Abstract:
PURPOSE: To simplify processing procedures of a device by accessing automatically and continuously data in plural addresses by one address input to read or write data of continuous instruction codes in a high speed. CONSTITUTION: The memory of a semiconductor storage device is divided to memory chips 3 and 4, and word addresses A 8 WA 15 are inputted to decoders 5 and 6 through address increment circuits 7 and 8. A column decoder 9 is connected to chips 3 and 4 through input/output gate circuits 10 and 11 respectively, and word bits A 0 WA 7 are inputted to the decoder 9, and a shift register 12 is connected to circuits 10 and 11. Data in plural addresses are accessed automatically and continuously by one address input to read or write of data of continuous instruction codes from or onto chips 3 and 4 at a high speed, and processing procedures of the storage device are simplified. COPYRIGHT: (C)1986,JPO&Japio
Abstract:
PURPOSE: To simplify a memory reading action in a certain order for refreshing by performing a reading action through an address counter and by refreshing it automatically. CONSTITUTION: A counter for forming and outputting an adress signal after it is activated by an external timing signal is built in an automatic refresh circuit RFE. The address and a specified address from a shift register SR accomplish reading of a memory array M-ARY for refreshing in a certain order without use of microprocessor, etc. COPYRIGHT: (C)1985,JPO&Japio
Abstract:
Examples of the present disclosure provide apparatuses and methods related to generating and executing a control flow. An example apparatus can include a first device configured to generate control flow instructions, and a second device including an array of memory cells, an execution unit to execute the control flow instructions, and a controller configured to control an execution of the control flow instructions on data stored in the array.
Abstract:
A shiftable memory supporting atomic operation employs built-in shifting capability to shift a contiguous subset of data from a first location to a second location within memory during an atomic operation. The shiftable memory includes the memory to store data. The memory has the built-in shifting capability. The shiftable memory further includes an atomic primitive defined on the memory to operate on the contiguous subset.
Abstract:
A non-volatile memory device capable of reading and writing a large number of memory cells in parallel has an architecture that reduces redundancy in the multiple read/write circuits to a minimum. In one aspect, data latches associated with the multiple read/write circuits are I/O enabled and coupled in a compact manner for storage and serial transfer. They are implemented by one or more chain of link modules, which can selectively behave as inverters or latches. A method enables the use of a minimum number of link modules by cycling data between a set of master link modules and a substantially smaller set of slave link modules.
Abstract:
Selecting circuits for columns of an array of memory cells are used to hold read data or write data of the memory cells. The memory cells may be multistate memory cells. There is a shift register chain, having a stage for columns of the array. A strobe pulse is shifted through this shift register. The strobe points, with each clock, at and enables in parallel different selecting circuits in sequence. That particular selecting circuits that have been enabled by the strobe will then perform a certain function. In a read mode, the selected selecting circuits will send the stored information through to the output buffers for output from the integrated circuit, and while in a programming mode, the selected selecting circuits will receive data from input buffers. This data will be written into memory cells.
Abstract:
Selecting circuits for columns of an array of memory cells are used to hold read data or write data of the memory cells. The memory cells may be multistate memory cells. There is a shift register chain, having a stage for columns of the array. A strobe pulse is shifted through this shift register. The strobe points, with each clock, at and enables a different selecting circuit in sequence. That particular selecting circuit that has been enabled by the strobe will then perform a certain function. In a read mode, the selected selecting circuit will send the stored information through to the output buffer for output from the integrated circuit, and while in a programming mode, the selected selecting circuit will receive data from an input buffer. This data will be written into a memory cell.
Abstract:
L'invention concerne un procédé de lecture de cellules mémoire (CELi,j,k) au moyen d'amplificateurs de lecture (SAi), les cellules mémoire étant reliées à des lignes de bit (BLi,j), la lecture de chaque cellule mémoire comprenant une phase de précharge de la ligne de bit à laquelle la cellule mémoire est reliée et une phase de lecture proprement dite de la cellule mémoire. Selon l'invention, chaque amplificateur de lecture (SAi) est utilisé pour précharger au moins deux lignes de bit, puis pour lire une cellule mémoire et une seule dans l'une des lignes de bit préchargées. Application notamment aux mémoires série, pour la précharge anticipée de lignes de bit ayant la même adresse partielle, pendant la réception d'une adresse de lecture.
Abstract:
A memory buffer apparatus (29) includes an extended shift register (32) and a memory (30). The extended shift register (32) shifts a plurality of serial bits to produce a multi-bit data word. The multi-bit data word has a predetermined length based on a delay interval that is a multiple of a serial bit period. The memory (30) stores the bit-slice of the multi-bit data word. The bit-slice has a length less than that of the multi-bit data word. An extended output shift register (34) can also be included in the apparatus (29). The extended output shift register (34) has a length greater than the stored bit-slice, and performs a parallel-to-serial conversion of the bit-slice output from the memory (30).