Abstract: A first memory portion of a plurality of memory portions is configured to determine a designated position of the first memory portion (in a predefined sequence of the plurality of memory portions), and to receive a sub-request conveyed to the plurality of memory portions in the first memory device. The sub-request has a single contiguous instruction portion and a plurality of data segments. The single contiguous instruction portion has a single relative memory address and a single set of one or more instructions to write the data segments. The first memory portion detects that the received sub-request includes an instruction to write data, and in response, identifies a first data segment allocated to the first memory portion, places the first data segment into a buffer of the first memory portion, and writes the buffered first data segment to a location in non-volatile memory of the first memory portion.

Abstract: Described herein are systems and methods to prevent a controller in a DDIO (data direct input output) system from shifting currently-required data out of a cache memory. In one embodiment, a compute element disables caching of some specific addresses in a non-cache memory, but still enables caching of other addresses in the non-cache memory, thereby practically disabling the DDIO system, so that data sets not currently needed are placed in the addresses in the non-cache memory which are not cached. As a result, currently-required data are not shifted out of cache memory. The compute element then determines that the data sets, which formerly avoided being cached, are now required. The system therefore copies the data sets that are now required from addresses in non-cache memory not accessible to cache memory, to addresses in non-cache memory accessible to cache memory, thereby allowing the caching and processing of such data sets.

Abstract: An input/output virtualization (IOY) host controller (HC) (IOV-HC) of a flash-memory-based storage device is disclosed. In one aspect, an IOV-HC is coupled to input/output (I/O) clients via corresponding client register interfaces (CRIs), and is also coupled to a flash-memory-based storage device. The IOV-HC comprises transfer request list (TRL) slot offset registers indicating slots of a shared TRL that are assigned as base slots to each of the CRIs. The IOV-HC further comprises TRL slot count registers indicating how many slots of the shared TRL are assigned to each of the CRIs. When a transfer request (TR) directed to the flash-memory-based storage device is received from a CRI, the IOV-HC is configured to map the TR to a slot of the shared TRL based on a TRL slot offset register and a TRL slot count register of the plurality of TRL slot count registers corresponding to the CRI.

Abstract: Systems and methods for metablock relinking may be provided. A first physical block of a first metablock may be determined to have a different health than a second physical block of a second metablock based on health indicators of the first and second physical blocks. Each of the health indicators may indicate an extent to which a respective one of the first and second physical blocks may be written to and/or erased before the respective one of the first and second physical blocks becomes defective. The first physical block of the first metablock may be replaced with the second physical block of the second metablock based on a determination that the health of the first physical block of the first metablock is different than the health of the second physical block of the second metablock.

Abstract: A scheduling device according to one embodiment includes an access request accepting section and an access request selecting section. The access request accepting section is configured to accept access requests from requesters. The access request selecting section is configured to select a first access request as a reference for access request selection from among the accepted access requests, select an access request transferable in a bank interleave (BI) mode with respect to the first access request, and select an access request transferable in a continuous read/write (CN) mode in response to a determination that there is no access request transferable in the BI mode, or that the preceding access request was in the BI or the CN mode. The access request selecting section is configured to repeat the selections in response to a determination that there is no access request transferable in the BI mode and in the CN mode.

Abstract: For browser cache cleanup, to consider for eviction a data item stored in a cache of a browser application in a device, a probability that the data item will be needed again during a period after the eviction is computed. A type is determined of a network that will be available at the device during the period. A cost is computed of obtaining the data item over a network of the type, from a location of the device during the period. Using the probability and the cost, a weight of the data item is computed. The weight is associated with the data item as a part of associating a set of weights with a set of data items in the cache. The data item is selected for eviction from the cache because the weight is a lowest weight in the set of weights.

Abstract: An apparatus includes an operand cache for storing operands from a register file for use by execution circuitry. In some embodiments, eviction priority for the operand cache is based on the status of entries (e.g., whether dirty or clean) and the retention priority of entries. In some embodiments, flushes are handled differently based on their retention priority (e.g., low-priority entries may be pre-emptively flushed). In some embodiments, timing for cache clean operations is specified on a per-instruction basis. Disclosed techniques may spread out write backs in time, facilitate cache clean operations, facilitate thread switching, extend the time operands are available in an operand cache, and/or improve the use of compiler hints, in some embodiments.

Abstract: A processor system (10) includes: a first memory controller (16) that controls writing/reading data to/from a first memory (60); a second memory controller (17) that controls writing/reading data to/from a second memory (70); a first processor (13) that inputs and outputs the data from and to the first memory through a bus (14); a second processor (11) that inputs and outputs processed data from and to the second memory through the bus; and a management unit 32 that deallocates an address range corresponding to the second memory from the first process and allocates the address range to the second processor.

Abstract: According to one embodiment, a system includes first to third managers and a storage unit. The first manager generates read requests corresponding to read-unit data items read by a read command received from an device, and manages first information indicating the state of transmission of the read-unit data items to the device. The storage unit temporarily stores the read-unit data items read from nonvolatile memories in a random order, based on the read requests. The second manager manages second information indicating whether each read-unit data item has been read from the nonvolatile memories. The third manager transmits, based on the first and second information, the read-unit data items to the device in an order designated by the read command, the read-unit data items being stored in the storage unit in a random order.

Abstract: An information processing device includes a plurality of processors including an Acquire side processor and a Release side processor, and a shared memory. The Acquire side processor and the Release side processor includes a cache, a memory access control unit in the Release side processor configured to issue a StoreFence instruction for requesting a guarantee of completing the cache invalidation by the Acquire side processor, a memory access control unit in the Acquire side processor configured to issue a LoadFence instruction in response to the StoreFence instruction for guaranteeing completion of the cache invalidation in accordance with the invalidation request from the shared memory after completing a process for the cache invalidation, and an invalidation request control unit configured to perform a process for invalidating the cache in accordance with the invalidation request from the shared memory.

Abstract: A data storage system incorporating a write-caching subsystem that implements a steady-state media-based cache is described. The steady-state of the media-based cache can be obtained by directing non-sequential write commands and data received from the host device to multiple independent cache locations and, thereafter, selectively copying or moving such data between the caches so that none of the caches are either too full or too empty. In this manner, a non-sequential write command can be cached in a power-safe manner until it is efficient and/or convenient to write such data to the mainstore portion of the physical media.

Abstract: System on a Chip (SoC) devices include two packetized memory buses for conveying local memory packets and system interconnect packets. In an in-situ configuration of a data processing system two or more SoCs are coupled with one or more hybrid memory cubes (HMCs). The memory packets enable communication with local HMCs in a given SoC's memory domain. The system interconnect packets enable communication between SoCs and communication between memory domains. In a dedicated routing configuration each SoC in a system has its own memory domain to address local HMCs and a separate system interconnect domain to address HMC hubs, HMC memory devices, or other SoC devices connected in the system interconnect domain.

Abstract: A search system is obtained by combining a TCAM and a search engine not using the TCAM. The search engine not using the TCAM is constructed using a general-purpose memory cell structure, and includes a different-sized memory spaces each corresponding to an effective bit length of search target data.

Abstract: An input/output virtualization (IOY) host controller (HC) (IOV-HC) of a flash-memory-based storage device is disclosed. In one aspect, an IOV-HC is coupled to input/output (I/O) clients via corresponding client register interfaces (CRIs), and is also coupled to a flash-memory-based storage device. The IOV-HC comprises transfer request list (TRL) slot offset registers indicating slots of a shared TRL that are assigned as base slots to each of the CRIs. The IOV-HC further comprises TRL slot count registers indicating how many slots of the shared TRL are assigned to each of the CRIs. When a transfer request (TR) directed to the flash-memory-based storage device is received from a CRI, the IOV-HC is configured to map the TR to a slot of the shared TRL based on a TRL slot offset register and a TRL slot count register of the plurality of TRL slot count registers corresponding to the CRI.

Abstract: A device includes a host including a main memory, and semiconductor memory including a nonvolatile semiconductor memory, memory unit, and controller. The nonvolatile semiconductor memory stores first address information. The memory unit stores second address information as part of the first address information. The controller accesses the nonvolatile semiconductor memory based on the second address information. Third address information is stored in the main memory, and is part or all of the first address information. The controller uses the third address information when accessing the nonvolatile semiconductor memory if address information to be referred is not stored in the second address information.

Abstract: The present invention relates to a programming mode for improving the reliability of a multi-layer storage flash memory device in a semiconductor storage field. The present invention provides several programming modes for improving the reliability of a multi-layer storage flash memory device and switching control methods thereof, based on the technical conception of skipping some specific logic pages in the programming process to reduce the impact of the floating gate coupling effect on the operation of the flash memory. By skipping some logic pages, the present invention effectively reduces the floating gate coupling effect in the horizontal, diagonal and vertical directions of the multi-layer storage flash memory in the programming process. Therefore, the error rate is reduced, the service life of the device is prolonged, and the reliability of the whole system is enhanced.

Abstract: A first cache is provided to cache a first portion of a first block of digital content received over a network connection shared between a first user associated with the first cache and at least one second user. The first cache caches the first portion in response to the first user or the second user(s) requesting the first block. The first cache selects the first portion based on a fullness of the first cache, a number of blocks cached in the first cache, or a cache eviction rule associated with the first cache.

Abstract: A method of operating a memory controller controlling a nonvolatile memory device including a user area and a meta area is provided. The method includes selecting a source block among a plurality of memory blocks included in the user area, loading a mapping table stored in the meta area on the basis of a sub-bitmap of the selected source block, and generating a valid page layout constituted by valid pages among pages included in the source block on the basis of the loaded mapping table. The sub-bitmap includes information of a valid mapping table with respect to the selected source block.

Abstract: The present invention addresses the problem of providing a migration system and a migration method by which a completion timing of a live migration of virtual machines can be adjusted. The migration system (1) comprises: a transfer means (61A) for transmitting memory data of the virtual machines from a transfer source physical host (31) to a transfer destination physical host (32) to synchronize data of the virtual machines on the physical host (31) and the virtual machines on the physical host (32); a determination means (51A) for determining, for each of the virtual machines, whether the data of the virtual machine (81A) on the transfer source physical host (31) is synchronized with the data of the virtual machine (81B); and a control means (10) for issuing an instruction of switching from the virtual machines on the physical host (31) to the virtual machines on the physical host (32), if the data of all the virtual machines is synchronized based on the determination result.

Abstract: A method for command processing in a memory controller includes receiving a serial input signal including a series of binary digits, capturing the binary digits at ones of odd locations or even locations of the serial input signal to form a first sub-series, capturing the binary digits at other ones of the odd locations or the even locations of the serial input signal to form a second sub-series, comparing the first and second sub-series, and performing a command represented by the first sub-series, if the first and second sub-series are complementary to each other.