Abstract: A device and method for facilitating orthogonal data transposition during data transfers to/from a processing array and a storage memory since the data words processed by the processing array (using computational memory cells) are stored orthogonally to how the data words are stored in storage memory. Thus, when data words are transferred between storage memory and the processing array, a mechanism orthogonally transposes the data words.

Abstract: A computational memory cell and processing array have a ratioless write port so that a write to the memory cell does not need to overcome the drive strength of a PMOS transistor that is part of the storage cell of the memory cell. The computational memory cell also may have a second read port that has an isolation circuit.

Abstract: A write data processing apparatus and method associated with computational memory cells formed as a memory/processing array provides the ability to shift data between adjacent bit lines in each section of the memory/processing array or the same relative bit lines in adjacent sections of the memory/processing array. The memory/processing array has one or more sections and each section has its own unique set of “n” bit lines.

Abstract: A read and write data processing apparatus and method associated with computational memory cells formed as a memory/processing array provides the ability for selected write data in a bit line section to be logically combined (e.g. logically ANDed) with the read result on a read bit line, as if the write data were the read data output of another computational memory cell being read during the read operation. When accumulation logic is implemented in the bit line sections, the implementation and utilization of additional read logic circuitry provides a mechanism for selected write data in a bit line section to be used as the data with which the read result on the read bit line accumulates, before the newly accumulated result is captured and stored in the bit line section's read register.

Abstract: A method for use in an associative memory device when multiplying by a sparse matrix includes storing only non-zero elements of the sparse matrix in the associative memory device as multiplicands. The storing includes locating the non-zero elements in computation columns of the associative memory device according to linear algebra rules along with their associated multiplicands such that a multiplicand and a multiplier of each multiplication operation to be performed are stored in a same computation column. The locating locates one of the non-zero elements in more than one computation column if one of the non-zero elements is utilized in more than one multiplication operation.

Abstract: Disclosed is an in-memory computing device including a memory array with non-volatile memory cells arranged in rows and columns; a multiple row decoder to activate at least two cells in a column of the memory array at the same time to generate a parametric change in a bit line connected to at least one cell in the column; and circuitry to write data associated with the parametric change into the memory array. Additionally disclosed is a method of computing inside a memory array including non-volatile memory cells arranged in rows and columns, the method includes activating at least two cells in a column of the memory array at the same time to generate a parametric change in a bit line connected to at least one cell in the column; and writing data associated with the parametric change into the memory array.

Abstract: A system includes an associative memory array and a concurrent adder. The memory array includes a plurality of sections, where each section includes cells arranged in rows and columns. The memory array stores bit j from a first multi-bit number and bit j from a second multi-bit number in a same column in section j. The concurrent adder performs, in parallel, multi-bit add operations of P pairs of multi-bit operands stored in columns of a memory array. Each pair of the P pairs is stored in a different column of the array and each add operation occurs in its associated different column.

Abstract: A self-correcting memory device (SCMD) includes a non-destructive memory array that includes memory cells arranged in rows and columns that includes a storage section, a comparison section, a comparing element, a selective write unit and a row decoder. The storage section stores a first copy, a second copy and a third copy of a data item in physically separated columns. The comparison section temporarily stores the first copy in a first row and the second copy in a second row. The comparing element compares between bits of the first and second rows and provides at least one per bit change indication. The selective write unit receives at least one per bit change indication and fetches from the third copy a correct value for each bit having a positive bit change indication. The row decoder concurrently writes each correct value back to its bit location in the first and second copies.

Abstract: A memory cell that may be used for computation and processing array using the memory cell are capable to performing a logic operation including a boolean AND, a boolean OR, a boolean NAND or a boolean NOR. The memory cell may have a read port that has isolation circuits that isolate the data stored in the storage cell of the memory cell from the read bit line.

Abstract: An associative processor includes a memory array and a controller. The memory array stores a multiplicity of N bit stochastic numbers in separate rows of a stochastic section of the memory array and each stochastic number has a same probability distribution P. The controller includes a probability calculator which receives a desired probability distribution Pdesired, determines a Boolean function of a set of the N bit stochastic numbers which produces the probability distribution Pdesired and activates associated rows of the stochastic numbers to implement the function on the rows to produce a resultant stochastic number having the probability distribution Pdesired.

Abstract: A read register is provided that captures and stores the read result on a read bit line connected to a set of computational memory cells. The read register may be implemented in the set of computational memory cell to enable the logical XOR, logical AND, and/or logical OR accumulation of read results in the read register. The set of computational memory cells with the read register provides a mechanism for performing complex logical functions across multiple computational memory cells connected to the same read bit line.

Abstract: A memory cell that may be used for computation and processing array using the memory cell are capable to performing a logic operation including a boolean AND, a boolean OR, a boolean NAND or a boolean NOR. The memory cell may have a read port that has isolation circuits that isolate the data stored in the storage cell of the memory cell from the read bit line.

Abstract: Multi-bank, dual-pipe SRAM systems, methods, processes of operating such SRAMs, and/or methods of fabricating multi-bank, dual-pipe SRAM are disclosed. For example, one illustrative multi-bank, dual-pipe SRAM may comprise features for capturing read and write addresses, splitting and/or combining them via one or more splitting/combining processes, and/or bussing them to the SRAM memory banks, where they may be read and written to a particular bank. Illustrative multi-bank, dual-pipe SRAMs and methods herein may also comprise features for capturing two beats of write data, splitting and/or combining them via one or more splitting/combining processes, and bussing them to each SRAM bank, where they may be split/combined/recombined via one or more processes to write data to particular memory bank(s).

Abstract: A system, method and circuits are described that pertain to locked loop circuits, distributed duty cycle correction loop circuitry. In some embodiments, the system and circuit may involve or be configured for coupling with lock loop circuitry such as phase locked loop (PLL) circuitry and/or a delay locked loop (DLL) circuitry. For example, one illustrative implementation may include or involve a phase locked loop (PLL) with distributed duty cycle correction loop/circuitry.

Abstract: A method for an associative memory device includes replacing a set of three multi-bit binary numbers P, Q and R, stored in the associative memory device, with two multi-bit binary numbers X and Y, also stored in the associative memory device, wherein a sum of the binary numbers P, Q and R is equal to a sum of the binary numbers X and Y. A system includes an associative memory array having rows and columns and a multi-bit multiplier. Each column of the array stores two multi-bit binary numbers to be multiplied. The multi-bit multiplier multiplies, in parallel, the two multi-bit binary numbers per column by concurrently processing all bits of partial products generated by the multiplier. The multiplier performs the processing without any carry propagation delay when adding all but the last two partial products.

Abstract: A method of operating a clock frequency detected control-i/o buffer enable circuit in a semiconductor device uses control I/O buffer enable circuitry and/or features of saving power in standby mode. The method may provide low standby power consumption, such as providing low standby power consumption in high-speed synchronous SRAM and RLDRAM devices.

Abstract: Systems and methods of synchronous memories and synchronous memory operation are disclosed. According to one illustrative implementation, a memory device is disclosed comprising memory circuitry having a memory output, the memory circuitry including a sense amplifier having a first output and a second output, a first data path coupled to the first output of the sense amplifier, the first data path including 2 latches/registers, and a second data path coupled to the second output of the sense amplifier, the second data path including a plurality latches/registers. In further implementations, various control circuitry, connections and control signals may be utilized to operate the latches/registers in the first and second data paths according to specified configurations, control, modes, latency and/or timing domain information, to achieve, for example, pipelined output latching and/or double data rate output.

Abstract: A method to add a first one bit variable with a second one bit variable and a carry-in bit, to generate a sum bit and a carry-out bit, the method includes initiating the sum bit to the value of the second one bit variable, initiating the carry-out bit to a value of the carry-in bit and modifying the sum bit and the carry-out bit if a comparison of a sequence of the first one bit variable, the second one bit variable and an inverse value of the carry-in bit matches one of a predefined set of a change trigger sequences.

Abstract: A memory cell that may be used for computation and processing array using the memory cell are capable to performing a logic operation including a boolean AND, a boolean OR, a boolean NAND or a boolean NOR. The memory cell may have a read port that has isolation circuits that isolate the data stored in the storage cell of the memory cell from the read bit line.

Abstract: A method for finding an extreme value among a plurality of numbers in an associative memory includes creating a spread-out representation (SOR) for each number of the plurality of numbers, storing each SOR in a column of the associative memory array and performing a horizontal bit-wise Boolean operation on rows of the associative memory array to produce an extreme SOR (ESOR) having the extreme value. A system for finding an extreme value includes an associative memory array to store the plurality of numbers, each number storable in a column; a spread-out representation (SOR) creator to create a SOR for each number of the plurality of numbers and to store each SOR in a column of the associative memory array, and an extreme SOR (ESOR) finder to find an extreme value using a horizontal bit-wise Boolean operation on rows of the associative memory array storing bits of the SORs.