Abstract: Systems and methods are described relating to a matcher that inputs partial vectors at a rate of 1 per clock cycle and delivers complete vectors at the output with an indication per vector of its validity. The matcher can copy a maximum number of valid elements from an input queue to target vector in-order each clock cycle and eliminate copied elements from the input queue. The completely filled target vectors are paired with the complete data vectors and outputted as composite vectors.

Abstract: Approaches for a distributed storage system that comprises a plurality of nodes. Each node, of the plurality of nodes, executes one or more application processes which are capable of accessing persistent shared memory. The persistent shared memory is implemented by solid state devices physically maintained on each of the plurality of nodes. Each the one or more application processes, maintained on a particular node, of the plurality of nodes, communicates with a shared data fabric (SDF) to access the persistent shared memory. The persistent shared memory comprises a scoreboard implemented in shared DRAM memory that is mapped to a persistent storage. The scoreboard provides a crash tolerant mechanism for enabling application processes to communicate with the shared data fabric (SDF).

Abstract: A memory module includes a plurality of memory devices and is operable in a computer system to perform memory operations in response to memory commands from a memory controller of the computer system. The memory module comprises a register device configured to receive a set of input control/address signals associated with a respective memory command (e.g., a read command or a write command) from the memory controller and to generate a set of output control/address signals in response to the set of input control/address signals. The set of output control/address signals are provided to the plurality of memory devices.

Abstract: Computer readable media, methods and apparatuses are disclosed that may be configured for sequentially reading data of a file stored on a storage medium. The disclosure also provides for alternating writing, in a sequential order, portions of the file data to a first buffer and a second buffer. The disclosure also provides for writing from a first buffer and a second buffer to a first track until the first track is filled.

Abstract: Methods of operating a memory, and memories for performing such methods, include determining that a particular area of the memory is defective, locating a free area of the memory, programming data intended for the particular area of the memory to the free area of the memory, checking the particular area of the memory for data previously programmed to the particular area of the memory, and moving any previously-programmed data from the particular area of the memory to the free area of the memory.

Abstract: In one embodiment, a method includes receiving from a memory controller, a request to access memory stored at memory modules, the request directed to one of a plurality of logical ranks, mapping at a rank aggregator, the logical rank to one of a plurality of physical ranks at the memory modules, and forwarding the request to one of the memory modules according to the mapping. Two or more of the memory modules are combined to represent the number of logical ranks at the memory controller such that there is a one-to-one mapping between the logical ranks and the physical ranks. An apparatus for rank aggregation is also disclosed.

Abstract: A memory device includes an on-board cache system that facilitates the ability of the memory device to interface with a plurality of processors operating in a parallel processing manner. The cache system operates in a manner that can be transparent to a memory controller to which the memory device is connected. Alternatively, the memory controller can control the operation of the cache system.

Abstract: The present invention is directed generally to systems and methods which provide a memory module having multiple data channels that are independently accessible (i.e., a multi-data channel memory module). According to one embodiment, the multi-data channel memory module enables a plurality of independent sub-cache-block accesses to be serviced simultaneously. In addition, the memory architecture also supports cache-block accesses. For instance, multiple ones of the data channels may be employed for servicing a cache-block access. In one embodiment a DIMM architecture that comprises multiple data channels is provided. Each data channel supports a sub-cache-block access, and multiple ones of the data channels may be used for supporting a cache-block access. The plurality of data channels to a given DIMM may be used simultaneously to support different, independent memory access operations.

Abstract: Systems, methods, and devices for dynamically mapping and remapping memory when a portion of memory is activated or deactivated are provided. In accordance with an embodiment, an electronic device may include several memory banks, one or more processors, and a memory controller. The memory banks may store data in hardware memory locations and may be independently deactivated. The processors may request the data using physical memory addresses, and the memory controller may translate the physical addresses to hardware memory locations. The memory controller may use a first memory mapping function when a first number of memory banks is active and a second memory mapping function when a second number is active. When one of the memory banks is to be deactivated, the memory controller may copy data from only the memory bank that is to be deactivated to the active remainder of memory banks.

Abstract: A semiconductor memory system includes a first semiconductor memory die and a second semiconductor memory die. The first semiconductor memory die includes a primary data interface to receive an input data stream during write operations and to deserialize the input data stream into a first plurality of data streams, and also includes a secondary data interface, coupled to the primary data interface, to transmit the first plurality of data streams. The second semiconductor memory die includes a secondary data interface, coupled to the secondary data interface of the first semiconductor memory die, to receive the first plurality of data streams.

Abstract: The disclosed embodiments provide techniques for reducing address-translation latency and the serialization latency of combined TLB and data cache misses in a coherent shared-memory system. For instance, the last-level TLB structures of two or more multiprocessor nodes can be configured to act together as either a distributed shared last-level TLB or a directory-based shared last-level TLB. Such TLB-sharing techniques increase the total amount of useful translations that are cached by the system, thereby reducing the number of page-table walks and improving performance. Furthermore, a coherent shared-memory system with a shared last-level TLB can be further configured to fuse TLB and cache misses such that some of the latency of data coherence operations is overlapped with address translation and data cache access latencies, thereby further improving the performance of memory operations.

Abstract: A method and system are disclosed for remapping logical addresses between memory banks of discrete or embedded multi-bank storage device. The method may include a controller of a storage device tracking a total erase count for a storage device, determining if an erase count imbalance greater than a threshold exists between banks, and then remapping logical address ranges from the highest erase count bank to the lowest erase count bank to even out wear between the banks. The system may include a controller that may maintain a bank routing table, an erase counting mechanism and execute instructions for triggering a remapping process to remap an amount of logical addresses such that an address range is reduced for a hotter bank and increased for a colder bank.

Abstract: Provided are a device, system, and method for mapping memory controller connectors to memory connectors. A memory is programmed to transmit for each of a plurality of the memory data connectors, a pattern on the memory data connectors that has a first value for a selected memory data connector of the memory data connectors and a different value from the first value for the memory data connectors other than the selected memory data connector. For each of the memory data connectors, a read command is issued to read the pattern on the memory data connectors. a device data connector receiving the first value in the read pattern is mapped to the selected memory data connector transmitting the first value.

Abstract: According to embodiments, a memory system includes a plurality of memory chips configuring banks, an instruction generator, and a memory controller. The instruction generator generates a plurality of instructions. The memory controller is configured to execute memory accesses to the banks based on the instructions. Each memory access comprises a first command sequence and a second command sequence. The first command sequence causes in-bank processing shortly subsequent to the first command. The second command sequence is executed subsequent to the in-bank processing. The memory controller executes successively a second command sequence to a first bank based on a first instruction and a first command sequence to the first bank based on a second instruction subsequent to the first instruction, and then starts a memory access to a second bank based on a third instruction while the first bank is executing the in-bank processing caused by the first command sequence.

Abstract: Systems and methods are provided that facilitate memory storage in a memory device. The system contains a memory controller and a memory array communicatively coupled to the memory controller. The memory controller sends commands to the memory array and the memory array writes or retrieves data contained therein based upon the command. The memory controller can monitor multiple banks and manage bank activations. Accordingly, memory access overhead can be reduced and memory devices can be more efficient.

Abstract: A transparent four rank memory module has a front side and a back side. The front side has a third memory rank stacked on a first memory rank. The back side has a fourth memory rank stacked on a second memory rank. An emulator coupled to the memory module activates and controls one individual memory rank from either the first memory rank, the second memory rank, the third memory rank, or the fourth memory rank based on the signals received from a memory controller.

Abstract: Techniques for processing signal information from a high speed communication bus. The techniques includes determining spatial regions on an eye characterized by a start point, an end point, a middle point, a left point, and a right point. The start point is a beginning of an eye opening at a reference voltage. The end point is at an ending of eye opening at the reference voltage. The middle point is at a center point of eye opening at the reference voltage. The left point is a left sampling location characterized by a minimum setup time requirement, and the right point is a right sampling location characterized by a minimum hold time requirement. Determining the points is based on shifting a DQS position and a DQ position and running a plurality of memory built-in self test (BIST) engines and a plurality of results of BIST tests.

Abstract: A memory device includes an on-board processing system that facilitates the ability of the memory device to interface with a plurality of processors operating in a parallel processing manner. The processing system includes circuitry that performs processing functions on data stored in the memory device in an indivisible manner. More particularly, the system reads data from a bank of memory cells or cache memory, performs a logic function on the data to produce results data, and writes the results data back to the bank or the cache memory. The logic function may be a Boolean logic function or some other logic function.

Abstract: Provided is a multi-port cache memory apparatus and a method of the multi-port cache memory apparatus. The multi-port memory apparatus may divide an address space into address regions and allocate the divided memory regions to cache banks, thereby preventing the concentration of access to a particular cache.

Abstract: A computing system comprises at least a processing module, a main memory, a memory controller, and a plurality of memory components. A method begins by the memory controller receiving a memory access request regarding a data segment. The method continues with the memory controller interpreting the memory access request to determine whether an error encoding dispersal function of the data segment is applicable. The method continues with the memory controller identifying at least a threshold number of memories based on the memory access request, wherein the threshold number of memories includes at least one of the main memory and/or one or more of the plurality of memory components, when the error encoding dispersal function is applicable. The method continues with the memory controller addressing the at least a threshold number of memories to facilitate the memory access request.

Abstract: The present disclosure includes systems and techniques relating to implementing fault tolerant data storage in solid state memory. In some implementations, a method includes receiving a data request for a solid state memory; identifying a logical block grouping corresponding to the data request, wherein the logical block grouping indicates physical data storage blocks spanning at least two distinct memory units of the solid state memory; reading stored data and parity information from at least a portion of the physical data storage blocks spanning the at least two distinct memory units; and recovering data of at least one block of the logical block grouping based on the stored data and the parity information.

Abstract: A semiconductor memory device including a plurality of memory die and a controller die. The controller die is connected to an internal control bus. The controller die is configured to provide to a selected one of the memory die an internal read command responsive to an external read command. The selected memory die is configured to provide read data to the controller in response to the internal read command; wherein latency between receipt by the controller die of the external read command and receipt of the read data from the selected memory die differs for at least two of the memory die when selected as the selected memory die.

Abstract: According to an example embodiment, a processor is provided including an integrated on-chip memory device component. The on-chip memory device component includes a plurality of memory banks, and multiple logical ports, each logical port coupled to one or more of the plurality of memory banks, enabling access to multiple memory banks, among the plurality of memory banks, per clock cycle, each memory bank accessible by a single logical port per clock cycle and each logical port accessing a single memory bank per clock cycle.

Abstract: A semiconductor memory device includes a plural number of data input/output pins, a plural number of banks, in each of which a plural number of the information data is stored, a selector and a control circuit. In a first access mode, the control circuit simultaneously accesses the multiple banks in response to a single read-out command or to a single write-in command from outside. In the first access mode, the selector coordinates a plurality of data input/output pins with the multiple banks in a predetermined relationship.

Abstract: The invention relates to a device for monitoring and using internal signals in a programmable system (2), wherein said device includes at least one programmable system (2) including at least one programmable circuit (10, 20, 30), and at least one host system (3) capable of communicating with said programmable system for controlling the monitoring and the use of internal signals in at least one programmable circuit, characterized in that the device further comprises at least one local storage unit (12, 22, 32), at least one control and data-exchange logic unit (4) controlled by a host system, and at least one processing and control unit (8) connected to the at least one host system for communication between the associated host system and at least one storage unit, and for indexing the internal signals of each programmable circuit associated with at least one interface relative to each storage unit.

Abstract: An apparatus and associated methodology for a data storage system having a data storage space operably transferring user data via input/output (I/O) commands between the data storage system and another device. The data storage space includes a first memory device operably storing location information for a selected user data set corresponding to one of the I/O commands. The first memory also operably stores a first amount of the selected user data set. The data storage space also includes a second memory device different than the first memory device and operably storing a different second amount of the selected user data set. The data storage system has a controller that interleaves an entirety of the selected user data set from the first and second memory devices during execution of another of the I/O commands.

Abstract: A computer system includes a controller coupled to a plurality of memory modules each of which includes a memory hub and a plurality of memory devices. The memory hub includes a row cache memory that stores data as they are read from the memory devices. When the memory module is not being accessed by the controller, a sequencer in the memory module generates requests to read data from a row of memory cells. The data read responsive to the generated read requests are also stored in the row cache memory. As a result, read data in the row being accessed may be stored in the row cache memory even though the data was not previously read from the memory device responsive to a memory request from the controller.

Abstract: Disclosed herein are an apparatus and method for controlling memory. The apparatus includes a memory access request buffer unit, a memory access request control unit, and a bank control unit. The memory access request buffer unit determines and stores memory access request order so that the plurality of memory access requests is processed in the order of input except that memory access requests attempting to access the same bank and the same row are successively processed. The memory access request control unit reads the memory access requests from the memory access request buffer unit in the determined order, distributes the memory access requests to banks, and transfers the memory access requests to memory. The bank control unit stores a preset number of memory access requests in each of buffer units for respective banks, and controls the operating state of each of the banks.

Abstract: A method, and corresponding apparatus, of managing processing thread migrations within a plurality of memory clusters, includes embedding, in memory components of the plurality of memory clusters, instructions indicative of processing thread migrations; storing, in one or more memory components of a particular memory cluster among the plurality of memory clusters, data configured to designate the particular memory cluster as a sink memory cluster, the sink memory cluster preventing an incoming migrated processing thread from migrating out of the sink memory cluster; and processing one or more processing threads, in one or more of the plurality of memory clusters, in accordance with at least one of the embedded migration instructions and the data stored in the one or more memory components of the sink memory cluster.

Abstract: A memory device is provided, including a first memory die, a second memory die and a controller. The first memory die has a first system block. The second memory die has a second system block. The controller is coupled to the first and second memory dies through a chip enable lane in order to write the same in-system programming codes (ISP codes) to the first and second system blocks, in which, when the memory device is turned on, the controller reads the ISP code from the first system block or the second system block.

Abstract: Disclosed is a software architecture supporting a large-capacity collective memory layer in a multi-node system by using a remote direct memory access technique and a software virtualization technique and a computing system performing computing processing by using the architecture. In particular, provided is a software architecture including: a memory region managing module collectively managing a predetermined memory region of a node, a memory service providing module providing a large-capacity collective memory service to a virtual address space in a user process, and a memory sharing support module supporting sharing of the large-capacity collective memory of the multi-node system.

Abstract: An external memory interface includes an input/output (IO) logic unit operable to convert a rate of data from a first rate corresponding to a memory controller/schedule unit to a second rate corresponding to an external memory device. The external memory interface also includes a latency adjustment unit, operating in a timing domain of the memory controller/schedule unit, operable to add between 1 to [(second rate/first rate)?1] cycles of latency of the second rate.

Abstract: System refresh in a cache memory that includes generating a refresh time period (RTIM) pulse at a centralized refresh controller of the cache memory and activating a refresh request at the centralized refresh controller based on generating the RTIM pulse. The refresh request is associated with a single cache memory bank of the cache memory. A refresh grant is received and transmitted to a bank controller. The bank controller is associated with and localized at the single cache memory bank of the cache memory.

Abstract: A method for managing multi-layered data structures in a pipelined memory architecture, comprising the steps of: —providing a multi-level data structure where each level corresponds to a memory access; —storing each level in a separate memory block with respect to the other levels. In this way, a more efficient usage of memory is achieved.

Abstract: An apparatus generally having a plurality of memories and a first circuit is disclosed. The memories may be configured to store a plurality of first data points. The first data points generally form a two-dimensional block. The first data points may be arranged among the memories such that a load cycle from the memories accesses a rectangular region of the two-dimensional block. The load cycle generally comprises a plurality of read cycles, a different one of the read cycles corresponding to each one of the memories. The first circuit may be configured to (i) receive the first data points as read from the memories and (ii) generate a plurality of second data points by a video codec transformation of the first data points between a spatial domain and a frequency domain.

Abstract: Method, process, and apparatus to efficiently store, read, and/or process portions of word data. A portion of a data word, which includes multiple portions, may be read by a computer processor. The processor may read a first portion of the data word from a first memory. The processor may read a second portion of the data word from a second portion of memory. The second portion may include bits which are less critical than the bits of the first portion. The second memory may be distinct from the first memory based on one or more physical attributes.

Abstract: A memory controller (101) according to this invention includes: a command generation unit (102) which generates access commands each including a physical address, based on an access request including a logical address indicating a rectangular area in image data; and a command issuance unit (105) which issues, to a memory (0), the access commands generated by the command generation unit (102). The command generation unit (102) includes a group determination unit (104) which determines a group to which a bank including data to be accessed belongs, based on the physical address corresponding to the access request. The command generation unit (102) generates a pair of a first and a second access commands which share a prefetch buffer between two banks belonging to different groups, when data to be accessed is continuous across two banks belonging to different groups.

Abstract: Provided are a storage apparatus and data management method with which the usage ratio of each of the storage tiers is determined beforehand for each virtual volume and data can be managed by being migrated between storage tiers within a range of predetermined usage ratios. A storage apparatus 5, comprising storage devices 30 of a plurality of types of varying performance; and a controller 31 which manages each of storage areas provided by the storage devices 30 of a plurality of types by means of storage tiers ST of a plurality of different types respectively, and which assigns the storage areas in page units to virtual volumes VVOL from any storage tier among the storage tiers ST of a plurality of types, the controller 31 managing usage ratios of the storage tiers ST of a plurality of types and assigning the storage areas in page units to the virtual volumes VVOL based on the usage ratio managed.

Abstract: According to one embodiment, a data storage apparatus includes a write command module, a read command module, and a controller. The write command module is configured to process a write command for writing data to the nonvolatile memories for a plurality of channels, respectively. The read command module is configured to process a read command usually and to process a read command for read modify write (RMW) operation. The controller is configured to control the read command module, causing to execute the read command for the RMW operation, prior to the normal read command, thereby to execute a flush command, and to control the write command module, causing to execute a write flush process that includes the processing of a write command for the RMW operation after the read command for the RMW operation has been executed.

Abstract: A memory system includes a master device, such as a graphics controller or processor, and an integrated circuit memory device operable in a dual column addressing mode. The integrated circuit memory device includes an interface and column decoder to access a row of storage cells or a page in a memory bank. During a first mode of operation, a first row of storage cells in a first memory bank is accessible in response to a first column address. During a second mode of operation, a first plurality of storage cells in the first row of storage cells is accessible in response to a second column address during a column cycle time interval. A second plurality of storage cells in the first row of storage cells is accessible in response to a third column address during the column cycle time interval. The first and second pluralities of storage cells are concurrently accessible from the interface.

Abstract: A storage device able to make a redundant write operation of unselected data unnecessary and able to optimize an arrangement of pages to a state having a high efficiency for rewriting, wherein the storage device has a first memory unit, a second memory unit having a different access speed from the first memory, and a control circuit, wherein the control circuit has a function of timely moving the stored data in two ways between the first memory unit and the second memory unit having different access speeds in reading or rewriting.

Abstract: A memory module may include a plurality of dynamic random access memory (DRAM) chips, each of which may have one or more data input/output (D/Q) terminals. The memory module may include data redriving/retiming circuits connected to the D/Q terminals of the plurality of DRAM chips. The data redriving/retiming circuits may provide isolation between a system memory bus and the D/Q terminals of the DRAM chips.

Abstract: Methods of accessing memory cells, methods of distributing memory requests, systems, and memory controllers are described. In one such method, where memory cells are divided into at least a first region of memory cells and a second region of memory cells, memory cells in the first region are accessed according to a first address definition and memory cells in the second region are accessed according to a second address definition that is different from the first address definition. Additional embodiments are described.

Abstract: Some embodiments of the present invention provide a system that maps an address to an entity, wherein the mapping interleaves addresses between a number of entities. During operation, the system receives an address A from a set of X consecutive addresses, wherein the address A is to be mapped to an entity E in a set of Y entities, and wherein Y need not be a power of two. Next, the system obtains F=floor(log2(Y)) and C=ceiling(log2(Y)). The system then calculates L, which equals the value of the F least-significant bits of A. The system also calculates M, which equals the value of the C most-significant bits of A. Next, the system calculates S=L+M. Finally, if S<Y, the system sets E=S. Otherwise, if S?Y, the system sets E=S?Y.

Abstract: A system and method for serial interface topologies is disclosed. A serial interface topology includes a replication device configured to receive control information from a controller interface. The replication device is configured to transmit two or more copies of substantially replicated control information to a device control interface. A data interface is configured to provide differential, point-to-point communication of data with the device controller interface.

Abstract: A data storage device and methods of performing memory operations using location-based parameters are disclosed. A method includes identifying a set of parameter values associated with a physical block of a memory array on a memory die. The set of parameter values is identified based on a physical location of the physical block. A physical location may include an edge or a central region of the memory array or the memory die. The memory die may comprise a nonvolatile semiconductor memory (e.g., flash memory). Parameter values may include a size or a number of programming steps, pulse widths, maximum programming or erase voltages, reading or verify reference voltages, and parameters relating to error correction, among others, including time dependent parameters. A memory access operation, such as a reading, programming, or erasing operation, is initiated with respect to the physical block in accordance with the set of parameter values.

Abstract: Described herein are method and apparatus for scheduling access requests for a multi-bank low-latency random read memory (LLRRM) device within a storage system. The LLRRM device comprising a plurality of memory banks, each bank being simultaneously and independently accessible. A queuing layer residing in storage system may allocate a plurality of request-queuing data structures (“queues”), each queue being assigned to a memory bank. The queuing layer may receive access requests for memory banks in the LLRRM device and store each received access request in the queue assigned to the requested memory bank. The queuing layer may then send, to the LLRRM device for processing, an access request from each request-queuing data structure in successive order. As such, requests sent to the LLRRM device will comprise requests that will be applied to each memory bank in successive order as well, thereby reducing access latencies of the LLRRM device.

Abstract: An assembly where a number of receivers receiving packets for storing in queues in a storage and a means for de-queuing data from the storage. A controller determines addresses for the storage, the address being determined on the basis of at least a fill level of the queue(s), where information relating to de-queues addresses is only read-out when the fill-level(s) exceed a limit so as to not spend bandwidth on this information before it is required.

Abstract: The present invention provides a system and method for controlling data entries in a hierarchical buffer system. The system includes an integrated circuit device with a memory core, a high speed upstream data bus, and a plurality of 1st tier buffers that receive data from the memory. The system further includes a 2nd tier transfer buffer spanning a plurality of asynchronous timing domains that delivers the data onto the upstream data bus to minimize gaps in a data transfer. The method includes managing the buffers to allow data to flow from a plurality of 1st tier buffers through a 2nd tier transfer buffer, and delivering the data onto a high speed data bus with pre-determined timing in a manner which minimizes latency to the extent that the returning read data beats are always transmitted contiguously with no intervening gaps.

Abstract: A translating memory module is disclosed including a printed circuit board, at least one memory integrated circuit coupled to the printed board, and at least one support chip coupled to the printed circuit board and coupled between the edge connector and the at least one memory integrated circuit. The at least one support chip includes a bi-directional translator to translate between a first memory communication protocol for the at least one memory integrated circuit and a second memory communication protocol for a memory channel differing from the first memory communication protocol. The second memory communication protocol to communicate data, address, and control signals over the memory channel bus to read and write data into the memory of the translating memory module.