output interface and a memory controller and the second and third semiconductor devices 1340 and 1350 may include a memory device die.
- the second and third semiconductor devices 1340 and 1350 may include a plurality of memory devices stacked on each other, and may include a memory cell array.
- a memory device of the second semiconductor device 1340 and a memory device of the third semiconductor device 1350 may be the same or different types of memory.
- each of the first through third semiconductor devices 1330 through 1350 may include a memory controller.
- the memory controller may be on the same die as a memory cell array or may be on a different die than the memory cell array.
- the first semiconductor device 1330 may include an optical interface.
- a memory controller may be positioned in the first or second semiconductor device 1330 or 1340 and a memory device may be positioned in the second or third semiconductor device 1340 or 1350 .
- the memory device may be connected with the memory controller through a TSV.
- the multi-chip package 1300 may be implemented using hybrid memory cube (HMC) in which a memory controller and a memory cell array die are stacked.
- HMC hybrid memory cube
- the performance of memory devices increases due to the increase of bandwidth and the area of the memory devices is minimized. As a result, power consumption and manufacturing cost may be reduced.
- FIG. 20 is an exemplary three-dimensional conceptual diagram of an example of the multi-chip package 1300 illustrated in FIG. 19 according to an exemplary embodiment of the inventive concept.
- the multi-chip package 1300 ′ includes a plurality of the dies 1330 through 1350 connected with one another through TSVs 1360 in a stack structure.
- Each of the dies 1330 through 1350 may include a plurality of circuit blocks (not shown) and a periphery circuit to realize the functions of the semiconductor memory device 200 .
- the dies 1330 through 1350 may be referred to as a cell array.
- the plurality of circuit blocks may be implemented by memory blocks.
- the TSVs 1360 may include a conductive material including a metal such as copper (Cu).
- the TSVs 1360 are arranged at the center of a silicon substrate.
- the silicon substrate surrounds the TSVs 1360 .
- An insulating region (not shown) may be disposed between the TSVs 1360 and the silicon substrate.
- the present general inventive concept can also be embodied as computer-readable codes on a computer-readable medium.
- the computer-readable recording medium is any data storage device that can store data as a program which can be thereafter read by a computer system. Examples of the computer-readable recording medium include read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tapes, floppy disks, and optical data storage devices.
- the computer-readable recording medium can also be distributed over network coupled computer systems so that the computer-readable code is stored and executed in a distributed fashion. Also, functional programs, codes, and code segments to accomplish the present general inventive concept can be easily construed by programmers.
- parameters, such as write recovery time, of memory devices may be efficiently released, so that the yield of memory devices can be increased with the released parameters.
Abstract
A memory system includes a memory device and a memory controller. The memory device includes a plurality of memory cells. The memory controller is configured to continuously perform a plurality of write commands on the memory device between an active command and a precharge command. In the memory system, when after a first write operation having a last write command of the plurality of write commands is performed and then the precharge command is issued, the last write command is issued for a second write operation after the precharge command. The first write operation and the second write operation write a same data to memory cells of plurality of memory cells having a same address.
Description
- This application is a divisional of U.S. application Ser. No. 14/013,275 filed Aug. 29, 2013, which claims priority under 35 U.S.C. §119(a) to Korean Patent Application No. 10-2012-0095223 filed on Aug. 29, 2012 in the Korean Intellectual Property Office, the disclosure of which is incorporated by reference herein in its entirety.
- The present inventive concept relates to a memory device, and more particularly, to a method of writing data to a memory device.
- The increased degree of integration of semiconductor devices has reduced elements in size and a gap between elements. For example, dynamic random access memory (DRAM) device decreases in size, contact resistance and bit line resistance of a DRAM write path, thereby increasing a write time through the DRAM write path. Further, as the size of cell transistors is reduced to increase the degree of integration of semiconductor devices, the driving performance of the cell transistors decreases. Accordingly, semiconductor devices may need more time for a write operation.
- According to an exemplary embodiment of the inventive concept, a memory system includes a memory device and a memory controller. The memory device includes a plurality of memory cells. The memory controller is configured to continuously perform a plurality of write commands on the memory device. In the memory system, the memory device perfoms a first write operation corresponding to a last write command of the plurality of write commands, performs a precharge operation and then performs a second write operation corresponding to the last write command after the precharge operation.The first write operation and the second write operation write a same data to memory cells of plurality of memory cells having a same address.
- The precharge operation may be performed in response to a precharge command issued from the memory controller or an internally generated precharge command in the memory device.
- According to an exemplary embodiment of the inventive concept, a method of writing data to a memory device is provided. A word line in a memory bank is activated in response to an active command. A plurality of data sets is continuously written to memory cells associated with the word line in response to a corresponding write command of a plurality of write commands. The word line is precharged after a last write command of the plurality of write commands is performed. In response to the last write command, the last data set is written to the memory cells after the precharging.
- The precharging maybe performed in response to a precharge command issued from a memory controller or an internally generated precharge command in the memory device.
- According to an exemplary embodiment of the inventive concept, a method of writing data to a memory device is provided. A plurality of write requests and a plurality of data sets are received from a host. A sequence of a plurality of write commands from the plurality of write requests is generated according to a predetermined scheduling method and the sequence is applied to a memory device between an active command and a precharge command. A last write command of the plurality of write commands is applied to the memory device after the precharge command.
- According to an exemplary embodiment of the inventive concept, a memory controller includes an arbiter. The arbiter is configured to generate an active command, a precharge command, and a plurality of write commands having a common row address and configured to continuously issue the plurality of write commands between the active command and the precharge command, wherein the precharge command is issued after a first write operation is performed in response to a last write command of the plurality of write commands , the last write command is issued for a second write operation after the precharge command, and wherein the first write operation and the second write operation write a same data set to memory cells of plurality of memory cells having a same column address.
- These and other features of the inventive concept will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings of which:
-
FIG. 1 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept; -
FIG. 2 is a block diagram of a memory controller according to an exemplary embodiment of the inventive concept; -
FIG. 3 is a block diagram of a memory device according to an exemplary embodiment of the inventive concept; -
FIG. 4 is a block diagram of a memory cell illustrated inFIG. 3 according to an exemplary embodiment of the inventive concept; -
FIG. 5 is a circuit diagram conceptually showing a data write path to the memory cell illustrated inFIG. 4 ; -
FIG. 6 is a flowchart of a method of writing data to a memory device according to an exemplary embodiment of the inventive concept; -
FIG. 7 is a diagram of a command queue and an execution sequence according to an exemplary embodiment of the inventive concept; -
FIGS. 8A and 8B are signal timing charts illustrating a data write operation according to an exemplary embodiment of the inventive concept; -
FIGS. 9A through 9C are signal timing charts illustrating a data write operation according to an exemplary embodiment of the inventive concept; -
FIG. 10 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept; -
FIG. 11 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept; -
FIGS. 12A through 12C are diagrams for explaining a method of scheduling a write operation according to an exemplary embodiment of the inventive concept; -
FIG. 13 is a diagram for explaining a method of scheduling a write operation according to an exemplary embodiment of the inventive concept; -
FIG. 14 is a block diagram of a module including a plurality of memory devices according to an exemplary embodiment of the inventive concept; -
FIG. 15 is a block diagram of a module including a plurality of memory devices according to an exemplary embodiment of the inventive concept; -
FIG. 16 is a block diagram of a data processing system including the memory device illustrated inFIG. 1 according to an exemplary embodiment of the inventive concept; -
FIG. 17 is a block diagram of a data processing system including the memory device illustrated inFIG. 1 according to an exemplary embodiment of the inventive concept; -
FIG. 18 is a block diagram of a data processing system including the memory device illustrated inFIG. 1 according to an exemplary embodiment of the inventive concept; -
FIG. 19 is a diagram of a multi-chip package including the semiconductor memory device illustrated inFIG. 1 according to an exemplary embodiment of the inventive concept; and -
FIG. 20 is a three-dimensional conceptual diagram of an example of the multi-chip package illustrated inFIG. 19 according to an exemplary embodiment of the inventive concept. - Exemplary embodiments of the inventive concept will be described below in more detail with reference to the accompanying drawings. This inventive concept may, however, be embodied in different forms and should not be construed as limited to the embodiments set forth herein. In the drawings, the size and relative sizes of layers and regions may be exaggerated for clarity. Like numbers may refer to like elements throughout the specification and drawings.
- It will be understood that when an element is referred to as being “connected” or “coupled” to another element, it can be directly connected or coupled to the other element or intervening elements may be present.
- As used herein, the singular “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise
-
FIG. 1 is a block diagram of amemory system 10 according to an exemplary embodiment of the inventive concept.FIG. 2 is a block diagram of amemory controller 100 according to an exemplary embodiment of the inventive concept.FIG. 3 is a block diagram of amemory device 200 according to an exemplary embodiment of the inventive concept. Referring toFIGS. 1 through 3 , thememory system 10 includes thememory controller 100 and thememory device 200. - The
memory controller 100 includes anarbiter 110, a command queue, atransaction processing unit 140, and amemory interface 150. The command queue includes awrite queue 130 and aread queue 120, as illustrated inFIG. 2 . In an exemplary embodiment, thewrite queue 130 and theread queue 120 may be integrated into a single queue. - The
arbiter 110 receives a write request and a read request and generates a write command from the write request and a read command from the read request, sequentially storing the read command to theread queue 120 and the write command to thewrite queue 130. Theread queue 120 may store a read command and an address. Thewrite queue 130 may store a write command, an address, and write data. In an exemplary embodiment, the write data may be stored in a memory (e.g., a data queue or buffer (not shown)) while the write command and the address are stored in thewrite queue 130. - The
arbiter 100 schedules or re-orders the sequence of the read and/or write commands stored in thequeues - The
memory controller 100 generates and executes other commands to control the operations of thememory device 200. For instance, when thememory device 200 includes a DRAM device, thearbiter 110 also generates an active command and a precharge command to open and close each row to execute a read or write request from the host. Thearbiter 110 schedules commands from the requests received from thehost 20 and the active and precharge commands according to a predetermined scheduling method. Thearbiter 110 transmits the commands including an active command, a read/write command, and a precharge command according to the scheduling method to thememory device 200 via thememory interface 150 to control the operations of thememory device 200. - The
transaction processing unit 140 prepares thememory device 200 to execute the commands CMD output from thearbiter 110. Thetransaction processing unit 140 may serve to provide data to thehost 20 without accessing thememory device 200. For example, when receiving a read request from thehost 20 with respect to write data that has been stored in thewrite queue 130, in other words, write data that has not been written to thememory device 200, thememory controller 100 may read the data from thewrite queue 130 and transmit it to thehost 20 without accessing thememory device 200. - The
memory controller 100 may execute a read command prior to any other commands before a write command among multiple read or write requests received from thehost 20. Thememory controller 100 stores a write command in thewrite queue 130 and then schedules an execution sequence of commands stored in thewrite queue 130 according to a predetermined scheduling method. For example, a write command stored in thewrite queue 130 may be executed according to the priority determined by the scheduling method of thememory controller 100 and then the write command may be erased from thewrite queue 130. - A pointer designating a write command entry in the
write queue 130 may be sequentially increased. For instance, once a write command designated by a pointer in thewrite queue 130 is executed, the pointer may be shifted to a next write command entry. However, after a write command (e.g., a write command right before a precharge command) is executed at a last write cycle in which a write recovery time (tWR inFIGS. 8A and 9B ) is not sufficient, thememory controller 100 does not shift the pointer to a next entry but controls the write command to be executed again. For example, when a write command entry corresponds to data written right before the precharge of thememory device 200 and the memory controller does not have sufficient time to write the data, thememory controller 100 re-executes the write command by retaining the write command entry in thewrite queue 130 instead of erasing it after the write command corresponding to the entry is executed. In an exemplary embodiment, thememory controller 100 may execute the write command entry after execution of any other command following the precharge. The precharge may be performed in response to a precharge command issued from thememory controller 100 or an internally generated precharge command in thememory device 200. For example, an auto-precharge operaion may be performed by an internally generated precharge command without a precharge command issued from thememory controller 100. - The
memory device 200 includes amemory cell array 210, arow decoder 220, asense amplifier 230, acolumn decoder 240, acontrol logic 250, and a data input/output circuit 260. The operations of thememory device 200 will be described later. - The
memory cell array 210 is a data storage area in which memory cells are arranged in a row direction and a column direction. Thesense amplifier 230 senses and amplifies data in the memory cells and stores data in the memory cells. Thememory cell array 210 illustrated inFIG. 3 may include a plurality of (e.g., 4 or 8) memory banks, but the inventive concept is not restricted to the 4 or 8 memory banks. - Data DQ, input through the data input/
output circuit 260, is written to thememory cell array 210 based on an address signal ADD. The data DQ read from thememory cell array 210 based on the address signal ADD is output through the data input/output circuit 260. - The address signal ADD is input to an address buffer (not shown) to designate a memory cell to or from which data will be written or read. The address buffer temporarily stores the address signal ADD.
- The
row decoder 220 decodes a row address in the address signal ADD output from the address buffer to designate a word line connected to a memory cell to or from which data will be input or output. For example, therow decoder 220 decodes a row address output from the address buffer and enables a word line in a data write or read mode. - The
column decoder 240 decodes a column address in the address signal ADD output from the address buffer to designate a bit line connected to a memory cell to or from which data will be input or output. - The
memory cell array 210 outputs data from or writes data to a memory cell designated by a row address and a column address. - The
control logic 250 receives and decodes an external command signal CMD, and generates a decoded command signal. Thecontrol logic 250 may include a mode register set/extended mode register set (MRS/EMRS) circuit (not shown) which sets an operation mode. The MRS/EMRS circuit sets an internal mode register in response to an MRS/EMRS command for setting the operation mode of thememory device 200 and/or the address signal ADD. - Although not shown in
FIG. 3 , thememory device 200 may also include a clock circuit that generates a clock signal and a power circuit that receives an external power supply voltage and generates or distributes an internal voltage. -
FIG. 4 is a block diagram of amemory cell 210 according to an exemplary embodiment of the inventive concept. Referring toFIG. 4 , thememory cell 210 includes an access transistor TA connected to a word line WL and a bit line BL and a memory cell MC selectively connected by the access transistor TA to the bit line BL. The memory cell MC may include a cell capacitor. -
FIG. 5 is a circuit diagram showing a data write path to the memory cell MC illustrated inFIG. 4 . Referring toFIG. 5 , data is written to the memory cell MC through the bit line BL and the access transistor TA. - The data write path includes bit line resistance Rbl of the bit line BL and contact resistance Rc between the access transistor TA and the memory cell (or cell capacitor) MC. As the bit line BL gets finer and longer, the bit line resistance Rbl increases. As the contact size of the memory cell MC decreases, the contact resistance Rc increases. Therefore, current Ids flowing to the memory cell MC through the bit line BL decreases as the degree of integration of the
memory cell 210 increases. As a result, it takes more time to write data to the memory cell MC through the increased resistance of the data write path. For example, the write recovery time (tWR) needs more clock cycles to correctly write data in thememory cell 210, which will decrease write performance. -
FIG. 6 is a flowchart of a method of writing data to thememory device 200 according to an exemplary embodiment of the inventive concept. Referring toFIGS. 2, 3 , and 6, a write command and write data are received from a host in operation S110. The write command is stored in thewrite queue 130 and the write data is stored in the data queue in operation S120. For instance, the write command and an address are stored in thewrite queue 130. The address may include a bank address, a row address, and a column address. - The
memory controller 100 generates a sequence of commands (e.g., an active command, a write command, and a precharge command) for writing the data to thememory device 200 and applies the sequence of commands to thememory device 200 in operation S130. Thememory controller 100, after having issued the precharge command, applies the write command again to correctly write the data to thememory device 200 in operation S140. Hereafter, the repeated write command is interchangeably used as a rewrite command. To rewrite the data written right before the precharge, thememory controller 100 stores the data till the execution of the rewrite command. For example, after the execution of the rewrite command is completed, thememory controller 100 may erase the write command and data. -
FIG. 7 is a diagram of a command queue and an execution sequence according to an exemplary embodiment of the inventive concept.FIGS. 8A and 8B are signal timing charts illustrating a data write operation according to an exemplary embodiment of the inventive concept. In particular,FIG. 8 illustrates the burst write operation of double data rate (DDR) DRAM with a clock write latency (CWL) of 5 and a burst length (BL) of 8. - Referring to
FIG. 7 andFIGS. 8A and 8B , write commands “write (a, m, n)” and “write (a, m, p)” are sequentially stored in a write queue as shown in table T3. In response to the write command “write (a, m, n)”, data is written to memory cells whose address information includes a bank address of “a”, a row address of “m”, and a column address of “n”. In response to the write command “write (a, m, p)”, data is written to memory cells whose address information includes a bank address of “a”, a row address of “m”, and a column address of “p”. - To execute the write commands (e.g., “write (a, m, n)” and “write (a, m, p)” stored in the write queue), the
arbiter 110 generates a sequence of commands (or a command sequence) to be applied to thememory device 200. For instance, thearbiter 110 may generate a sequence of commands such as an active command “Active (a, m)”, a first write command “write (a, m, n)”, a second write command “write (a, m, p)”, and a precharge command “Precharge (a)” and apply the sequence of commands to thememory device 200 as illustrated in table T4 ofFIG. 7 . - Referring to
FIGS. 8A and 8B , the command sequence (or an execution sequence) generated by thememory controller 100 may be applied to thememory device 200 in the order of an active command Active, a first write command Write1 at T0, a second write command Write2 at T4, and a precharge command PRE at Tm in synchronization with the clock signal CLK. A no-operation command NOP may be placed between commands (e.g., between the first write command Write1 and the second write command Write2 or the second write command Write2 and the precharge command PRE). - In response to the active command Active, a corresponding word line WL in a corresponding bank is enabled. Then, the first write command Writel enables a data write path including a corresponding bit line to write data DQ. Since the clock write latency is 5, the data DQ is written to the
memory device 200 at T5 five clock cycles after the first write command Write1 at T0. The data DQ may be written to memory cells associated with the word line WL and the bit line BL before the precharge command PRE is issued at Tm. - In response to the second write command Write2, a data write path is enabled and second burst data Dset2 is written to the
memory device 200 at T9. When the precharge command PRE is issued before the second burst data Dset2 is correctly written, the second burst data Dset2 has insufficient write recovery time (tWR). The word line WL that has been enabled is disabled in response to the precharge command PRE. A second write period tD2 of second burst data Dset2 is a time period measured between the first data D0 at T9 and the precharge command PRE at Tm. A first write period tD1 of first burst data Dset1 is a time period measured between the first data D0 at T5 and the precharge command PRE at Tm. Accordingly, the second write period tD2 is shorter than the first write period tDl. For example, time given to write the second burst data Dset2 is shorter than time given to write the first burst data Dset1. As a result, the second burst data Dset2 written right before the precharge command PRE may not be properly written due to insufficient write recovery time (tWR). - For instance, when a bank and a word line in the
memory device 200 are activated or enabled and then, a plurality of write commands are continuously applied prior to a precharge command, the last write cycle corresponding to the last write command of the multiple write commands has a shorter data write period than that of the preceding write cycles. Therefore, a corresponding data is insufficiently written into a memory cell corresponding to the last write cycle prior to the precharge command. According to an exemplary embodiment, thearbiter 110 controls the data Dset2 of the last write cycle to be rewritten thereafter (e.g., after the precharge command). Here, “data in the last cycle” indicates the data Dset2 written right before the precharge. - For a write request, data received from the
host 20 is temporarily stored in the data queue in thememory controller 100. The data corresponding to the last write cycle may be insufficiently written in thememory device 200 when there is insufficient write recovery time for the data, Therefore, thememory controller 100 does not erase the data for the last write cycle from thewrite queue 130 or the data queue but retains the data and rewrites the data to the same address in thememory device 200 after the precharge command. - In this operation, the
arbiter 110 regenerates the write command “write (a, m, p)” as shown inFIG. 7 and applies the write command to thememory device 200. The active command “active (a, m)” is applied to thememory device 200 first to enable a bank and a word line corresponding to the write command “write (a, m, p)”. For example, thearbiter 110 regenerates and applies a sequence of commands “active (a, m)” and “write (a, m, p)” to thememory device 200 to execute the write command “write (a, m, p)” executed right before the precharge, so that the rewrite operation is executed as illustrated inFIG. 8B when the write command “write (a, m, p)” has insufficient write recovery time (tWR). The operation is performed in order ofFIG. 8A andFIG. 8B in time domain. Although not shown inFIGS. 8A and 8B , other commands (e.g., a read command) may be executed before the rewrite command. -
FIGS. 9A through 9C are signal timing charts illustrating a data writing operation according to an exemplary embodiment of the inventive concept.FIGS. 9A through 9C also illustrate the burst write operation of DDR DRAM with a CWL of 5 and a BL of 8. For example,FIGS. 9A through 9C show a case where data is written to a word line WLn, then data is read from another wordline WLn+ 1, and then last data is rewritten to the word line WLn. - Referring to
FIGS. 9A and 9B , after data Dset1 and Dset2 are written to the word line WLn, the word line WLn is precharged by a precharge command at Tm before the wordline WLn+1 is enabled. The wordline WLn+1 is required to be enabled after a row precharge time (tRP). The row precharge time (tRP) is the number of clock cycles needed to terminate access to the enabled wordline WLn, and open access to the nextwordline WLn+ 1. After the precharge command for the word line WLn, the wordline WLn+ 1 is activated and then a read command Read is applied to the word line WLn+1 after a time tRCD (i.e., the number of cycles from the active command to a read/write command). Then, data is read from the word line WLn+1 a time tAA (i.e., the number of clock cycles from the read command to first data) after the read command is applied. Therefore, latency of the read command executed after the precharge is “tRP+tRCD+tAA”. - After the read command is executed on the word
line WLn+ 1, the data Dset2 that has been written to the word line WLn before the precharge of the word line WLn is rewritten as illustrated inFIG. 9C . The operations are performed in order ofFIG. 9A ,FIG. 9B , andFIG. 9C in time domain. -
FIG. 10 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept. Referring toFIG. 10 , the memory system includes amemory controller 100 a and amemory device 200 a. Thememory device 200 a includes awrite queue 270. The structure of thememory controller 100 a may be similar to that of thememory controller 100 illustrated inFIG. 2 . For example, thememory device 200 a includes thewrite queue 270 in addition to the structure of thememory device 200 illustrated inFIG. 3 .FIG. 10 shows amemory device 200 a including thewrite queue 270 for storing a write command and an address and a separate storage space for storing relevant data. - The
memory device 200 a stores write commands received from thememory controller 100 a in thewrite queue 270. Thememory device 200 a may sequentially execute the write commands stored in thewrite queue 270 and erase a write command entry that has been executed from thewrite queue 270. However, thememory device 200 a may retain a write command entry for data that has been written right before a precharge command even after the execution of the write command entry. For example, when the precharge command is issued before the data is correctly written into thememory device 200 a, thememory device 200 a retains the write command entry for the rewriting of the data after the precharge command. - The
memory device 200 a may execute at least one read or write command after the precharge command and before the rewriting of the data. For example, after the precharge command and before the rewriting of the data, a different command or operation may be performed. - The
memory device 200 a may execute a rewrite command for rewriting the same data as that written before without intervention of thememory controller 100 a. While writing data to a memory cell in response to a write command stored in thewrite queue 270, thememory device 200 a may send a state signal WT indicating “under a write operation” to thememory controller 100 a. The state signal WT is transmitted using a separate signal line between thememory controller 100 a and thememory device 200 a. For example, a special signal line for the state signal WT is provided between thememory controller 100 a and thememory device 200 a. Alternatively, the state signal WT may be transmitted using one of the existing signal lines. Thememory controller 100 a accesses thememory device 200 a based on the state signal WT output from thememory device 200 a. -
FIG. 11 is a block diagram of a memory system according to an exemplary embodiment of the inventive concept. Referring toFIG. 11 , the memory system includes amemory controller 100 b and amemory device 200 b. Thememory device 200 b includes anevent detector 280. The structure of thememory controller 100 b may be similar to that of thememory controller 100 illustrated inFIG. 2 . For example, thememory device 200 b includes theevent detector 280 in addition to the structure of thememory device 200 illustrated inFIG. 3 . - The
event detector 280 detects whether a precharge command is performed on a page after a write command is executed on the page. Hereafter, the page is interchangeably used as an enabled wordline. At this time, theevent detector 280 sends an alarm signal AT to thememory controller 100 b. The alarm signal AT informs thememory controller 100 b that the write command has not been properly executed. Upon receiving the alarm signal AT from thememory device 200 b, thememory controller 100 b considers that an operation (e.g., a write operation right before precharge) corresponding to the alarm signal AT has not been performed and performs the operation thereafter. - According to the embodiment illustrated in
FIG. 11 , thememory controller 100 b may apply a rewrite command to thememory device 200 b in response to the alarm signal AT received from thememory device 200 b so that relevant data is rewritten. - The alarm signal AT is transmitted using a separate signal line between the
memory controller 100 b and thememory device 200 b. For example, a special signal line for the alarm signal AT is provided between thememory controller 100 b and thememory device 200 b. Alternatively, the alarm signal AT may be transmitted using one of the existing signal lines. -
FIGS. 12A through 12C are diagrams for explaining a method of scheduling a write operation according to an exemplary embodiment of the inventive concept. According to an exemplary embodiment, a memory system schedules write operations using a write queue to reduce the number of active and precharge commands and improve performance of a memory system. - A write queue may be included within the
memory controller 100 or thememory device 200, as described above. It is assumed that there are write commands A through H as shown inFIG. 12A . As shown inFIG. 12A , each of the write commands A through H includes a bank address BA, a row address RA and a column address CA. Each of the write commands A through H is for writing data to a certain address. - When the write commands A through H are stored in the write queue, the
memory controller 100 may schedule them so that they are sequentially executed as shown inFIG. 12B . - Alternatively, the
memory controller 100 may schedule them referring to address information as shown inFIG. 12C . For instance, the write commands A through H may be scheduled so that write commands having the same row address RA may be executed sequentially. Referring toFIG. 12C , after the write command A is executed, the write commands C, E, and G having the same row address RA as the write command A may be scheduled to be sequentially executed. Thereafter, the write command B is executed and then write commands D, F, and H having the same row address RA as the write command B may be scheduled to be sequentially executed. - In
FIGS. 12B and 12C , tRP denotes a precharge command period or a precharge-to-active delay, tRRD denotes an active-to-active command period, tAA denotes an internal read command-to-first data delay, tCCD denotes a write-to-write delay, and tRCD denotes an active-to-internal read delay or an active-to-write delay. - As illustrated in
FIGS. 12B and 12C , a total execution time is much longer in a case shown inFIG. 12B than in a case shown inFIG. 12C . Consequently, the total execution time can be reduced by the schedule of a plurality of write commands. -
FIG. 13 is a diagram for explaining a method of scheduling a write operation according to an exemplary embodiment of the inventive concept. According to an exemplary embodiment, write commands having the same bank address BA and the same row address RA are sequentially executed. When no addresses include the same bank address BA and the same row address RA, write commands having the same bank address BA are sequentially executed. - When the operations of a memory device (e.g., DRAM) are scheduled according to the above-described priority, a case where write commands having the same bank address BA but different row addresses RA are sequentially executed may be prevented. As a result, the deterioration of system performance is prevented.
-
FIG. 14 is a block diagram of amodule 500 including a plurality of memory devices 550-1 through 550-4 according to an exemplary embodiment of the inventive concept. Referring toFIG. 14 , themodule 500 includes amemory controller 510, an input/output (IO)interface 511, and the memory devices 550-1 through 550-4. Thememory controller 510 and theI0 interface 511 are disposed between a host and the memory devices 550-1 through 550-4, communicating with the host. - In an exemplary embodiment, the
memory controller 510 and theIO interface 511 may be integrated in a single chip. Each of the memory devices 550-1 through 550-4 may communicate data with the host through the integrated chip. - The
IO interface 511 may include an optical interface. In this case, theIO interface 511 may include an IO controller (not shown) controlling the input and output operations of the memory devices 550-1 through 550-4 and a signal converter (not shown) converting an input or output signal into an optical signal. - The
IO interface 511 may transfer data using an optical fiber or a waveguide. The data is suitable for the transmission of high-speed signals, for example, complying with serial advantage technology attachment (SATA) standards and may be transmitted using wavelength division multiplexing (WDM). -
FIG. 15 is a block diagram of amodule 600 including a plurality of memory devices 610-1 through 610-5 according to an exemplary embodiment of the inventive concept. One (e.g., 610-3) of the memory devices 610-1 through 610-5 is directly connected to and communicates with amemory controller 620. The memory devices 610-1 through 610-5 may be serially connected in a chain with one other. The memory devices 610-1, 610-2, 610-4, and 610-5 that are not directly connected to thememory controller 620 communicate with a host indirectly through the chain. - In an exemplary embodiment, the
memory controller 620 controlling the operation of the memory devices 610-1 through 610-5 may implemented within themodule 600 or may be stacked on the memory devices 610-1 through 610-5. -
FIG. 16 is a block diagram of adata processing system 800 including the memory device illustrated inFIG. 1 according to an exemplary embodiment of the inventive concept. - The
data processing system 800 may be implemented as a personal computer (PC), a tablet PC, a net-book, an e-reader, a personal digital assistant (PDA), a portable multimedia player (PMP), an MP3 player, or an MP4 player. - The
data processing system 800 includes thememory device 840 and amemory controller 850 controlling the data processing operations of thememory device 840. - The
memory controller 850 may correspond to thememory controller memory device 840 may correspond to thememory device - A
processor 820 may display data stored in thememory device 840 through adisplay 810 according to data input through aninput device 830. Theinput device 830 may be implemented by a pointing device such as a touch pad or a computer mouse, a keypad, or a keyboard. - The
processor 820 may control the overall operation of thedata processing system 800 and the operations of thememory controller 850. -
FIG. 17 is a block diagram of adata processing system 900 including thememory device 950 illustrated inFIG. 1 according to an exemplary embodiment of the inventive concept. Referring toFIG. 17 , thedata processing system 900 may be implemented as a cellular phone, a smart phone, a tablet personal computer (PC), a personal digital assistant (PDA) or a radio communication system. - The
data processing system 900 includes thememory device 950 and amemory controller 960 controlling the operations of thememory device 950. Thememory controller 960 may control the data access operations, e.g., a write operation, and a read operation, of thememory device 950 according to the control of aprocessor 940. - The data stored in the
memory device 950 may be displayed through adisplay 930 according to the control of theprocessor 940 and/or thememory controller 960. - A
radio transceiver 910 transmits or receives radio signals through an antenna ANT. Theradio transceiver 910 may convert radio signals received through the antenna ANT into signals that are processed by theprocessor 940. Accordingly, theprocessor 940 may process the signals output from theradio transceiver 910 and may transmit the processed signals to thememory controller 960 or thedisplay 930. Thememory controller 960 may transmit the signals processed by theprocessor 940 to thememory device 950. Theradio transceiver 910 may also convert signals output from theprocessor 940 into radio signals and may output the radio signals to an external device through the antenna ANT. - An
input device 920 enables control signals for controlling the operation of theprocessor 940 or data to be processed by theprocessor 940 to be input to thedata processing system 900. Theinput device 920 may be implemented by a pointing device such as a touch pad or a computer mouse, a keypad, or a keyboard. - The
processor 940 may control the operation of thedisplay 930 to display data output from thememory controller 960, data output from theradio transceiver 910, or data output from theinput device 920. - The
memory controller 960 may correspond to thememory controller memory device 950 may correspond to thememory device -
FIG. 18 is a block diagram of adata processing system 1000 including the memory device illustrated inFIG. 1 according to an exemplary embodiment of the inventive concept. Thedata processing system 1000 may be implemented as an image processor such as a digital camera, a cellular phone equipped with a digital camera, a smart phone equipped with a digital camera, or a tablet PC equipped with a digital camera. - The
data processing system 1000 includes thememory device 1040 and amemory controller 1050 controlling the data processing operations, such as a write operation, and a read operation, of thememory device 1040. Animage sensor 1010 included in thedata processing system 1000 converts optical images into digital signals and outputs the digital signals to aprocessor 1020 or thememory controller 1050. The digital signals may be controlled by theprocessor 1020 to be displayed through adisplay 1030 or stored in thememory device 1040 through thememory controller 1050. - Data stored in the
memory device 1040 may be displayed through thedisplay 1030 according to the control of theprocessor 1020 or thememory controller 1050. Thememory controller 1050 may control the operations of thememory device 1040. Thememory controller 1050 may correspond to thememory controller memory device 1040 may correspond to thememory device -
FIG. 19 is a diagram of amulti-chip package 1300 including the semiconductor memory device illustrated inFIG. 1 according to an exemplary embodiment of the inventive concept. Referring toFIG. 19 , themulti-chip package 1300 includes a plurality of semiconductor devices, e.g., first throughthird chips package substrate 1310. Each of thesemiconductor devices 1330 through 1350 may include a memory controller and/or a semiconductor memory device according to an exemplary embodiment. A through-silicon via (TSV) (not shown), a bonding wire (not shown), a bump (not shown), or asolder ball 1320 may be used to electrically connect thesemiconductor devices 1330 through 1350 with one other. - The
first semiconductor device 1330 may include a logic device die including an input/output interface and a memory controller and the second andthird semiconductor devices third semiconductor devices second semiconductor device 1340 and a memory device of thethird semiconductor device 1350 may be the same or different types of memory. - Alternatively, each of the first through
third semiconductor devices 1330 through 1350 may include a memory controller. In an exemplary embodiment, the memory controller may be on the same die as a memory cell array or may be on a different die than the memory cell array. - In an exemplary embodiment, the
first semiconductor device 1330 may include an optical interface. A memory controller may be positioned in the first orsecond semiconductor device third semiconductor device - The
multi-chip package 1300 may be implemented using hybrid memory cube (HMC) in which a memory controller and a memory cell array die are stacked. When the HMC is used, the performance of memory devices increases due to the increase of bandwidth and the area of the memory devices is minimized. As a result, power consumption and manufacturing cost may be reduced. -
FIG. 20 is an exemplary three-dimensional conceptual diagram of an example of themulti-chip package 1300 illustrated inFIG. 19 according to an exemplary embodiment of the inventive concept. Referring toFIG. 20 , themulti-chip package 1300′ includes a plurality of the dies 1330 through 1350 connected with one another through TSVs 1360 in a stack structure. Each of the dies 1330 through 1350 may include a plurality of circuit blocks (not shown) and a periphery circuit to realize the functions of thesemiconductor memory device 200. The dies 1330 through 1350 may be referred to as a cell array. The plurality of circuit blocks may be implemented by memory blocks. - The
TSVs 1360 may include a conductive material including a metal such as copper (Cu). TheTSVs 1360 are arranged at the center of a silicon substrate. The silicon substrate surrounds theTSVs 1360. An insulating region (not shown) may be disposed between the TSVs 1360 and the silicon substrate. - The present general inventive concept can also be embodied as computer-readable codes on a computer-readable medium. The computer-readable recording medium is any data storage device that can store data as a program which can be thereafter read by a computer system. Examples of the computer-readable recording medium include read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tapes, floppy disks, and optical data storage devices.
- The computer-readable recording medium can also be distributed over network coupled computer systems so that the computer-readable code is stored and executed in a distributed fashion. Also, functional programs, codes, and code segments to accomplish the present general inventive concept can be easily construed by programmers.
- As described above, according to an exemplary embodiment of the inventive concept, when a write operation of data is not properly performed in a memory device, a rewrite operation of the data is performed, so that write fail problems are prevented.
- Therefore, the probability of write fail in the fine processes of memory devices is reduced. In addition, parameters, such as write recovery time, of memory devices (e.g., DRAM) may be efficiently released, so that the yield of memory devices can be increased with the released parameters.
- While the present inventive concept has been shown and described with reference to exemplary embodiments thereof, it will be apparent to those of ordinary skill in the art that various changes in form and detail may be made therein without departing from the sprit and scope of the inventive concept as defined by the following claims.
Claims (8)
1. A method of writing data to a memory device, the method comprising:
receiving a plurality of write requests and a plurality of data sets from a host;
generating a plurality of write commands and storing the plurality of write commands to a write queue;
applying the plurality of write commands to a memory device between an active command and a precharge command based on a predetermined scheduling method; and
applying a last write command of the plurality of write commands to the memory device after the precharge command is performed.
2. The method of claim 1 , further comprising:
executing at least one read command or at least one write command after applying the precharge command and before applying the last write command.
3. The method of claim 2 ,
wherein the predetermined scheduling method determines a priority among the plurality of write commands based on a bank address and a row address.
4. The method of claim 1 , further comprising:
removing a write command executed from the plurality of write command stored in the write queue,
wherein the last write command is retained after the precharge command and is executed after the precharge command.
5. A memory controller, comprising:
an arbiter configured to generate an active command, a precharge command, and a plurality of write commands and configured to issue the plurality of write commands between the active command and the precharge command,
wherein the precharge command is issued after a first write operation is performed in response to a last write command of the plurality of write commands , the last write command is issued for a second write operation after the precharge command, and
wherein the first write operation and the second write operation write a same data set to memory cells of plurality of memory cells.
6. The memory controller of claim 5 , further comprising:
a write queue configured to store the plurality of write commands.
7. The memory controller of claim 5 ,
wherein the data set include a number of data corresponding to a burst length.
8. The memory system of claim 6 ,
wherein the arbiter further configured to:
receive a plurality of write requests from a host;
generate the active command, the plurality of write commands, and the precharge command;
store the plurality of write commands in the write queue; and
schedule the commands stored in the write queue according to a predetermined scheduling algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/096,920 US20160224243A1 (en) | 2012-08-29 | 2016-04-12 | Memory device for reducing a write fail, a system including the same, and a method thereof |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020120095223A KR20140028618A (en) | 2012-08-29 | 2012-08-29 | Memory device for reducimg write fail, system includinmg tha same, and method there-of |
KR10-2012-0095223 | 2012-08-29 | ||
US14/013,275 US9335951B2 (en) | 2012-08-29 | 2013-08-29 | Memory device for reducing a write fail, a system including the same, and a method thereof |
US15/096,920 US20160224243A1 (en) | 2012-08-29 | 2016-04-12 | Memory device for reducing a write fail, a system including the same, and a method thereof |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/013,275 Division US9335951B2 (en) | 2012-08-29 | 2013-08-29 | Memory device for reducing a write fail, a system including the same, and a method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
US20160224243A1 true US20160224243A1 (en) | 2016-08-04 |
Family
ID=50098571
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/013,275 Active 2034-01-28 US9335951B2 (en) | 2012-08-29 | 2013-08-29 | Memory device for reducing a write fail, a system including the same, and a method thereof |
US15/096,920 Abandoned US20160224243A1 (en) | 2012-08-29 | 2016-04-12 | Memory device for reducing a write fail, a system including the same, and a method thereof |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/013,275 Active 2034-01-28 US9335951B2 (en) | 2012-08-29 | 2013-08-29 | Memory device for reducing a write fail, a system including the same, and a method thereof |
Country Status (6)
Country | Link |
---|---|
US (2) | US9335951B2 (en) |
JP (1) | JP2014049135A (en) |
KR (1) | KR20140028618A (en) |
CN (1) | CN103680594B (en) |
DE (1) | DE102013109327A1 (en) |
TW (1) | TW201411642A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10162522B1 (en) * | 2016-09-30 | 2018-12-25 | Cadence Design Systems, Inc. | Architecture of single channel memory controller to support high bandwidth memory of pseudo channel mode or legacy mode |
US10403337B2 (en) | 2017-08-07 | 2019-09-03 | Micron Technology, Inc. | Output driver for multi-level signaling |
US10411704B1 (en) | 2018-03-23 | 2019-09-10 | Micron Technology, Inc. | Output impedance calibration for signaling |
US10425260B2 (en) * | 2017-08-07 | 2019-09-24 | Micron Technology, Inc. | Multi-level signaling in memory with wide system interface |
US10447512B2 (en) | 2017-08-07 | 2019-10-15 | Micron Technology, Inc. | Channel equalization for multi-level signaling |
US10530617B2 (en) | 2017-08-07 | 2020-01-07 | Micron Technology, Inc. | Programmable channel equalization for multi-level signaling |
WO2021231075A1 (en) * | 2020-05-15 | 2021-11-18 | Advanced Micro Devices, Inc. | Refresh management for dram |
WO2021242766A1 (en) * | 2020-05-29 | 2021-12-02 | Advanced Micro Devices, Inc. | Refresh management for dram |
US11606229B2 (en) | 2017-08-07 | 2023-03-14 | Micron Technology, Inc. | Method to vertically align multi-level cell |
Families Citing this family (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9304709B2 (en) | 2013-09-06 | 2016-04-05 | Western Digital Technologies, Inc. | High performance system providing selective merging of dataframe segments in hardware |
KR20150043045A (en) * | 2013-10-14 | 2015-04-22 | 에스케이하이닉스 주식회사 | Semiconductor device |
KR20150056704A (en) * | 2013-11-15 | 2015-05-27 | 에스케이하이닉스 주식회사 | Data storage device and operating method thereof |
US20150286529A1 (en) * | 2014-04-08 | 2015-10-08 | Micron Technology, Inc. | Memory device having controller with local memory |
KR101887797B1 (en) | 2014-05-08 | 2018-09-10 | 마이크론 테크놀로지, 인크. | In-memory lightweight coherency |
US9514802B2 (en) * | 2014-10-27 | 2016-12-06 | Samsung Electronics Co., Ltd. | Volatile memory self-defresh |
TWI621015B (en) * | 2015-09-01 | 2018-04-11 | 慧榮科技股份有限公司 | Methods for scheduling read and write commands and apparatuses using the same |
TWI588652B (en) * | 2015-09-01 | 2017-06-21 | 慧榮科技股份有限公司 | Methods for scheduling read and write commands and apparatuses using the same |
US10025531B2 (en) * | 2015-09-10 | 2018-07-17 | HoneycombData Inc. | Reducing read command latency in storage devices |
CN111176559B (en) * | 2015-12-04 | 2023-07-11 | 成都华为技术有限公司 | Data writing method and device and dual-activity system |
US10380060B2 (en) | 2016-06-17 | 2019-08-13 | Etron Technology, Inc. | Low-pincount high-bandwidth memory and memory bus |
KR20180049502A (en) | 2016-11-03 | 2018-05-11 | 삼성전자주식회사 | Semiconductor memory devices and methods of operating semiconductor memory devices |
KR20180053113A (en) * | 2016-11-11 | 2018-05-21 | 에스케이하이닉스 주식회사 | Memory device |
JP6862951B2 (en) * | 2017-03-15 | 2021-04-21 | 富士通株式会社 | Memory control device, information processing device and memory control method |
KR20200004002A (en) * | 2018-07-03 | 2020-01-13 | 삼성전자주식회사 | Memory device and operation method thereof |
US10692567B2 (en) * | 2018-09-06 | 2020-06-23 | M31 Technology Corporation | Method for assisting memory cell in access operation and operating memory cell, and memory device having assist circuit with predefined assist strength |
KR20200089886A (en) * | 2019-01-18 | 2020-07-28 | 에스케이하이닉스 주식회사 | Data Storage System and Setting Method of Precharge Policy |
KR20210076497A (en) * | 2019-12-16 | 2021-06-24 | 에스케이하이닉스 주식회사 | Storage device and operating method thereof |
US20210303215A1 (en) * | 2020-03-27 | 2021-09-30 | Etron Technology, Inc. | Memory controller, memory, and related memory system |
CN114168495A (en) * | 2020-09-10 | 2022-03-11 | 西部数据技术公司 | Enhanced read-ahead capability for memory devices |
KR20220046211A (en) * | 2020-10-07 | 2022-04-14 | 에스케이하이닉스 주식회사 | Memory controller for controlling resistive memory device and memory system including the same |
US20220229600A1 (en) * | 2021-01-21 | 2022-07-21 | Micron Technology, Inc. | Opportunistic data movement |
US20240004584A1 (en) * | 2022-06-30 | 2024-01-04 | Advanced Micro Devices, Inc. | DRAM Row Management for Processing in Memory |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030217239A1 (en) * | 2002-05-14 | 2003-11-20 | Jeddeloh Joseph M. | Out of order DRAM sequencer |
US20090327623A1 (en) * | 2008-06-30 | 2009-12-31 | Canon Kabushiki Kaisha | Command reorderable memory controller |
US20110099323A1 (en) * | 2009-10-27 | 2011-04-28 | Western Digital Technologies, Inc. | Non-volatile semiconductor memory segregating sequential, random, and system data to reduce garbage collection for page based mapping |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR19990079983A (en) | 1998-04-10 | 1999-11-05 | 김영환 | Queuing Device for Memory Controller |
US6360305B1 (en) * | 1998-12-04 | 2002-03-19 | Advanced Micro Devices, Inc. | Method and apparatus for optimizing memory performance with opportunistic pre-charging |
US6295586B1 (en) | 1998-12-04 | 2001-09-25 | Advanced Micro Devices, Inc. | Queue based memory controller |
CN1452745A (en) | 2000-04-03 | 2003-10-29 | 先进微装置公司 | Bus bridge including memory controller having improved memory request arbitration mechanism |
US6661721B2 (en) * | 2001-12-13 | 2003-12-09 | Infineon Technologies Ag | Systems and methods for executing precharge commands using posted precharge in integrated circuit memory devices with memory banks each including local precharge control circuits |
KR100487522B1 (en) * | 2002-04-01 | 2005-05-03 | 삼성전자주식회사 | Precharge control circuit for controlling write recover time(tWR) according to operating frequency of semiconductor memory device and the method to control write recover time(tWR) |
KR100720260B1 (en) * | 2004-11-15 | 2007-05-22 | 주식회사 하이닉스반도체 | Local input output line precharge circuit of semiconductor memory device |
JP4667092B2 (en) | 2005-03-17 | 2011-04-06 | 富士通株式会社 | Information processing apparatus and data control method in information processing apparatus |
JP2006268734A (en) | 2005-03-25 | 2006-10-05 | Kyocera Mita Corp | Memory access controller |
JP2008015699A (en) | 2006-07-04 | 2008-01-24 | Canon Inc | Memory controller |
US7644248B2 (en) | 2006-09-27 | 2010-01-05 | Intel Corporation | Mechanism to generate logically dedicated read and write channels in a memory controller |
CN100555451C (en) * | 2007-12-26 | 2009-10-28 | 中国航天时代电子公司第七七一研究所 | A kind of self-timing SRAM access control circuit |
JP2009259114A (en) | 2008-04-18 | 2009-11-05 | Toshiba Corp | System semiconductor device |
JP2010003067A (en) | 2008-06-19 | 2010-01-07 | Sony Corp | Memory system, access control method therefor, and computer program |
JP5428687B2 (en) | 2009-09-14 | 2014-02-26 | 株式会社リコー | Memory control device |
US8631214B2 (en) * | 2010-11-03 | 2014-01-14 | Kabushiki Kaisha Toshiba | Memory control circuit, control method therefor, and image processing apparatus |
KR101206238B1 (en) | 2011-02-18 | 2012-11-28 | 삼성중공업 주식회사 | System and method for payment bus fare |
-
2012
- 2012-08-29 KR KR1020120095223A patent/KR20140028618A/en not_active Application Discontinuation
-
2013
- 2013-08-28 DE DE102013109327.2A patent/DE102013109327A1/en active Pending
- 2013-08-29 TW TW102131060A patent/TW201411642A/en unknown
- 2013-08-29 JP JP2013178156A patent/JP2014049135A/en active Pending
- 2013-08-29 CN CN201310384656.3A patent/CN103680594B/en active Active
- 2013-08-29 US US14/013,275 patent/US9335951B2/en active Active
-
2016
- 2016-04-12 US US15/096,920 patent/US20160224243A1/en not_active Abandoned
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030217239A1 (en) * | 2002-05-14 | 2003-11-20 | Jeddeloh Joseph M. | Out of order DRAM sequencer |
US20090327623A1 (en) * | 2008-06-30 | 2009-12-31 | Canon Kabushiki Kaisha | Command reorderable memory controller |
US20110099323A1 (en) * | 2009-10-27 | 2011-04-28 | Western Digital Technologies, Inc. | Non-volatile semiconductor memory segregating sequential, random, and system data to reduce garbage collection for page based mapping |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10162522B1 (en) * | 2016-09-30 | 2018-12-25 | Cadence Design Systems, Inc. | Architecture of single channel memory controller to support high bandwidth memory of pseudo channel mode or legacy mode |
US10985953B2 (en) | 2017-08-07 | 2021-04-20 | Micron Technology, Inc. | Channel equalization for multi-level signaling |
US10686634B2 (en) * | 2017-08-07 | 2020-06-16 | Micron Technology, Inc | Multi-level signaling in memory with wide system interface |
US10425260B2 (en) * | 2017-08-07 | 2019-09-24 | Micron Technology, Inc. | Multi-level signaling in memory with wide system interface |
US10447512B2 (en) | 2017-08-07 | 2019-10-15 | Micron Technology, Inc. | Channel equalization for multi-level signaling |
US11038724B2 (en) | 2017-08-07 | 2021-06-15 | Micron Technology, Inc. | Programmable channel equalization for multi-level signaling |
US10573358B2 (en) | 2017-08-07 | 2020-02-25 | Micron Technology, Inc. | Output driver for multi-level signaling |
US11902060B2 (en) | 2017-08-07 | 2024-02-13 | Micron Technology, Inc. | Programmable channel equalization for multi-level signaling |
US10403337B2 (en) | 2017-08-07 | 2019-09-03 | Micron Technology, Inc. | Output driver for multi-level signaling |
US10530617B2 (en) | 2017-08-07 | 2020-01-07 | Micron Technology, Inc. | Programmable channel equalization for multi-level signaling |
US11606229B2 (en) | 2017-08-07 | 2023-03-14 | Micron Technology, Inc. | Method to vertically align multi-level cell |
US11502881B2 (en) | 2017-08-07 | 2022-11-15 | Micron Technology, Inc. | Channel equalization for multi-level signaling |
US11233681B2 (en) * | 2017-08-07 | 2022-01-25 | Micron Technology, Inc. | Multi-level signaling in memory with wide system interface |
US10411704B1 (en) | 2018-03-23 | 2019-09-10 | Micron Technology, Inc. | Output impedance calibration for signaling |
WO2021231075A1 (en) * | 2020-05-15 | 2021-11-18 | Advanced Micro Devices, Inc. | Refresh management for dram |
WO2021242766A1 (en) * | 2020-05-29 | 2021-12-02 | Advanced Micro Devices, Inc. | Refresh management for dram |
US11561862B2 (en) | 2020-05-29 | 2023-01-24 | Advanced Micro Devices, Inc. | Refresh management for DRAM |
Also Published As
Publication number | Publication date |
---|---|
CN103680594A (en) | 2014-03-26 |
TW201411642A (en) | 2014-03-16 |
US20140068203A1 (en) | 2014-03-06 |
KR20140028618A (en) | 2014-03-10 |
US9335951B2 (en) | 2016-05-10 |
DE102013109327A1 (en) | 2014-03-06 |
JP2014049135A (en) | 2014-03-17 |
CN103680594B (en) | 2018-03-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9335951B2 (en) | Memory device for reducing a write fail, a system including the same, and a method thereof | |
US9767050B2 (en) | Memory systems that adjust an auto-refresh operation responsive to a self-refresh operation history | |
US11282561B2 (en) | Refresh command control for host assist of row hammer mitigation | |
US9607678B2 (en) | Semiconductor memory device and memory system including same | |
US10248340B2 (en) | Semiconductor apparatus, memory module and operation method thereof | |
US20170140810A1 (en) | Memory device and memory system including the same for controlling collision between access operation and refresh operation | |
US10115448B2 (en) | Memory device for refresh and memory system including the same | |
US9257169B2 (en) | Memory device, memory system, and operating methods thereof | |
US9076549B2 (en) | Semiconductor memory device and refresh method thereof | |
US9792978B2 (en) | Semiconductor memory device and memory system including the same | |
US11860803B2 (en) | Memory device including processing circuit, and electronic device including system on chip and memory device | |
US9460766B2 (en) | Memory device, and memory system including the same | |
US8750068B2 (en) | Memory system and refresh control method thereof | |
US9767887B2 (en) | Memory device, memory module including the same, and memory system including the same | |
KR20180060091A (en) | Method of operating memory device and method of operating memory system | |
US20220374168A1 (en) | Memory with memory-initiated command insertion, and associated systems, devices, and methods | |
CN107230500B (en) | Semiconductor system including replacement storage unit | |
US9384796B2 (en) | Semiconductor memory device and memory system including the same | |
KR102458340B1 (en) | A memory device | |
CN114974330A (en) | Semiconductor memory device and column path control circuit of semiconductor memory device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |