Abstract: A non-volatile semiconductor memory includes a memory array, a selecting device selecting a page according to addresses, a data storage device, storing page data, and an output device outputting the stored data. The data storage device includes a first data storage device receiving data from a selected page of the memory array, a second data storage device receiving data from the first data storage device, and a data transmission device configured between the first and the second data storage device. The data transmission device transmits data in a second part of the first data storage device to the second data storage device when data in a first part of the second data storage device is output, and transmits data in a first part of the first data storage device to the second data storage device when data in a second part of the second data storage device is output.

Abstract: A phase-change memory includes a phase to provide an upper row address from a row address buffer, a phase to combine the upper row address with a lower row address to select data for a row data buffer, and a phase to output the data from the row data buffer, where an activate command starts and following activate commands are ignored until a preset time has elapsed.

Abstract: A sensor read/write circuit having a sensor, an integrator, a pulse generator, at least a first and second memory device, and a counter. The sensor senses a parameter and produces a sensor output representative of the sensed parameter. The sensor output is provided to the integrator which produces an integrated output representative of the sensed parameter. The integrated output triggers the pulse generator to produce a pulse which causes the first memory device to be written. The above sequence is repeated whereby a new sensor reading is generated and a second pulse causes the second memory device to be written but only if the first memory device has been substantially completely written, the first memory device has been subsequently disabled and the second memory device has been enabled.

Abstract: A data processing system having a data processing core and integrated pipelined array data processor and a buffer for storing list of algorithms for processing by the pipelined array data processor.

Abstract: This nonvolatile semiconductor memory device comprises a memory cell array configured having a plurality of memory mats arranged therein, each of the memory mats having a memory cell disposed therein at an intersection of a first line and a second line, the memory cell including a first variable resistance element. A third line extends through a plurality of the memory mats. A second variable resistance element is connected between the third line and the second line of each of the plurality of memory mats.

Abstract: Dual-voltage domain memory buffers, and related systems and methods are disclosed. To reduce area needed for voltage level shifters for voltage level shifting, latch banks are provided in a voltage domain of memory buffer read circuitry, separate from the voltage domain of a write data input to the latch banks. A write data input voltage level shifter is disposed between the write data input and the latch banks to voltage level shift write data on the write data input to the voltage domain of the latch banks. In this manner, voltage level shifters are not required to voltage level shill the latch bank outputs, because the latch banks are in the voltage domain of the memory buffer read circuitry. In this manner, semiconductor area that would otherwise be needed for the voltage level shifters to voltage level shift latch bank outputs is not required.

Abstract: An integrated includes a dual port memory cell such as a SRAM cell. A first port dummy read recovery block couples the first port complementary bit line to a high voltage supply node during a write logic low operation to the data node through the second port bit line, and couples the first port bit line to a high voltage supply node during a write logic low operation to the complementary data node through the second port complementary bit line. A second port dummy read recovery block couples the second port complementary bit line to a high voltage supply node during a write logic low operation to the data node through the first port bit line, and couples the second port bit line to a high voltage supply node during a write logic low operation to the complementary data node through the first port complementary bit line.

Abstract: An adaptive body bias (ABB) circuit and a semiconductor integrated circuit (IC) having the ABB circuit include: a logic circuit performing logic calculations, a clock line through which a clock signal is transmitted to the logic circuit, and at least one bias line through which a bias voltage is applied to the logic circuit, wherein the bias voltage is applied to a body of a metal oxide semiconductor (MOS) transistor constituting the logic circuit, and the bias line is arranged at a predetermined distance from the clock line to shield the clock signal from crosstalk due to other adjacent signal lines.

Abstract: In some embodiments, detecting resistance in a resistive memory cell may be done using a pulse edge. For example, a pulse may be applied through a resistive memory data cell and another through a reference delay circuit to determine which path has the larger delay in order to determine the resistive state of the data cell in question.

Abstract: A memory device includes an array of memory cells arranged into a plurality of rows and columns and having a plurality of word lines and a plurality of bit lines passing through the array. The memory cells in each row are activated via a word line signal on the corresponding word line, and the memory cells in each column are coupled to an associated bit line pair via which data is written into an activated memory cell of the column during a write operation and data is read from the activated memory cell of the column during a read operation. A dummy column of dummy memory cells is provided and includes a plurality of loading dummy memory cells for providing a load to the at least one dummy bit line, and at least one write timing dummy memory cell coupled to a dummy word line.

Abstract: Disclosed is a read timing generation circuit, capable of reducing dynamic power consumption. After a multi-bit address Add1, Add2, . . . , and AddN passes through an address change monitoring unit (100), a response pulse signal corresponding the address is generated. After the response pulse signal passes through an address trigger determination unit (200), a single trigger determination signal ATDPRE is generated. The single trigger determination signal ATDPRE passes through an ATD timing generation unit (300) and a post-timing generation unit (1000), thereby forming a read timing generation circuit in a serial link and generating corresponding read timing. Compared with the conventional read timing generation circuit in which each bit of an address signal corresponds to a stage of structures to execute the trigger, ATD control timing output, and ATD determination process separately, the present invention greatly reduces the total dynamic power consumption of the circuit.

Abstract: A signal control device includes: a dual port RAM from or to which data signals are read and written at predetermined operation timings by first and second CPUs connected to two ports, respectively; an address collision detection unit detecting collision between addresses in which the first and second CPUs respectively read and write the data signal from and to the dual port RAM; a first storage unit storing the data signal read by the first CPU; a second storage unit storing the data signal read from the address in which the second CPU writes the data signal to the dual port RAM when the collision between the addresses is detected; and a switching unit switching a reading source outputting the data signal to the port to which the first CPU is connected and outputting the read data signal to the first CPU entering a readable state.

Abstract: Methods of operating a memory device include determining whether each memory cell selected for a sense operation has any data state of a first subset of data states of a plurality of data states, wherein whether a memory cell has a data state that is a member of the first subset of data states determines a data value of a first portion of the data state of that memory cell. The methods further include initiating a transfer of the data values of the first portions of the data states of the selected memory cells and continuing the particular sense operation to sense for additional data states of the plurality of data states.

Abstract: A memory includes an array of memory cells including a plurality of memory cells with a common source, wherein each of the plurality of memory cells with a common source includes two sub-memory cells, each of the sub-memory cells corresponds to a bit line, and the respective bits are electrically independent. Each of the sub-memory cells in the memory according to the disclosure corresponds to a bit line, and the respective bit lines are electrically independent, thereby effectively avoiding interference to other memory cells which will not be programmed during a program operation.

Abstract: A volatile memory includes volatile memory cells in which data write and read operations are performed. The memory cells are arranged in rows and in columns and are distributed in first separate groups of memory cells for each column. The memory includes, for each column, a write bit line dedicated to write operations and connected to all the memory cells of the column and read bit lines dedicated to read operations. Each read bit line is connected to all the memory cells of one of the first groups of memory cells. Each memory cell in the column is connected to a single one of the read bit lines.

Abstract: A memory array includes a number of word lines, with each word line coupled to a word line driver for memory write operations and a word line driver for memory read operations. A decode stage includes write logic for each word line and read logic for each word line. A word line driver stage includes a write word line driver and a read word line driver. The write logic for at least one world line is configured to enable the write word line driver for a memory write operation of the word line while prohibiting the read word line logic from enabling the read word line driver for a memory read operation of the word line.

Abstract: Provided is a semiconductor memory device in which a plurality of first and second data lines coupled to a memory cell array are alternately arranged. The semiconductor memory device includes a first write driving circuit configured to load a plurality of first write data transmitted through a plurality of third data lines into the plurality of first data lines in response to a first write enable signal; a second write driving circuit configured to load a plurality of second write data transmitted through a plurality of fourth data lines into the plurality of second data lines in response to a second write enable signal; and a column control circuit configured to activate at least one of the first and second write enable signals during a given period, in response to a plurality of data width option modes, during a parallel test mode.

Abstract: Subject matter disclosed herein relates to methods and apparatus, such as memory devices and systems including such memory devices. In one apparatus example, a plurality of block configurations may be employed. Block configurations may include an arrangement of similarly doped semiconductor switches. Block configurations may select a respective tile of a memory array, a particular memory cell of the respective tile, and select a memory operation to apply to the particular memory cell. Immediately adjacent block configurations within a particular slice of the memory array may be substantially mirrored and immediately adjacent block configurations in separate immediately adjacent slices of the memory array may be substantially similar. Similarly doped diffusion regions for similarly doped semiconductor switches in substantially mirrored block configurations may be arranged to electrically share a common potential signal value level. Other apparatus and methods are also disclosed.

Abstract: A method of avoiding a write collision in single port memory devices from two or more independent write operations is described. A first write operation having a first even data object and a first odd data object is received from a first data sender. A second write operation having a second even data object and a second odd data object is received from a second data sender at substantially the same time as the first write operation. The second write operation is delayed so that the first even data object writes to a first single port memory device at a different time than the second even data object writes to the first single port memory device. The second write operation is delayed so that the first odd data object writes to a second single port memory device at a different time than the second odd data object.

Abstract: Embodiments of the present invention provide a method and a device for writing data. The method includes: receiving a data block that is to be written in an EDRAM; obtaining, according to a status of a bank in the EDRAM, usable addresses corresponding to usable banks in the EDRAM; selecting an address from the usable addresses as a write-in address of the data block; and writing the data block in a bank corresponding to the write-in address. In the embodiments of the present invention, problems in the prior art that a conflict occurs when a data block is written in a bank and a conflict occurs when a data block is read from a bank can be avoided, and working efficiency of the EDRAM is improved.

Abstract: A semiconductor device includes: a plurality of target lines to be driven; a plurality of target line drivers configured to drive the corresponding target lines in a logic level corresponding to a plurality of target line selection signals; a plurality of booster enable units configured to generate a booster enable signal by sensing whether a group of target lines that is obtained by grouping the target lines by a predetermined number is enabled or not; and a plurality of self-boosters configured to boost corresponding target lines by sensing levels of the corresponding target lines in response to the booster enable signal.

Abstract: A semiconductor memory comprises a dual-port memory array having a plurality of cross-access dual-port bit cells arranged in a plurality of rows and a plurality of columns, wherein each of the plurality of cross-access dual-port bit cells has two cross-access ports for read and write of one or more bits of data to the cross-access dual port bit cell. The semiconductor memory further comprises a pair of word lines associated with at least one of the plurality of rows of the dual-port memory array, wherein the pair of word lines is configured to carry a pair of row selection signals for enabling one or more read and write operations on one or more cross-access dual-port bit cells in the row.

Abstract: In accordance with an embodiment of the disclosure, systems and methods are provided for reducing an amount of peak power consumption in a device. In certain implementations, a first signal and a second signal are received, wherein the first signal and the second signal are indicative of amounts of power consumption in a device. The first signal is combined with the second signal to generate a combined signal, and at least a portion of the second signal is shifted in time to cause a combination of the first signal and the shifted portion to have a peak amplitude less than a peak amplitude of the combined signal.

Abstract: Apparatus and methods of increasing the data rate and bandwidth of system memory including stacked memory device dice. The system memory includes a memory device having a plurality of memory device dice in a stacked configuration, a memory controller coupled to the stacked memory device dice, and a partitioned data bus. The memory device dice each include one, two, or more groups of memory banks. By configuring each memory device die to deliver all of its bandwidth over a different single partition of the data channel, the system memory can achieve an increased data rate and bandwidth without significantly increasing costs over typical system memory configurations that include stacked memory device dice.

Abstract: A method according to one embodiment includes determining to move an extent from a source-tier in a storage system to a destination-tier in the storage system; determining whether any track from the set of tracks is presently being written to; designating to a write-stack associated with the source-tier each track that is presently being written to and designating to a read-stack associated with the source-tier remaining tracks from the set of tracks; removing oldest tracks from the read-stack and the write-stack until the read-stack and the write-stack have been depleted of tracks; when a parameter of the extent exceeds a migration threshold: populating a destination-tier cache with the tracks as they are removed from the read-stack and the write-stack using a predetermined read-to-write ratio and removing tracks from a source-tier cache that were removed from the read-stack and the write-stack; and migrating the extent from the source-tier to the destination-tier.

Abstract: A write is performed to a first cell of a memory at a first row and column during a first memory access cycle. A memory access operation is made to a second cell at a second row and column during an immediately following second memory access cycle. If the memory access is a read from the second cell and the second row is the same as the first row, or if the memory access is a write to the second cell and the second row is the same as the first row and the second column is different than the first column, then a simultaneous operation is performed during the second memory access cycle. The simultaneous operation is an access of the second cell (for read or write) and a re-write of data from the first memory access cycle write operation back to the first cell.

Abstract: A method for testing a memory device includes entering a test mode in which multiple memory banks operate in a same manner, allowing a row corresponding to a row address in the multiple memory banks to be activated, latching a bank address and the row address corresponding to the multiple memory banks, writing same data in a column selected by a column address in the multiple memory banks, reading the data written in the writing of the data from the multiple memory banks, checking whether the data read from the multiple memory banks in the reading of the data are equal to each other, and programming the row address to locations designated by the bank address latched in the latching in a nonvolatile memory when the data read from the multiple memory banks are different from each other.

Abstract: A multi-port memory cell is disclosed that includes first and second cross-coupled inverter circuits. The input node of each inverter circuit is coupled to the output node of the other inverter circuit to receive the inverted output of the other inverter circuit. The multi-port memory cell includes a first pair of access transistors of a first type, each coupled to the input node of a respective one of the first and second inverter circuits. The multi-port memory cell also includes a second pair of access transistors of the second type, each coupled to the input of a respective one of the first and second inverter circuits. The multi-port cell exhibits advantages in layout compactness and SEU tolerance.

Abstract: A disk drive including a disk configured to spin at a target spin speed, a servo core configured to access the disk, a first non-volatile memory configured to store a first initialization firmware, a second non-volatile memory configured to store a second initialization firmware, a first volatile memory, a second volatile memory, a non-volatile memory core configured to access the first non-volatile memory, and a main core. The main core is configured to load the second initialization firmware from the second non-volatile memory to the second volatile memory concurrently with the loading of the first initialization firmware from the first non-volatile memory to the first volatile memory by the non-volatile memory core, control the servo core to initiate spinning of the disk, and communicate with the non-volatile memory core to service host commands from the first non-volatile memory when the disk is not spinning at the target spin speed.

Abstract: Static random access memory (SRAM) circuits are used in most digital integrated circuits to store data. To handle multiple memory users, an efficient dual port six transistor (6T) SRAM memory cell is proposed. The dual port 6T SRAM cell uses independent word lines and bit lines such that the true side and the false side of the SRAM cell may be accessed independently. Single-ended reads allow the two independent word lines and bit lines to handle two reads in a single cycle using spatial domain multiplexing. Writes can be handled faster that read operations such that two writes can be handled in a single cycle using time division multiplexing. To further improve the operation of the dual port 6T SRAM cell a number of algorithmic techniques are used to improve the operation of the memory system.

Abstract: A memory system includes a memory array and a read/write module. The memory array includes bit lines, word lines, and memory cells. Each of the memory cells is located at an intersection of a respective one of the bit lines and a respective one of the word lines. The memory cells include a first memory cell and a second memory cell. The first memory cell is located at the intersection of a first bit line of the bit lines and a first word line of the word lines. The second memory cell is located at the intersection of a second bit line of the bit lines and a second word line of the word lines. The read/write module is configured to concurrently activate the first memory cell and the second memory cell to simultaneously access both the first memory cell and the second memory cell.

Abstract: In various embodiments an integrated circuit or chip is provided, the integrated circuit including a memory device including a plurality of memory cells, and with the memory cells being configured to store a data content, and a controller being configured to write a predefined data pattern in the memory cells of the memory device, reading the data content of the memory cells, mapping each read data content which corresponds to an expected data content depending on the predefined data pattern to a predefined instruction for the controller, with the predefined instruction causing the controller to carry out a predefined action which is representative for the accurate operation of the memory cells, determining that the memory device operates accurately, if the controller carries out the predefined action, and determining that the memory device does not operate accurately, if the controller does not carry out the predefined action.

Abstract: A non-volatile memory device capable of reading and writing a large number of memory cells with multiple read/write circuits in parallel has an architecture that reduces redundancy in the multiple read/write circuits to a minimum. The multiple read/write circuits are organized into a bank of similar stacks of components. Redundant circuits such as a processor for processing data among stacks each associated with multiple memory cells are factored out. The processor is implemented with an input logic, a latch and an output logic. The input logic can transform the data received from either the sense amplifier or the data latches. The output logic further processes the transformed data to send to either the sense amplifier or the data latches or to a controller. This provides an infrastructure with maximum versatility and a minimum of components for sophisticated processing of the data sensed and the data to be input or output.

Abstract: A method for testing a memory device includes entering a test mode in which multiple memory banks operate in a same manner, allowing a row corresponding to a row address in the multiple memory banks to be activated, latching a bank address and the row address corresponding to the multiple memory banks, writing same data in a column selected by a column address in the multiple memory banks, reading the data written in the writing of the data from the multiple memory banks, checking whether the data read from the multiple memory banks in the reading of the data are equal to each other, and programming the bank address and the row address to a nonvolatile memory when the data read from the multiple memory banks are different from each other.

Abstract: An integrated circuit with memory elements is provided. The memory elements may be single-port memory cells that are used to provide multiport memory functionality. The integrated circuit may include an arbitration circuit operable to receive memory access requests from at least first and second request generators. The arbitration circuit may be configured to operate in a synchronous mode and an asynchronous mode. The arbitration circuit operating in the synchronous mode may perform port selection based on a predetermined logic table. The arbitration circuit operating in the asynchronous mode may execute a memory request as soon as it is received by the arbitration circuit. Requests received while a current memory access is being performed may be put on hold until the current memory access has been completed.

Abstract: A system and method to read and write data at a memory cell that includes multiple non-volatile memories is disclosed. In a particular embodiment, a memory device includes a plurality of memory cells. At least one of the memory cells includes a first non-volatile memory including a first resistive memory element and a second multi-port non-volatile memory including a second resistive memory element. Each of the first non-volatile memory and the second non-volatile memory is accessible via multiple ports.

Abstract: A device and a method for controlling an SRAM-type device, including: a bistable circuit and two switching circuits respectively connecting two access terminals of the bistable circuit to two complementary bit lines in a first direction, each switching circuit including a first switch and a second switch in series between one of the bit lines and one of the access terminals, the control terminal of the second switch being connected to a word control line in the first direction; and a third switch between the midpoint of the series connection and a terminal of application of a reference potential, a control terminal of the third switch being connected to the other one of the access terminals.

Abstract: A memory apparatus includes a plurality of memory arrays, each memory array including a plurality of memory cells. The apparatus includes a plurality of global bit lines and each one of the global bit lines is connected to a plurality of local bit lines, which are in turn connected to a plurality of memory cells. The apparatus includes a plurality of global bit line (GBL) latches and each GBL latch is located along a separate global bit line to latch a signal along the respective global bit line. The apparatus further includes a plurality of solar bit lines configured to connect the global bit lines to an output latch via a plurality of logic gates.

Abstract: A memory cluster includes a first block, a second block, a third block, and a fourth block arranged to have a center hole, wherein the first, second, third, and fourth blocks are each have a first port, a second port, a third port, and a fourth port. A first core is in the center hole coupled to the first port of each of the first, second, third, and fourth blocks. A second core is in the center hole coupled to the second port of each of the first, second, third, and fourth blocks. A third core is in the center hole coupled to the third port of each of the first, second, third, and fourth blocks. A fourth core in the center hole coupled to the fourth port of each of the first, second, third, and fourth blocks.

Abstract: A method and apparatus for controlling writing of data to a graphic memory is provided. In the method and apparatus, a plurality of consecutively input data pieces are controlled to be not consecutively written to the same memory area in terms of time or space.

Abstract: To produce a memory which resists ion or photon attack, a memory structure is chosen whose memory point behaves asymmetrically with regard to these attacks. It is shown that in this case, it is sufficient to have a reference cell for an identical and periodic storage structure in order to be able to correct all the memory cells assailed by an attack. An error correction efficiency of ½ is thus obtained, with a simple redundancy, whereas the conventional methods make provision, for the same result, to triple the storage, to obtain a less beneficial efficiency of ?.

Abstract: A method of operating a multiport memory, which has first and second sets of word lines and bit lines for accessing a memory array, uses a first port and a second port for accesses during a first phase of a master clock and a third port and a fourth port during a second phase of the master clock. Each port has its own port clock, which clocks their own row and column addresses, that is no faster than the master clock. Assuming there is demand for it, four accesses occur for each cycle of the master clock. This has the effect of being able to be sure that a given access is complete within two cycles of the port clocks and can be operated at the rate of one access per cycle of the port clock.

Abstract: A nonvolatile semiconductor memory device includes a cell array including plural MATs (unit cell arrays) arranged in matrix, each MAT containing a plurality of first lines, a plurality of second lines intersecting the plurality of first lines, and a plurality of memory cells connected at intersections of the first and second lines between both lines, each memory cell containing an electrically erasable programmable variable resistive element of which resistance is nonvolatilely stored as data; and a plurality of write/erase circuits connected to the MATs and operative to execute data write or erase to the memory cells inside the MATs in accordance with input data. A part of the plurality of write/erase circuits writes data to memory cells inside a corresponding MAT while another part of the plurality of write/erase circuits erases data from memory cells inside a corresponding MAT at the same time.

Abstract: A method includes selecting a word line for programming in an array of analog memory cells that are arranged in rows associated with respective word lines and columns associated with respective bit lines. Word-line voltages, which program the memory cells in the selected word line, are applied to the respective word lines. Bit-line voltages, which cause one or more additional memory cells outside the selected word line to be programmed as a result of programming the selected word line, are applied to the respective bit lines. Using the applied word-line and bit-line voltages, data is stored in the memory cells in the selected word line and the additional memory cells are simultaneously programmed.

Abstract: Disclosed herein is a semiconductor device having first and second operation modes. In the first operation mode, the semiconductor device deactivates a DLL circuit during a self-refresh mode. In the second operation mode, the semiconductor device intermittently activates the DLL circuit to generate an internal clock signal.

Abstract: Systems and methods are provided for perform device selection in multi-chip package NAND flash memory systems. In some embodiments, the memory controller performs device selection by command. In other embodiments, the memory controller performs device selection by input address.

Abstract: According to one embodiment, the semiconductor memory includes a memory cell array which includes memory cells to store data, a buffer circuit which includes latches, each of the latches including transistors as control elements and a flip-flop, and a control circuit which turns off the transistors to deactivate one or more of the latches.

Abstract: A memory system includes a memory array and a read/write module. The memory array includes bit lines, word lines, and memory cells. Each of the memory cells is located at an intersection of a respective one of the bit lines and a respective one of the word lines. The memory cells include a first memory cell and a second memory cell. The first memory cell is located at the intersection of a first bit line of the bit lines and a first word line of the word lines. The second memory cell is located at the intersection of a second bit line of the bit lines and a second word line of the word lines. The read/write module is configured to concurrently activate the first memory cell and the second memory cell to simultaneously access both the first memory cell and the second memory cell.

Abstract: A device includes a semiconductor substrate, a first penetrating electrode penetrating through the semiconductor substrate, a first test pad, and a first tri-state buffer coupled between the first penetrating electrode and the first test pad. The first tri-state buffer receives a buffer control signal at a control terminal thereof. The device further includes a buffer control circuit supplying the buffer control signal to the first tri-state buffer.

Abstract: A semiconductor integrated circuit device with reduced consumption current is provided. A first step-down circuit stationarily forms internal voltage lower than supply voltage supplied through an external terminal. A second step-down circuit is switched between first mode and second mode according to control signals. In first mode, the internal voltage is formed from the supply voltage supplied through the external terminal and is outputted through a second output terminal. In second mode, operating current for a control system that forms the internal voltage is interrupted and an output high impedance state is established. The first output terminal of the first step-down circuit and the second output terminal of the second step-down circuit are connected in common, and the internal voltage is supplied to internal circuits.