Abstract: A memory device includes 4 memory banks each of which includes first and second arrays of memory cells. A mode register is programmed with a bit that selects a high-power, large-page operating mode or a low-power, small-page operating mode. In the high-power mode, a row decoder is coupled to the row lines in both the first and second arrays. In the low-power mode, the row decoder is coupled to the row lines in only one of the arrays as determined by the state of an array select signal. The array select signal corresponds to the most significant bit of the column address, but it is applied to the memory device at the time the row address is applied to the memory device. Sense amplifiers coupled to the first and second arrays may also be selectively enabled when the row lines for the corresponding array are coupled to the row decoder.

Abstract: A single flash memory device has selectable read modes for either a segment mode or a page mode. The desired mode is selected by writing a control word to a mode control register. Selecting the segment mode causes the device to output selected memory segments. Selecting the page mode causes the device to output selected memory pages.

Abstract: A semiconductor intergrated circuit device is comprised a main portion composed of a plurality of memory cells arranged in a plurality of rows and in a plurality of columns, a sub memory portion composed of a plurality of memory cells arranged in a plurality of rows and in a plurality of columns, a bi-directional data transfer circuit for connecting the main memory portion and the sub memory portion through data transfer bus lines, respectively, the sub memory portion being constituted with a plurality of memory cell groups, and a plurality of registers provided such that different data input/output modes are set independently for the plurality of the memory cell groups. Therefore, the semiconductor integrated circuit device of the present invention has a main memory suitable for being accessed from a plurality of data processors.

Abstract: A memory IC card including a card substrate, a semiconductor device mounted on the card substrate, which includes an CPU, a flash memory, a memory block and a flash memory rewrite circuit having a rewrite data control circuit that receives a rewrite instruction of the flash memory from the CPU to store data for a designated byte of a page for rewriting to the memory block, a page data control circuit that sends data of the page excepting the designated byte in the flash memory to the memory block to prepare new page data in the memory block and a data set control circuit that writes the new page data prepared in the memory block to the flash memory; outer terminals mounted on the card substrate; wirings provided on the card substrate to connect the outer terminals.

Abstract: A flash memory has erase blocks aligned primarily with array rows and secondarily with array rows. This architecture allows data to be stored across numerous pages without risking accidental erasure caused by crossing multiple erase blocks. As a result, non-volatile memory devices to be more easily substituted for volatile memory devices. In one embodiment, a flash memory includes an array of memory cells that have a plurality of adjacent pages. Addresses of the memory cells are scrambled within the pages to define erase blocks that cross the page boundaries.

Abstract: Methods for enhancing the efficiency of SDRAM include dividing all of the data blocks into at least two parts and storing each part in a different bank of memory. Specifically, the first part of each data block is stored in the first bank of memory and subsequent parts are stored in other banks. Since every data block begins in one bank and ends in another bank, no memory bank is ever accessed twice consecutively. In this manner it is always possible to perform precharge and row activation for the next data access while finishing the present data access. The methods of the invention are illustrated in conjunction with the storage and retrieval of ATM cells.

Abstract: A FLASH memory erasable by page includes a flash memory array containing a plurality of floating gate transistors arranged in pages, and a checking circuit for checking the threshold voltages of the floating gate transistors. Programmed transistors that have a threshold voltage less than a given threshold are reprogrammed. The checking circuit includes a non-volatile counter formed by at least one row of floating gate transistors, a reading circuit for reading the address of a page to be checked in the counter, and an incrementing circuit for incrementing the counter after a page has been checked.

Abstract: A memory array or structure and method for decoding a read address to facilitate simultaneous reading of successive rows. The memory includes row decoders in the form of decoding logic for enabling multiple rows of the memory structure to be read in response to a single row address. The memory structure helps to reduce the number of ports that are required for the memory structure and, thus, reduces the die area occupied by the memory structure. The row address may be divided into most significant bits and least significant bits. Further, the decoding logic may decode the most significant bits differently from the least significant bits when processing the row address. The most significant bits may be preprocessed or predecoded into a fully decoded format while the least significant bits may be decoded into a priority decoded format.

Abstract: A circuit for converting signals between a memory interface and a memory array is disclosed. The memory interface is not the same type as the memory array such that the signals between the interface and the array need to be synchronized and translated. The circuit includes an interface converter for shifting the logic levels of the signals between the memory interface and the memory array. Furthermore, the circuit has a translation block for translating and synchronizing the signals. In this respect signals between the memory array and the memory interface are synchronized and translated such that the memory array can be used with a memory interface of a different type.

Abstract: A semiconductor device with adjustable number of pages and page depth is disclosed. The semiconductor device includes multiple memory cell array blocks, a page control circuit for generating a control signal which varies the number of pages and the page depth in response to a page control signal, and a sense amplifying and write driving circuit. The page control circuit controls a row address and a column address to generate the control signal, that is, to vary the number of pages and the page depth. The sense amplifying and write driving circuit senses, amplifies and outputs data from a memory cell array block, and writes data into a memory cell array block in response to the control signal. The page control circuit includes an address buffer, a block controller and a control signal generator. The address buffer buffers the most significant bit (MSB) of the row address and outputs the buffered result, or ignores the MSB depending on the page control signal.

Abstract: An enhanced checkerboard pattern for optimizing performance when accessing a four-bank SDRAM. The screen is mapped using the enhanced checkerboard pattern, and each enhanced checkerboard pattern is composed of 16 squares. The enhanced checkerboard is made from two basic blocks, each block having 4 squares, and each square representing a distinct memory bank. The two basic blocks are mirror image of each other.

Abstract: A synchronous semiconductor memory device has improved layout and circuitry so as to provide rapid operation. Data paths between sub-arrays and memory cells and corresponding DQ pads are equalized to provide approximately equal line delays, transmission losses, etc. Input clock circuitry converts a “asynchronous” external clock signal and external clock enable signal to an internal “synchronous” clock signal. Input command signals are not stored in input registers, but instead are latched so as to provide such input signals rapidly downstream. Multiple redundant compare circuitry is provided to improve delays inherent in selecting between external or internal addresses. Input/output pull up circuitry is enabled during both read and write operations, but shortened during write operations. Two or more voltage pump circuits are employed that permit sharing of power therebetween to compensate for increased power demands to row lines, data output lines, etc.

Abstract: A method and apparatus for erase operations of a flash memory block. In one embodiment, a method comprises erasing a predetermined percent of rows in a memory block, analyzing a number of erase pulses used to erase the predetermined percent and calculating an acceptable number of additional erase pulses which could be applied to the memory block to erase the remaining rows. In another embodiment, a flash memory device comprises a memory array, a controller and a register. The memory array has a plurality of blocks of flash memory cells. The memory cells in each block are arranged in rows. The controller is used to control memory operations to the memory array and the register is coupled to the controller to track the erase status of each row of memory cells.

Abstract: An integrated circuit comprising a memory and a logic circuit. The memory may comprise a plurality of storage elements each configured to read and write data in response to an internal address signal. The logic circuit may be configured to generate a predetermined number of the internal address signals in response to (i) an external address signal, (ii) a clock signal and (iii) one or more control signals. The generation of the predetermined number of internal address signals may be non-interruptible.

Abstract: With the objective of providing a semiconductor memory device which is made identical in usability to a static RAM by use of dynamic memory cells and realizes a high-speed memory cycle time, there is provided a pseudo static RAM having a time multiplex mode which, when instructions for a memory operation for reading memory information from each of memory cells each requiring a refresh operation for periodically holding the memory information, or writing the same therein is issued, carries out an addressing-based autonomous refresh operation different from the memory operation before or after the memory operation. The pseudo static RAM includes address signal transition detectors for a row and a column, and a page mode which independently performs a column address selecting operation according to an address signal transition detect signal of the column address signal transition detector.

Abstract: A dynamic random access memory device includes a mode register set, a refresh period selector, and a bit organization selector. The mode register set outputs decoded signals having values according to a user-stored value in the mode register set. The mode register set can be accessed in response to an address externally supplied when a mode set command is applied. The refresh period selector generates a plurality of refresh period select signals in response to the decoded signals. A refresh counter in the device generates a sequence of row addresses having a timing according to a refresh period determined from an activated refresh period select signal. The bit organization select circuit generates a plurality of bit organization select signals in response to the decoded signals from the mode register set. A data output multiplexer in the device selects some of the read data bits according to a bit organization determined by one of the bit organization select signals.

Abstract: In a test mode, read data is output from a memory array with each of N latch circuits in an output circuit being set to an operating state under the control of a latency setting circuit. Thus, the data transmission period can be set shorter in the test mode than in a normal data reading operation, and a time required for testing the read data in the test mode is shortened.

Abstract: A nonvolatile semiconductor memory includes a plurality of memory cells arranged in columns and rows, a plurality of word lines, a plurality of bit lines, a plurality of output buffers, and a plurality of page buffers grouped in a plurality of sub-pages. Each page buffer is connected to corresponding bit lines through a first column decoder circuit and connected to one corresponding output buffer through a second column decoder circuit. This construction allows the peripheral control circuits to clock out data stored in page buffers of a first sub-page into output buffers while latching bit line data into page buffers of a second sub-page. Therefore, this architecture is able to perform read and update the page buffer data of different sub-pages simultaneously. Two sets of address registers are used to store the starting and the end address for programming. During programming, only sub-pages located between the starting and end address will be programmed successively.

Abstract: A memory system including a memory array, an input circuit and a logic circuit is presented. The input circuit is coupled to receive a memory address and a set of individual write controls for each byte of data word. During a write operation, the input circuit also receives the corresponding write data to be written into the SRAM. The logic circuit causes the write data and write control information to be stored in the input circuit for the duration of any sequential read operations immediately following the write operation and then to be read into memory during a subsequent write operation. During the read operation, data which is stored in the write data storage registers prior to being read into the memory can be read out from the memory system should the address of one or more read operations equal the address of the data to be written into the memory while temporarily stored in the write data storage registers.

Abstract: A memory controller includes a pair of input command decoders and a pair of multiplexers. If the memory controller receives a data transfer request related to a read or write burst which will stay within a page of memory, the first input command decoder circuit generates a first input command which is then passed, in sequence, by the first and second multiplexers. Conversely, if the data transfer request relates to a read or write burst which will burst over a page of the memory, the second input command decoder circuit generates second and third input commands. The second input command passes through the second multiplexer circuit while the third input command is held in a command register. The third input command is subsequently passed through the first and second multiplexers.

Abstract: Generally, the present invention provides memory controller for providing a synchronous SRAM interface to an embedded SDRAM. To achieve maximum performance SDRAM timing, row circuitry is emulated in the controller to produce SDRAM control signals. Control signal timing is optimized for read and write operations and can be flexibly adjusted using control registers. Since the timing of DRAM control signals is based on the embedded DRAM timing emulation, all margins can be minimized and the performance of the memory can be maximized. The SRAM interface can operate in a wide range of clock frequencies, which are not restricted to ratios of multiples of the embedded DRAM clock frequency.

Abstract: A semiconductor disk wherein a flash memory into which data is rewritten in block unit is employed as a storage medium, the semiconductor disk including a data memory in which file data are stored, a substitutive memory which substitutes for blocks of errors in the data memory, an error memory in which error information of the data memory are stored, and a memory controller which reads data out of, writes data into and erases data from the data memory, the substitutive memory and the error memory. Since the write errors of the flash memory can be remedied, the service life of the semiconductor disk can be increased.

Abstract: A semiconductor memory device is provided in which a burst length and/or a column address strobe (CAS) latency may be fixed. The semiconductor memory device, which may be an SDRAM (synchronous dynamic random access memory) device, includes a memory cell array, a burst address generation circuit to generate a burst address and a burst length detection signal, a mode setting register for setting a CAS latency and/or a burst length using an address, a pipeline circuit to delay and output data read from the memory cell array. The semiconductor memory device also includes a latency enable control signal generation circuit to generate a latency enable control signal in response to a read command or signal and the burst length detection signal, and a data output circuit to output data being output from the pipeline circuit in response to the latency enable control signal. Therefore, a circuit configuration is simplified and a test time is reduced, by fixing latency and/or burst length.

Abstract: A memory device includes 4 memory banks each of which includes first and second arrays of memory cells. A mode register is programmed with a bit that selects a high-power, large-page operating mode or a low-power, small-page operating mode. In the high-power mode, a row decoder is coupled to the row lines in both the first and second arrays. In the low-power mode, the row decoder is coupled to the row lines in only one of the arrays as determined by the state of an array select signal. The array select signal corresponds to the most significant bit of the column address, but it is applied to the memory device at the time the row address is applied to the memory device. Sense amplifiers coupled to the first and second arrays may also be selectively enabled when the row lines for the corresponding array are coupled to the row decoder.

Abstract: A nonvolatile semiconductor memory includes a plurality of memory cells arranged in columns and rows, a plurality of word lines, a plurality of bit lines, a plurality of output buffers, and a plurality of page buffers grouped in a plurality of sub-pages. Each page buffer is connected to corresponding bit lines through a first column decoder circuit and connected to one corresponding output buffer through a second column decoder circuit. This construction allows the peripheral control circuits to clock out data stored in page buffers of a first sub-page into output buffers while latching bit line data into page buffers of a second sub-page. Therefore, this architecture is able to perform read and update the page buffer data of different sub-pages simultaneously. Two sets of address registers are used to store the starting and the end address for programming. During programming, only sub-pages located between the starting and end address will be programmed successively.

Abstract: A nonvolatile semiconductor memory device comprising a main memory cell array and a spare memory cell array, capable of freely accessing data in the spare memory cell array irrespective of the physical addresses of the spare memory cell array, and a method thereof are disclosed. The logical addresses of the spare memory cell array are assigned prior to the logical addresses of the main memory cell array in response to a first control signal, and data stored in the spare memory cell array is read earlier than data in the main memory cell array.

Abstract: A timing and control structure for a memory, including the timing and control structure includes a first circuit that can recognize, on the basis of control signals supplied to the memory from the exterior, whether a random-access reading is to be executed, the control signals including a first control signal indicative of the presence of an address supplied to the memory from the exterior, and a second control signal that, upon switching edges of a first type, supplies to the control and timing structure a time base for the execution of the random-access readings and, upon switching edges of a second type, supplies a time base for the execution of the sequential readings, a second circuit controlled by the first circuit and upon a random-access reading, generates a first synchronism signal in response to a transition of the first type in the second control signal, a third circuit sensitive to transitions of the second type in the second control signal and which can generate a second synchronism signal upon t

Abstract: A memory IC card including a card substrate, a semiconductor device mounted on the card substrate, which includes an CPU, a flash memory, a memory block and a flash memory rewrite circuit having a rewrite data control circuit that receives a rewrite instruction of the flash memory from the CPU to store data for a designated byte of a page for rewriting to the memory block, a page data control circuit that sends data of the page excepting the designated byte in the flash memory to the memory block to prepare new page data in the memory block and a data set control circuit that writes the new page data prepared in the memory block to the flash memory; outer terminals mounted on the card substrate; wirings provided on the card substrate to connect the outer terminals.

Abstract: Network processors commonly utilize DRAM chips for the storage of data. Each DRAM chip contains multiple banks for quick storage of data and access to that data. Latency in the transfer or the ‘write’ of data into memory can occur because of a phenomenon referred to as memory bank polarization. By a procedure called quadword rotation, this latency effect is effectively eliminated. Data frames received by the network processor are transferred to a receive queue (FIFO). The frames are divided into segments that are written into the memory of the DRAM in accordance with a formula that rotates the distribution of each segment into the memory banks of the DRAM.

Abstract: In a conventional DRAM, row addresses and column addresses are latched by DFF and decoding of addresses is started a certain time after a clock rise, and it takes a long time after the clock rise until the decoding is completed, having a problem that it is not possible to perform read/write at high speed. The present invention adopts a configuration connecting latch circuits such as the row address latch circuits and column address latch circuits using a scan chain. This makes decoding of row addresses and column addresses start when the clock is “L”, making it possible to complete decoding on the rise of each operation clock cycle, shorten the operation clock cycle and speed up read/write. The conventional art conducts a test on the connection between the row addresses and column addresses of the logic section and memory through an actual operation test of the entire LSI, resulting in a low circuit failure detection rate.

Abstract: A high-speed clock-synchronous memory device is provided with a sense amplifier S/A shared by and between cell arrays, and a cell array controller unit CNTRLi, wherein input and output of data/command synchronous with the clock, access command supplies all address data bits (row and column) simultaneously. By acknowledging a change in bits observed between tow successive commands, regarding some of the address bits configuring an access address, the device judges whether the current access is made within the same cell array as the preceding access, between the neighboring cell arrays, or between remote cell arrays. According to the judgment, suitable command cycle is applied. At this time, the command cycle satisfies the relationship: S•N•F.

Abstract: A method and system for implementing a mirror addressing scheme in conjunction with a symmetrical data table are disclosed. The method includes receiving a first address. In response to determining that the first address corresponds to an upper portion of a data table, generating a second address from the first address, where the second address corresponds to a lower portion of the data table. The method further includes using the second memory address to access a memory array, whereby data corresponding to the upper portion of the data table is accessed from the lower portion of the data table. In one embodiment, determining that the first address corresponds to an upper portion of the data table is achieved by determining upper segment and lower segment boundaries for the first memory address determining that the most significant bit of the lower segment is asserted.

Abstract: A memory cell array has a unit formed from one memory cell and two select transistors sandwiching the memory cell. One block has one control gate line. Memory cells connected to one control gate line form one page. A sense amplifier having a latch function is connected to a bit line. In a data change operation, data of memory cells of one page are read to the sense amplifiers. After data are superscribed on data in the sense amplifiers, and a page erase is performed, data in the sense amplifiers are programmed in the memory cells of one page. Superscription of data in the sense amplifiers allows a data change operation for byte data or page data.

Abstract: A selection circuit causes either a memory 6H or 6L to enter an enabled state according to address data A16 of address data A0-A16 when a mode signal M is 1. The selection circuit comprises OR gates (10, 12) which output different outputs. When the address data A16 is 0, a nonvolatile memory 6L enters an enabled state. Then, the memory 6L is addressed according to the address data A0-A15 so that, for example, 8-bit lower data is written therein. On the other hand, when the address data A16 is 1, a nonvolatile memory 6H becomes in an enabled state. Then, the memory 6H is addressed according to the address data A0-A15 so that, for example, 8-bit upper data is written therein. Also, when an external terminal (17) is grounded, and a mode signal become 0, the OR gates (10, 12) outputs signals 0, so that the memories 6H, 6L simultaneously become in an enabled state. When data is read from corresponding addresses of each memory, data of, for example, 16-bits is obtained.

Abstract: A method of writing in page mode in an electrically erasable and programmable non-volatile memory includes an initialization phase of writing an information element for the selection of the page in a storage latch associated with a column of the non-volatile memory array, and the writing in a temporary memory of each of the data bits to be written in the page. A write phase includes the selection of rows of the non-volatile memory array according to the contents of the temporary memory. A page mode write circuit includes one latch per column of the non-volatile memory array to contain a page selection information element, and a control logic circuit to give the row selection signals as a function of the contents of the temporary memory in a phase for writing the column of the non-volatile memory array.

Abstract: A method and apparatus for masking data written to a memory device that reduces the effective write cycle time of the memory device is disclosed. Firing of the column selects is pre-empted, thereby masking data to be written to a memory device. By pre-empting the column selects, the margin required for disabling a write driver can be eliminated, thereby reducing the effective write cycle. Additionally, data masking can be performed on a per-byte basis by associating independent column selects with each data byte on multi-byte wide devices, e.g., x16 or x32.

Abstract: A semiconductor memory having burst mode operation includes a memory cell array, a sense amplifier circuit determining data of memory cells, a latch circuit having first and second latch groups and latching data of a sense amplifier, an enable circuit provided with an chip enable signal and controlling readout operation the semiconductor. The enable circuit instructs the circuit for readout operation to activate until the latch circuit latches data even if the chip enable signal indicates stopping the readout operation of semiconductor memory to output data of memory cells correctly.

Abstract: Disclosed a semiconductor memory device in which an access to a memory cell is designated according to a command, and a common data terminal is used as an input terminal to which a write signal to the memory cell is input and an output terminal from which a read signal from the memory cell is output. The semiconductor memory device includes: a first input circuit having input capacitance corresponding to the input terminal to which the command is input; and a second input circuit having input capacitance corresponding to the data terminal. A mask signal for checking the write signal input from the data terminal is input by either the first or second input circuit by a bonding option technique.

Abstract: A method and apparatus are provided for addressing a memory device. The apparatus receives a system address from a memory access device having an endianess. The system address has a word address bit corresponding to word boundaries within the memory device. The apparatus selectively inverts the word address bit as a function of the endianess of the memory access device to produce a selectively modified system address. The apparatus then accesses a memory location with the memory device based on the selectively modified system address.

Abstract: A specifying circuit specifies either the first masking method or the second masking method. A first generation circuit generates a signal corresponding to the first method. A second generation circuit generates a signal corresponding to the second method. A third generation circuit generates a write pulse signal on the basis of the output signal of the first generation circuit in response to the specification of the first masking method made by the specifying circuit and on the basis of the output signal of the second generation circuit in response to the specification of the second masking method made by the specifying circuit.

Abstract: In a PC card to be connected to a personal computer, two kinds of operational modes which are different in data bus width from each other can be changed over selectively. Either the CardBus mode with a data bus width of 32 bits or the 16-bit mode is selectable by a selector switch provided in a side face. The PC card 1 is operated in the 16-bit mode for use with a 16-bit-compatible personal computer, and operated in the 32-bit mode for use with a 32-bit-compatible personal computer. Thus, one PC card is useable with various personal computers.

Abstract: A redundancy architecture for a memory includes an array of memory cells divided into at least a pair of semi-arrays that are singularly addressable. Each semi-array is organized into rows and columns. The redundancy architecture includes a number of packets each including redundancy columns. The packets are divided into two subsets of packets. Each packet is addressable independently from the other by respective address circuits. Each packet also provides redundancy columns exclusively for a respective semi-array.

Abstract: A nonvolatile semiconductor memory includes a plurality of memory cells arranged in columns and rows, a plurality of word lines, a plurality of bit lines, a plurality of output buffers, and a plurality of page buffers grouped in a plurality of sub-pages. Each page buffer is connected to corresponding bit lines through a first column decoder circuit and connected to one corresponding output buffer through a second column decoder circuit. This construction allows the peripheral control circuits to clock out data stored in page buffers of a first sub-page into output buffers while latching bit line data into page buffers of a second sub-page. Therefore, this architecture is able to perform read and update the page buffer data of different sub-pages simultaneously. Two sets of address registers are used to store the starting and the end address for programming. During programming, only sub-pages located between the starting and end address will be programmed successively.

Abstract: In the present invention, disclosed is a semiconductor memory device capable of reducing the number of erasing times of each block allocated to a cluster or the number of blocks to be erased in one writing to the minimum. As an embodiment of the present invention, when a host system 1 performs accessing, for each cluster as a unit, to the FAT partition prepared on a flash memory 17 of the semiconductor memory device 100, a CPU 6 adds an address offset value held by address offset storage section 10 to a logical address specified by the host system 1, whereby a logical address of a head sector of the cluster correspond to a physical address of a head sector of a unit block for erasing/writing data in the flash memory 17.

Abstract: A method for operating a memory device includes receiving a first page address and extracting a first addressed page defined by the first page address. The method further includes serially accessing the first addressed page, and, during serial access of the first addressed page, broadcasting a next page address to begin extraction of a next addressed page so that serial access of the next addressed page may immediately follow serial access of the first addressed page with no access latency period.

Abstract: A core memory containing an array of core cell memory elements are accessed using a cascode barrel reading arrangement and method. The cascode barrel read uses a plurality of cascodes and a plurality of sense amplifiers to read core cells that have consecutive array addresses. The core cells are connected with the plurality of cascodes via a core cell selector. After data from a core cell from a particular cascode has been read and the next consecutive core cell is being read from a different cascode, the original cascode looks ahead to the core cell with the next highest address. Consequently, when the sense amplifier is ready to sense the original cascode again, the data from the core cell with the next highest address has already been loaded and is immediately ready to be read.

Abstract: A synchronous flash memory includes an array of non-volatile memory cells. The memory device has a package configuration that is compatible with an SDRAM. The memory includes a clock connection to receive an external clock signal, a chip select (CS#) connection to receive a chip select signal, a row address strobe (RAS#) connection to receive a row address strobe, a column address strobe (CAS#) connection to receive a column address strobe and a write enable (WE#) connection to receive a write enable signal. Control circuitry is provided to perform a burst read operation of memory cells in a first block of the memory and interrupt the burst read operation when the chip select signal is active, the row address strobe is either inactive or active, the column address strobe is de-active, the write enable signal is active, and the address signals identify the first block simultaneously during the burst read operation.

Abstract: In a memory device capable of processing a small amount of data in a high speed, this memory device is suitable for various sorts of systems in which a plurality of access requests for continuous addresses are mixed with each other, and are issued as irregular requests to a memory subsystem. A data array is provided in a memory device having a memory cell. This data array may be arranged as a virtual register array having an arbitrary number of arbitrary word length. The data register array is accessed by employing a virtual register number and a virtual word number, which are supplied from an external circuit provided outside the memory device. In the memory device, both the virtual register number and the virtual word number, which are supplied from the external circuit, are converted into both an absolute register number and an absolute word number by an internally-provided converting circuit so as to access the data register array.

Abstract: A system and apparatus for controlling a burst sequence in a synchronous memory is described. In one embodiment, the system comprises a synchronous memory and a burst read device coupled to the synchronous memory. In one embodiment, the burst read device is configured to sense a page of data as a current page from the synchronous memory, wherein the current page contains a fixed number of words of data. The device is further configured to latch the current page of data, and synchronously read the current page of data, one word at a time. In an alternate embodiment, the burst read device further comprises a wrap-bit. If the wrap-bit is not set, the burst read device is configured to latch the current page of data, adjust a word pointer to indicate a next word of data, and repeat latching and adjusting in a sequential burst read order.

Abstract: A block write circuit in a memory device having a wide internal data path performs block write and data masking functions. The memory device includes a plurality of data terminals adapted to receive respective data signals, and a plurality of array groups each including a plurality of arrays and each array includes a plurality of memory cells. A plurality of input/output line groups each include a plurality of input/output lines coupled to the arrays of an associated array group. The block write circuit comprises a plurality of write driver groups, each write driver group including a plurality of write driver circuits having outputs coupled to respective data lines in an associated data line group. Each write driver circuit includes an input and develops a data signal on its output responsive to a data signal applied on its input. A multiplexer circuit includes a plurality of inputs coupled to respective data terminals, and a plurality of output subgroups.