Abstract: Embodiments detailed herein relate to systems and methods to load a tile register pair. In one example, a processor includes: decode circuitry to decode a load matrix pair instruction having fields for an opcode and source and destination identifiers to identify source and destination matrices, respectively, each matrix having a PAIR parameter equal to TRUE; and execution circuitry to execute the decoded load matrix pair instruction to load every element of left and right tiles of the identified destination matrix from corresponding element positions of left and right tiles of the identified source matrix, respectively, wherein the executing operates on one row of the identified destination matrix at a time, starting with the first row.

Abstract: A memory request, including an address, is accessed. The memory request also specifies a type of an operation (e.g., a read or write) associated with an instance (e.g., a block) of data. A group of caches is selected using a bit or bits in the address. A first hash of the address is performed to select a cache in the group. A second hash of the address is performed to select a set of cache lines in the cache. Unless the operation results in a cache miss, the memory request is processed at the selected cache. When there is a cache miss, a third hash of the address is performed to select a memory controller, and a fourth hash of the address is performed to select a bank group and a bank in memory.

Abstract: An information processing apparatus includes a first memory configured to retain a request group, based on requests received by a reception interface, a second memory configured to retain a request group, based on requests received by the reception interface, and a first transmission interface configured to transmit the request group retained in the first memory to the first storage and a second transmission interface configured to transmit the request group retained in the second memory to the second storage. The request group transmitted by the first transmission interface and the request group transmitted by the second transmission interface are different request groups.

Abstract: A system monitors and dynamically changes memory mapping in a runtime of a computing system. The computing system has various memory resources, and multiple possible mappings that indicate how data is to be stored in and subsequently accessed from the memory resources. The performance of each memory mapping may be different under different runtime or load conditions of the computing device. A memory controller can monitor runtime performance of the current memory mapping and dynamically change memory mappings at runtime based on monitored or observed performance of the memory mappings. The performance monitoring can be modified for any of a number of different granularities possible within the system, from the byte level to memory channel.

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: Customers of shared resources in a multi-tenant environment can modify operational parameters of electronic resources. A customer can be provisioned a data volume of a specified size, storage type (e.g., hard disk drive or solid state device), committed rate of input/output operations per second, and/or geographical location, for example. The customer can subsequently modify any such operational parameters by submitting an appropriate request, or the operational parameters can be adjusted automatically based on any of a number of criteria. Data volumes for the customer can be migrated, split, or combined in order to provide the shared resources in accordance with the modified operational parameters.

Abstract: The invention provides a portable memory medium with a memory area and a memory management system for managing the memory area, wherein different options for access to the memory area are provided. The memory management system comprises a configuration command, the execution of which causes an activation of one of at least two different activatable memory configurations.

Abstract: Provided are a storage apparatus, a storage management method, and a storage management program capable of performing a backing-up operation under the condition that a host computer is in operation. A storage apparatus 1 according to the present invention includes a cache memory 20, a storage device 30 that stores data, a data copy unit 12 that copies the data to be stored in the storage device 30 in a storage device for duplication 40, and a control unit 11 in which, when writing data in the storage device 30, if the data copy unit 12 is executing a separation copy which does not allow data rewriting during copying, the data to be written in the storage device 30 is stored in the cache memory 20, and after completing the separation copy, the data stored in the cache memory 20 is written in the storage device 30.

Abstract: Disclosed is a host bus adapter (HBA) that to receives an input/output (I/O) command from an operating system I/O driver. Firmware stored on the host bus adapter includes primary firmware and secondary firmware to process the I/O command. The HBA is to respond to the I/O command under the control of one of the primary firmware or secondary firmware. The selected one of said primary firmware and secondary firmware may be used to certify a hardware driver for either the current generation (primary firmware) or a future generation (secondary firmware).

Abstract: A method and apparatus for efficient memory bank utilization in multi-threaded packet processors is presented. A plurality of memory access requests, are received and are buffered by a plurality of memory First In First Out (FIFO) buffers, each of the memory FIFO buffers in communication with a memory controller. The memory access requests are distributed evenly across said memory banks by way of the memory controller. This reduces and/or eliminates memory latency which can occur when sequential memory operations are performed on the same memory bank.

Abstract: A solution is provided to flexibly choose a combination of flash memory devices to reduce the overall cost of the flash memory devices or increase the overall utilization of the flash memory devices, while satisfying the capacity requirements for the flash memory devices in a system design, wherein a decoding unit is used for determining which flash memory devices will be accessed and re-mapping incoming serial addressing bits, for accessing one flash memory device, into an outgoing serial addressing bits for accessing another flash memory device.

Abstract: Divisions by numbers that are not divisible by two (2) can be performed in a computing system based on a summation that estimates and/or approximates the reciprocal of the dividing number or denominator value. By way of example, dividing by three (3) can be calculated based on a summation that approximates or estimates one third (?) represented as the sum of a selected group of the inverses of the powers of two (2) in a pattern, namely the sum of: ¼, 1/16, 1/64, 1/256, . . . ). Applications of the division techniques are virtually unlimited and include memory mapping of global memory addresses to memory channel addresses by dividing a global memory address into the number of memory channels, allowing memory mapping to be performed in an efficient manner even for large memory spaces using a number of memory channels that are not divisible by two, including prime numbers.

Abstract: A device, system, and method are disclosed. In one embodiment the device includes a non-volatile memory (NVM) storage array to store a plurality of storage elements. The device also includes a dual-scope directory structure having a background space and a foreground space. The structure is capable of storing several entries that each correspond to a location in the NVM storage array storing a storage element. The background space includes entries for storage elements written into the array without any partial overwrites of a previously stored storage element in the background space. The foreground space includes entries for storage elements written into the array with at least one partial overwrite of one or more previously stored storage elements in the background space.

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: A semiconductor memory device includes a path control unit configured to activate an address transmission path corresponding to a bank address, an address providing unit configured to provide a memory address to the path control unit in response to an active signal, and a plurality of memory banks each configured to receive the memory address provided through the corresponding address transmission path of the path control unit, wherein the bank address corresponds to a memory bank of the plurality of memory banks.

Abstract: Systems and methods for efficient memory corruption detection in a processor. A processor detects a first data structure is to be allocated in a physical memory. The physical memory may be a DRAM with a spare bank of memory reserved for a hardware failover mechanism. Either the processor or an operating system (OS) determines a first version number corresponding to the first data structure. During initialization of the first data structure, the first version number may be stored in a first location in the spare bank. The processor receives from the OS a pointer holding the first version number. When the processor executes memory access operations targeting the first data structure, the processor compares the first version number with a third version number stored in a location in the physical memory indicated by the memory access address. The processor may set a trap in response to determining a mismatch.

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 divided into a plurality of ranks. The memory hub is operable to configure the memory module to simultaneously address any number of ranks to operate in a high bandwidth mode, a high memory depth mode, or any combination of such modes.

Abstract: A memory device includes a plurality of storage units in which to store data of a bank, wherein the data has a logical order prior to storage and a physical order different than the logical order within the plurality of storage units and a within-device reordering unit to reorder the data of a bank into the logical order prior to performing on-chip processing. In another embodiment, the memory device includes an external device interface connectable to an external device communicating with the memory device, an internal processing element to process data stored on the device and multiple banks of storage. Each bank includes a plurality of storage units and each storage unit has two ports, an external port connectable to the external device interface and an internal port connected to the internal processing element.

Abstract: A device for increasing chip testing efficiency includes a pattern generator, a reading unit, a logic operation circuit, and a judgment unit. The pattern generator is used for writing a logic voltage to each bank of a memory chip. The reading unit is used for reading logic voltages stored in all memory cells of each bank. The logic operation circuit is used for executing a first logic operation on the logic voltages stored in all memory cells of each bank to generate a plurality of first logic operation results corresponding to each bank, and executing a second logic operation on the plurality of first logic operation results to generate a second logic operation result corresponding to the memory chip. The judgment unit determines whether the memory chip passes the test according to the second logic operation result.

Abstract: Systems and methods for re-mapping memory transactions are described. In an embodiment, a method includes receiving a memory request from a hardware subsystem to a memory, replacing a first identifier with a modified identifier in the memory request, and transmitting the memory request to the memory through a processor complex. The method further includes receiving a response from the memory, determining that the response corresponds to the memory request, replacing the modified identifier with the first identifier in the response, and transmitting the response to the hardware subsystem. In some embodiments, a system may be implemented as a system-on-a-chip (SoC). Devices suitable for using these systems include, for example, desktop and laptop computers, tablets, network appliances, mobile phones, personal digital assistants, e-book readers, televisions, and game consoles.

Abstract: A bank select device has a plurality of addressable locations and a plurality of storage locations correlated to each other so that each storage location is correlated to plural addressable locations and each addressable location is correlated to one storage location. Each storage location contains a respective bank select. The addressable locations and storage locations are grouped into interleave patterns such that, for each pattern, there are Q storage locations and 2A addressable locations arranged in L sequential loops each containing Q sequentially addressable locations and a remainder loop containing R sequentially addressable locations, where L·Q+R=2A. A shunt defines a non-zero offset for each interleave so that each interleave commences with a different bank select and a complete rotation of all of the interleaves addresses each of the memory banks an equal number of times. The shunt (S) may be selected as mod(2A,Q), ?Q+mod(2A,Q), ±1 or ±prime to , where ?<S<+.

Abstract: A storage management system and a storage management method are provided. The storage management system includes a host, a memory buffer, a plurality of storage blocks, and an input/output bus to perform an interface function among the host, the memory buffer, and the plurality of storage blocks, wherein each of the plurality of storage blocks is connected with the input/output bus via a corresponding channel, and the plurality of storage blocks is managed for each channel group generated by grouping at least one channel.

Abstract: A system monitors and dynamically changes memory mapping in a runtime of a computing system. The computing system has various memory resources, and multiple possible mappings that indicate how data is to be stored in and subsequently accessed from the memory resources. The performance of each memory mapping may be different under different runtime or load conditions of the computing device. A memory controller can monitor runtime performance of the current memory mapping and dynamically change memory mappings at runtime based on monitored or observed performance of the memory mappings. The performance monitoring can be modified for any of a number of different granularities possible within the system, from the byte level to memory channel.

Abstract: A memory module such as a DIMM includes two separate memories with corresponding data, address and control interfaces. Each separate memory core includes plural memory banks for corresponding portions of the data interface. The separate interfaces include separate byte strobes and control signals. The two memories may be separately powered or share power connection. The two memories may be disposed on a single semiconductor integrated circuit or separate semiconductor integrated circuit. The two memories may be connected to two external memory interfaces of a single data processor or to separate data processors.

Abstract: A method and apparatus for efficient memory bank utilization in multi-threaded packet processors is presented. A plurality of memory access requests, are received and are buffered by a plurality of memory First In First Out (FIFO) buffers, each of the memory FIFO buffers in communication with a memory controller. The memory access requests are distributed evenly across said memory banks by way of the memory controller. This reduces and/or eliminates memory latency which can occur when sequential memory operations are performed on the same memory bank.

Abstract: Memory management process for optimizing the access to a central memory located within a processing system comprising a set of specific units communicating with each other through said memory, said process involving the steps of: a) arranging in a local memory at least a first and a second bank of storage (A, B) for the purpose of temporary object exchanged between a first data object producer (400) and a second data object consumer (410); b) arranging a address translation process for mapping the real address of an object to be stored within said banks into the address of the bank; b) receiving one object produced by said producer and dividing it into stripes of reduced size; c) storing the first stripe into said first bank; d) storing the next stripe into said second bank while the preceding stripe is read by said object consumer (410); e) storing the next stripe into said first bank again while the preceding stripe is read by said object consumer (410).

Abstract: Techniques are provided which may be implemented in various methods and/or apparatuses that to provide a memory pool interface capability to interface with a plurality of shared processes/engines and/or a virtual buffer interface associated there with.

Abstract: Embodiments of a memory system that communicates bidirectional data between a memory controller and a memory IC via bidirectional links using half-duplex communication are described. Each of the bidirectional links conveys write data or read data, but not both. States of routing circuits in the memory controller and the memory IC are selected for a current command being processed so that data can be selectively routed from a queue in the memory controller to a corresponding bank set in the memory IC via one of the bidirectional links, or to another queue in the memory controller from a corresponding bank set in the memory IC via another of the bidirectional links. This communication technique reduces or eliminates the turnaround delay that occurs when the memory controller transitions from receiving the read data to providing the write data, thereby eliminating gaps in the data streams on the bidirectional links.

Abstract: Non-volatile storage devices and methods capable of achieving large capacity solid state drives containing multiple banks of memory devices. The storage devices include a printed circuit board, at least two banks of non-volatile solid-state memory devices, bank switching circuitry, a connector, and a memory controller. The bank switching circuitry is integrated onto the memory controller and functionally interposed between the banks of memory devices and the front end of the memory controller. The bank switching circuitry operates to switch accesses by the memory controller among the at least two banks.

Abstract: A transaction splitting apparatus and method are provided in which neighboring sub-transactions accessing a predetermined bank in each memory may access different banks. The transaction splitting apparatus includes a first processing unit to split a transaction into at least one sub-transaction, the transaction accessing a first bank among a plurality of banks comprised in a memory, and a second processing unit to translate an address of the at least one sub-transaction, to interleave the at least one sub-transaction using the plurality of banks.

Abstract: A controller for a solid state disk is provided. The controller includes a storage module to store an index of at least one idle bank among a plurality of memory banks, and a control module to control an access to the at least one idle bank using the stored index. Here, the access to the at least one idle bank may be controlled based on a state of a channel corresponding to each of the at least one idle bank.

Abstract: A modular integrated circuit includes a hub module that is coupled to a plurality of spoke modules via a plurality of hub interfaces. A memory module stores hub software and hub data and configuration data. The hub software operates in accordance with a memory map that includes a plurality of first reserved blocks corresponding to memory reserved for the plurality of spoke modules, and at least one second reserved block corresponding to memory reserved for at least one optional spoke module. The plurality of first reserved blocks are activated based on the configuration data and the at least one second reserved block is deactivated based on the configuration data.

Abstract: A memory apparatus (100, 200, 300, 500, 600, 700) has a plurality of memory banks (d0 to d7, m0 to m3, p, p0, p1), wherein a write or erase operation to the memory banks (d0 to d7, m0 to m3, p, p0, p1) is substantially slower than a read operation to the banks (d0 to d7, m0 to m3, p, p0, p1). The memory apparatus (100, 200, 300, 500, 600, 700) is configured to read a redundant storage of data instead of a primary storage location in the memory banks (d0 to d7, m0 to m3, p, p0, p1) for the data or reconstruct requested data in response to a query for the data when the primary storage location is undergoing at least one of a write operation and an erase operation.

Abstract: An electronic tag system, an electronic tag, and a controlling method thereof according to the present invention include an electronic tag that includes a memory having a divided band and a bank status that stores a status of data stored in the divided bank, a controlling circuit that reads and writes the data from and to the bank and changes the status and a controlling device that allows the controlling circuit connected through the electronic tag and an electronic tag reader/writer to transmit and receive the read and written data from and to the bank and issue an instruction to change the status.

Abstract: A memory module and a memory module system are provided. The memory module system includes a plurality of memory modules each module comprising a plurality of memory blocks and a plurality of corresponding routers each storing a channel identification (ID) and a module ID corresponding to one or more memory blocks; and a controller configured to access the memory modules. During initialization, the controller reads and stores the channel ID and the module ID from each of the routers. The controller outputs a channel ID and a module ID that correspond to one or more memory blocks to be accessed.

Abstract: A memory structure includes a plurality of address banks where each address bank is operative to store a memory address. In certain embodiments, at least two of the address banks share physical memory locations for at least one redundant most significant bit. Additionally, at least two of the address banks in certain embodiments share physical memory locations for at least one redundant most significant bit and at least one redundant least significant bit. At least two of the address banks in certain embodiments also share physical memory locations for at least one redundant interior bit.

Abstract: A system monitors and dynamically changes memory mapping in a runtime of a computing system. The computing system has various memory resources, and multiple possible mappings that indicate how data is to be stored in and subsequently accessed from the memory resources. The performance of each memory mapping may be different under different runtime or load conditions of the computing device. A memory controller can monitor runtime performance of the current memory mapping and dynamically change memory mappings at runtime based on monitored or observed performance of the memory mappings. The performance monitoring can be modified for any of a number of different granularities possible within the system, from the byte level to memory channel.

Abstract: A method and system for permitting host write operations in one part of a flash memory concurrently with another operation in a second part of the flash memory is disclosed. The method includes receiving data at a front end of a memory system, selecting at least one of a plurality of subarrays in the memory system for executing a host write operation, and selecting at least one other subarray in which to execute a second operation. The write operation and second operation are then executed substantially concurrently. The memory system includes a plurality of subarrays, each associated with a separate subarray controller, and a front end controller adapted to select and initiate concurrent operations in the subarrays.

Abstract: A method, system and computer program product are disclosed for maintaining data coherence, for use in a multi-node processing system where each of the nodes includes one or more components. In one embodiment, the method comprises establishing a data domain, assigning a group of the components to the data domain, sending a coherence message from a first component of the processing system to a second component of the processing system, and determining if that second component is assigned to the data domain. In this embodiment, if that second component is assigned to the data domain, the coherence message is transferred to all of the components assigned to the data domain to maintain data coherency among those components. In an embodiment, if that second component is assigned to the data domain, the first component is assigned to the data domain.

Abstract: Methods and systems for managing and locating available storage space in a system comprising data files stored in a plurality of storage devices and configured in accordance with various data storage schemes (mirroring, striping and parity-striping). A mapping table associated with each of the plurality of storage devices is used to determine the available locations and amount of available space in the storage devices. The data storage schemes for one or more of the stored data files are changed to a basic storage mode when the size of a new data file configured in accordance with an assigned data storage scheme exceeds the amount of available space. The configured new data file is stored in accordance with the assigned data storage scheme in one or more of the available locations and the locations of the new data file are recorded.

Abstract: It is an object of the invention to provide a memory architecture that can handle data interleaving efficiently. This and other objects are achieved by the system according to the invention. The data handling system, is configured for receiving at an input a plurality of commands. The system comprises: a plurality of memory banks; a distributor connected to the input and having a plurality of distributor outputs. Each specific one of the plurality of memory banks (106) is connected to a specific one of the plurality of distributor outputs. The distributor comprises a permutator for designating for each specific command a specific distributor output. The distributor distributes the specific command to the specific designated distributor output. The permutator has a control input and the designating is reconfigurable under the control of reconfiguration data received at the control input.

Abstract: A data packet access control apparatus and a data packet access control method are disclosed. RAM resources in a data packet processing chip are used to implement a Bypass FIFO. The Bypass FIFO is used as a first-level cache for small amount of data, and an external RAM of the data packet processing chip is used as a second-level cache for large amount of data. In this way, some data packets are read and written within the chip and not all data packets have to be read and written through the external RAM. A data packet reading/writing operation may be performed to the external RAM by a BANK interleave mode.

Abstract: A method for accessing a memory is provided. The method includes entering a memory accessing mode for updating a top of low memory (TOLM) value stored in a TOLM register in a chipset of a system with a highest memory address when a memory accessing command is received. The memory accessing command requests the utilization of a memory block in a memory of the system corresponding to an address space occupied by a memory-mapped input output (MMIO) function. The system then accesses the corresponding memory block in the memory according to the address space recorded in the memory accessing command. After the access is completed, the memory accessing mode is closed and the original TOLM value is written back to the TOLM register. Therefore, the present invention can access the “MMIO memory block” to prevent a waste of the memory.

Abstract: Subject matter disclosed herein relates to remapping memory devices.

Abstract: The present techniques provide systems and methods of controlling access to more than one open page in a memory component, such as a memory bank. Several components may request access to the memory banks. A controller can receive the requests and open or close the pages in the memory bank in response to the requests. In some embodiments, the controller assigns priority to some components requesting access, and assigns a specific page in a memory bank to the priority component. Further, additional available pages in the same memory bank may also be opened by other priority components, or by components with lower priorities. The controller may conserve power, or may increase the efficiency of processing transactions between components and the memory bank by closing pages after time outs, after transactions are complete, or in response to a number of requests received by masters.

Abstract: Systems, methods of operating a memory device, and methods of arbitrating access to a memory array in a memory device having an internal processor are provided. In one or more embodiments, conflicts in accessing the memory array are reduced by interfacing an external processor, such as a memory controller, with the internal processor, which could be an embedded ALU, through a control interface. The external processor can control access to the memory array, and the internal processor can send signals to the external processor to request access to the memory array. The signals may also request a particular bank in the memory array. In different embodiments, the external processor and the internal processor communicate via the control interface or a standard memory interface to grant access to the memory array, or to a particular bank in the memory array, for example.

Abstract: Techniques for data replication are presented. A snap shot request is processed within an environment associated with a local volume by flushing pending Input/Output (I/O) operations into an event packet. The event packet is sent to a replicated volume and processed against the replicated volume to create a snap shot version of the local volume.

Abstract: A configurable memory access controller and related systems and methods. In embodiments described herein, the configurable memory controller is adapted to provide a separate memory access configuration for each of a plurality of memory banks in a given memory system. The memory access configuration provided for each memory bank can either be to leave open or close at least one memory page in each memory bank. In this manner, a memory access configuration can be provided for each memory bank on an individualized basis to optimize memory access times based on the type of data activity in each memory bank. In embodiments described herein, the memory controller can also be configured to allow for dynamic configuration of one or more memory banks. Dynamic configuration involves changing or overriding the memory access configuration for a particular memory bank to optimize memory access times.

Abstract: A memory node for use within a data storage system having a plurality of interconnected memory nodes is provided. The memory node comprises three data input interfaces, three data output interfaces, a memory module for storing data, and a controller coupled to the three data output interfaces, the three data input interfaces, and the memory module. The controller is configured to receive data via one of the three input interfaces, the data having a predetermined destination, read a first portion of the data to determine if the memory node is the predetermined destination, store a second portion of the data on the memory module, if the memory node is the predetermined destination, and transmit the received data via at least one of the three data output interfaces, if the memory node is not the predetermined destination.

Abstract: A memory system with high availability is provided. The memory system includes multiple memory channels. Each memory channel includes at least one memory module with memory devices organized as partial ranks coupled to memory device bus segments. Each partial rank includes a subset of the memory devices accessible as a subchannel on a subset of the memory device bus segments. The memory system also includes a memory controller in communication with the multiple memory channels. The memory controller distributes an access request across the memory channels to access a full rank. The full rank includes at least two of the partial ranks on separate memory channels. Partial ranks on a common memory module can be concurrently accessed. The memory modules can use at least one checksum memory device as a dedicated checksum memory device or a shared checksum memory device between at least two of the concurrently accessible partial ranks.