Abstract: For address generation, a block size and a skip value are obtained, and at least one address, at least one increment value, and a step value are initialized. For a count index not in excess of a block size, iteratively performed are: selection of an output address for output from at least one phase responsive to at least the at least one address; first update of the at least one address as being equal to summation of the at least one increment and the at least one address modulo the block size; and second update of the at least one increment as being equal to summation of the at least one increment and the step value modulo the block size. The selection and the first and second updates are iteratively repeated responsive to increments of the count index to output a sequence of addresses.

Abstract: According to one embodiment, an interleave control device of a memory system includes a memory divided into sections, and a data bus used, in common, for data transfers for the sections, the device comprises a detector and a start module. The detector is configured to detect a transfer of data of a predetermined size during a transfer of data on the data bus to be written to a certain section of the memory or data read from the section. The start module is configured to start a transfer of interleave control data in place of the data to be written or the read data when the detector detects the transfer of the data of the predetermined size.

Abstract: Embodiments that dynamically reorganize data of cache lines in non-uniform cache access (NUCA) caches are contemplated. Various embodiments comprise a computing device, having one or more processors coupled with one or more NUCA cache elements. The NUCA cache elements may comprise one or more banks of cache memory, wherein ways of the cache are horizontally distributed across multiple banks. To improve access latency of the data by the processors, the computing devices may dynamically propagate cache lines into banks closer to the processors using the cache lines. To accomplish such dynamic reorganization, embodiments may maintain “direction” bits for cache lines. The direction bits may indicate to which processor the data should be moved. Further, embodiments may use the direction bits to make cache line movement decisions.

Abstract: A backup method relies on a single secondary storage device, such as a tape storage device, which emulates multiple secondary storage devices. The emulated secondary storage devices are coupled to data sources. Data which is received from the data sources is tagged with respective unique identifiers, interleaved and stored on a removable storage medium, such as a tape. This facilitates maximum usage of the media access bandwidth of the single secondary storage device.

Abstract: A system and method for increasing cache size is provided. Generally, the system contains a storage device having storage blocks therein and a memory. A processor is also provided, which is configured by the memory to perform the steps of: categorizing storage blocks within the storage device as within a first category of storage blocks if the storage blocks that are available to the system for storing data when needed; categorizing storage blocks within the storage device as within a second category of storage blocks if the storage blocks contain application data therein; and categorizing storage blocks within the storage device as within a third category of storage blocks if the storage blocks are storing cached data and are available for storing application data if no first category of storage blocks are available to the system.

Abstract: Circuit, method, and computer program for reordering data units of a data block in accordance with a first pre-determined function. The method includes, for each data unit of the data block—(i) generating an address corresponding to a memory location of a single-port memory module into which the data unit is to be stored, and (ii) storing the data unit in the memory location based on the address generated for the data unit. Each address is generated in accordance with the first pre-determined function, and each memory location of the single-port memory has a different delay associated with the memory location. The method further includes reading each data unit out of the single-port memory in accordance with the first pre-determined function, wherein data units of the data block are reordered based on each different delay associated with each memory location.

Abstract: A non-uniform interleaving scheme in a multiple channel DRAM system comprises associating memory data with a memory address, associating address zones to predetermined ranges of memory addresses and associating predetermined interleaving granularities with the address zones. Memory data is interleaved across two or more memory channels such that a predetermined interleaving granularity is applied to each address zone.

Abstract: Systems and methods for reducing problems and disadvantages associated with physically asymmetrical memory structures are disclosed. A method for configuring memories in an information handling system having a plurality of memories, each memory local to one of a plurality of nodes, and wherein at least one memory of the plurality of memories has a different memory capacity than at least one other memory of the plurality of memories is provided. The method may include determining a smallest memory capacity of the plurality of memories. The method may also include allocating a node-interleaved memory using a portion of each memory equal to the smallest memory capacity. For each particular memory not fully allocated to the node-interleaved memory, each portion of each particular memory not allocated to the node-interleaved memory may be associated with a node local to the particular memory.

Abstract: A magnetic recording hard disk drive (HDD) has at least one read/write head that accesses more than one disk surface. The HDD is able to transfer data to and from the host computer seamlessly without interruption during the time the head is being moved from one disk surface to another disk surface. Nonvolatile solid state memory is associated with pairs of disk surfaces. During the time of a head transfer from one disk surface in the pair to the other disk surface, data is read from or written to the associated nonvolatile memory. The data is first read from or written to one disk surface, then from or to the nonvolatile memory, and then, after completion of the head transfer, from or to the other disk surface, thereby allowing seamless uninterrupted transfer of data.

Abstract: Some of the embodiments of the present disclosure provide an apparatus comprising a command cancellation channel (CCC) including a plurality of stages, the CCC configured to receive a first memory address of a sequence of memory addresses and a corresponding first modification command, determine that at least a first stage of the plurality of stages includes the first memory address and a corresponding second modification command, and erase the first memory address or cancel the second modification command while shifting the first memory address and the second modification command from the first stage to a second stage. Other embodiments are also described and claimed.

Abstract: A method and an apparatus that allocate a stream memory and/or a local memory for a variable in an executable loaded from a host processor to the compute processor according to whether a compute processor supports a storage capability are described. The compute processor may be a graphics processing unit (GPU) or a central processing unit (CPU). Alternatively, an application running in a host processor configures storage capabilities in a compute processor, such as CPU or GPU, to determine a memory location for accessing a variable in an executable executed by a plurality of threads in the compute processor. The configuration and allocation are based on API calls in the host processor.

Abstract: Concurrent threads in a multithreaded processor share access to a memory, with any location in the shared memory being accessible by any thread. In one embodiment, the shared memory has multiple independently-addressable memory banks, and one location per bank can be accessed in parallel. Parallel processing engines executing the threads generate a group of parallel memory access requests. Address conflict logic determines whether the requests can be satisfied in parallel (e.g., based on bank access constraints) and serializes the requests to the extent needed to avoid conflicts. In some embodiments, data read from one address in the shared memory can be broadcast to multiple processing engines.

Abstract: Access to a memory area by a first processor that executes a first processor program and a second processor that executes a second processor program is granted to one of the first processor and the second processor at a time. Access to the memory area by the first processor and the second processor are cyclically uniquely allocated (e.g., t?[(ad mod m)=o]) between the first and the second processor by the first and second processor programs.

Abstract: An apparatus that enables data to be input to and output from a first processing device that performs an arithmetic operation and outputs first data, a second processing device that performs an arithmetic operation and outputs second data that has a number of bits which is smaller than the first data, a first storage device and a second storage device. The apparatus includes a data dividing unit and a storage control unit. The data dividing unit divides the first data output from the first processing device. The storage control unit causes the divided first data to be stored in the first storage device and the second storage device and causes the second data output from the second processing device to be stored in one of the first and second storage devices.

Abstract: A packet transmission control apparatus includes a plurality of controllers, an arbitrator, a BUSY control circuit, and a memory. The controller controls a transmission of a packet to an interface and manages a request for data to a memory and a reception of data from the memory. The arbitrator selects a controller to be used from among the plurality of controllers. The BUSY control circuit recognizes a BUSY state of a control unit at destination of a packet. The memory stores data to be requested.

Abstract: In a particular embodiment, a dynamic interleaving system changes the number of interleaving channels of a multi-channel memory based on a detected level of bandwidth requests from a plurality of master ports to a plurality of slave ports. At a low level of bandwidth requests, the number of interleaving channels is reduced.

Abstract: A memory access mode detection circuit and method for detecting and initiating memory access modes for a memory device. The memory access mode detection circuit receives the memory address signals, the control signals, and the clock signal and generates a first mode detection signal in response to receipt of the memory address signals or a first combination of control signals. An first mode initiation signal is generated a time delay subsequent to the detection signal to initiate the first mode memory access operation. In response to receipt of a second combination of control signals and an active clock signal, the memory access mode detection circuit further generates a second mode detection signal to initiate a second mode memory access operation and to suppress generation of the first mode detection signal, thereby canceling the first mode memory access operation.

Abstract: A memory system communicates at least partially temporally overlapping write-data sequences associated with independent column write accesses on data links from a memory controller to a memory device via bidirectional links. Each of these write-data sequences may be associated with a different bank set in the memory IC. These bank sets may be micro-threaded so that each bank set is independently addressable and can concurrently perform operations associated with independent commands, including simultaneous column read/write. Furthermore, temporally interleaved data-mask information for the write-data sequences may be communicated from the memory controller to the memory IC via a data-mask link, so that alternate bits in the interleaved data-mask information may correspond to different write sequences.

Abstract: A reconfigurable interleaver is provided, configured to produce a sequence of interleaved addresses, configurable for at least two different interleaving patterns. The reconfigurable interleaver comprises a plurality of reconfigurable counters. The number of values that the counters count is configurable as are their start values. The interleaver further comprises a plurality of memory in which the counters indicate memory positions so that values may be retrieved. Computational elements compute an interleaved sequence of addresses in dependency on the retrieved values. By reconfiguring the counters and possibly changing the content of the memories, the interleaver may be configured for a different interleaving pattern.

Abstract: A memory storage system of an embodiment includes a nonvolatile memory unit and memory control circuitry coupled to the memory unit. Storage locations of the memory unit are organized into one or more sub-blocks configured to store sectors of information from a host. The sectors of information can be identified by sector numbers of a predetermined order. The memory control circuitry is configured to write a sector of information to a location of a particular sub-block of a particular block. The memory control circuitry is further configured to write a sector of information to a location of a sub-block of the particular block that is other than the particular sub-block, regardless of the predetermined order of the sector numbers of the sectors of information. The memory control circuitry is further configured to write the sectors of information to the locations of the sub-blocks of the particular block substantially concurrently.

Abstract: A graphics system utilizes virtual memory pages and has a partitioned graphics memory that includes memory elements. The system supports having an non-power of two number of active memory elements. Additionally, a partition swizzling operation is used to adjust the partition numbers associated with individual units of virtual memory allocation on particular virtual memory pages to achieve a selected partition interleaving pattern.

Abstract: An apparatus comprising a plurality of buffers and a channel router circuit. The buffers may be each configured to generate a control signal in response to a respective one of a plurality of channel requests received from a respective one of a plurality of clients. The channel router circuit may be configured to connect one or more of the buffers to one of a plurality of memory resources. The channel router circuit may be configured to return a data signal to a respective one of the buffers in an order requested by each of the buffers.

Abstract: A Flash memory system includes N flash devices, where N is an integer, each flash device having a flash device interface consisting of a control signal line, a R/B signal line, and a I/O signal line, and wherein each flash device has an operating speed of s. A logic block is connected to each flash device interface, and is further connected to a controller which whose interfaces also has a control signal line, a R/B signal line, and a I/O signal line, so that controller operates at an operating speed of N times s, and wherein the logic block controls each flash device simultaneously.

Abstract: Memory control techniques for dual channel lockstep configurations are disclosed. In accordance with one example embodiment, a memory controller issues two burst-length 4 DRAM commands to two double-data-rate (DDR) DRAM sub-channels behind a memory buffer (e.g., FB-DIMM or buffer-on-board). The two commands are in time-staggered lockstep. The time-stagger allows data coming back from the two back-side DDR sub-channels to flow naturally on the host channel without conflict. Multiple DIMMs can be used to obtain chip-fail ECC capabilities and to reclaim at least some of the lost performance imposed by the burst-length of 4 s typically associated with dual channel lockstep memory controllers. The techniques can be implemented, for instance, with a buffered memory solution such as fully buffered DIMM (FB-DIMM) or buffer-on-board configurations.

Abstract: A disclosed circuit includes circuitry for coupling to a volatile memory, circuitry for coupling to a nonvolatile NAND flash memory, and circuitry that: (i) receives a volatile memory request from a processor and satisfies the volatile memory request by accessing the volatile memory, and (ii) receives a nonvolatile NOR flash memory read request from the processor and satisfies the NOR read request by accessing both the NAND flash memory and the volatile memory. The circuit may also include circuitry that receives a volatile memory request from another processor and satisfies the volatile memory request from the other processor by accessing the volatile memory, and circuitry that receives a NAND flash memory read request from the other processor and satisfies the NAND read request by accessing the NAND flash memory. Multiprocessor systems including the circuit are described, as is a method for satisfying a NOR flash memory read request.

Abstract: A system for pushing data, the system includes a source node that stores a coherent copy of a block of data. The system also includes a push engine configured to determine a next consumer of the block of data. The determination being made in the absence of the push engine detecting a request for the block of data from the next consumer. The push engine causes the source node to push the block of data to a memory associated with the next consumer to reduce latency of the next consumer accessing the block of data.

Abstract: A memory bank contains a plurality of memories, a first Butterfly network is configured to apply memory addresses to the memory bank, and a second Butterfly network is configured to pass data to or from the memory bank. A control signal is generated for the first and second Butterfly networks in accordance with a multiple access rule to enable parallel access to the memory bank, without memory access conflict, for one of a linear order and an interleaved order. The method and apparatus is particularly advantageous for use in turbo decoding.

Abstract: Apparatus and methods are disclosed, such as those that store data in a plurality of non-volatile integrated circuit memory devices, such as NAND flash, with convolutional encoding. A relatively high code rate for the convolutional code consumes relatively little extra memory space. In one embodiment, the convolutional code is spread over portions of a plurality of memory devices, rather than being concentrated within a page of a particular memory device. In one embodiment, a code rate of m/n is used, and the convolutional code is stored across n memory devices.

Abstract: Status indication in a system having a plurality of memory devices is disclosed. A memory device in the system includes a plurality of data pins for connection to a data bus. The memory device also includes a status pin for connection to a status line that is independent from the data bus. The memory device also includes first circuitry for generating, upon completion of a memory operation having a first duration, a strobe pulse of a second duration much shorter than the first duration. The strobe pulse provides an indication of the completion of the memory operation. The memory device also includes second circuitry for outputting the strobe pulse onto the status line via the status pin.

Abstract: A memory system comprises a memory including a plurality of bits arranged as one or more words. Each bit in each word is capable of being programmed either to a particular logical state or to another logical state. A variable data width controller is in communication with the memory. The variable data width controller comprises an adder to determine a programming number of bits in a word to be programmed into a memory. Each bit to be programmed is in the particular logical state. A partitioning block divides the word in to two or more sub-words when the programming number exceeds a maximum number. A switch is in communication with the partitioning block. The switch sequentially provides one or more write pulses. Each write pulse enables a separate communication path between the memory and one of the word and the sub-words.

Abstract: Included are embodiments for subframe interleaving. At least one embodiment of a method includes receiving at least one subframe, the at least one subframe being derived from a plurality of frames of data and interspersing at least a portion of the at least one subframe according to a predetermined subframe interleaving strategy.

Abstract: In one embodiment, the present invention includes a deinterleaver having an input interface to receive orthogonal frequency division multiplexing (OFDM) symbols from a demodulator, a memory coupled to the input interface to store the OFDM symbols, an output interface coupled to the memory to receive the OFDM symbols stored in the memory, and a digital phase lock loop (PLL) to control and adjust a reading rate of data from the memory responsive to dynamic and static channel conditions.

Abstract: A method and system for decreasing power consumption in memory arrays having usage-driven power management provides decreased power consumption in the memory array of a processing system. Per-page usage information is gathered on memory by a memory controller and periodically evaluated by software. The software distinguishes between more frequently accessed pages and less frequently accessed pages by analyzing the gathered usage information and periodically migrates physical memory pages in order to group less frequently accessed pages and more frequently access pages in separately power-managed memory ranks. When used in conjunction with a usage-driven power management mechanism, the ranks containing the less frequently accessed pages can enter deeper power-saving states and/or any power-saving state for longer periods.

Abstract: To store N bits of M?2 logical pages, the bits are interleaved and the interleaved bits are programmed to [N/M] memory cells, M bits per cell. Preferably, the interleaving puts the same number of bits from each logical page into each bit-page of the [N/M] cells. When the bits are read from the cells, the bits are de-interleaved. The interleaving may be deterministic or random, and may be effected by software or by dedicated hardware.

Abstract: A signal processing circuit includes a signal processing section which generates first address data and second address data in accordance with data processing, reads data stored in an external memory based on the first address data and the second address data for performing a predetermined processing, and outputs processed data along with the first address data and the second address data, an address conversion section which, receiving the first address data and the second address data input thereto, holds at least 1 bit of the first address and outputs third address data, and also adds the at least 1 bit of the held first address data to the second address and outputs fourth address data, and a data interface which performs a writing operation or a reading operation of the data processed by the signal processing section with respect to the external memory on the basis of a time when the address conversion section outputs the third address data and the forth address data.

Abstract: A disjoint instruction for accessing operands in memory while executing in a processor of a plurality of processes interrogates a state indicator settable by other processors to determine if the disjoint instruction accessed the operands without an intervening store operation from another processor to the operand. A condition code is set based on the state indicator.

Abstract: A device may include a group of requestors issuing requests, a memory that includes a set of memory banks, and a control block. The control block may receive a request from one of the requestors, where the request includes a first address. The control block may perform a logic operation on a high order bit and a low order bit of the first address to form a second address, identify one of the memory banks based on the second address, and send the request to the identified memory bank.

Abstract: Provided are an apparatus and method for partially accessing a DRAM. The apparatus for partially accessing a DRAM includes a memory controller. The memory controller includes a first sub-controller which controls a first DRAM and a second sub-controller which controls a second DRAM. Accordingly, a garbage cycle, i.e., an operation which wastes data transfer bandwidth, that may generate when a related art DRAM accessing apparatus is used, is removed.

Abstract: A method to associate a storage policy with a cache region is disclosed. In this method, a cache region associated with an application is created. The application runs on virtual machines, and where a first virtual machine has a local memory cache that is private to the first virtual machine. The first virtual machine additionally has a shared memory cache that is shared by the first virtual machine and a second virtual machine. Additionally, the cache region is associated with a storage policy. Here, the storage policy specifies that a first copy of an object to be stored in the cache region is to be stored in the local memory cache and that a second copy of the object to be stored in the cache region is to be stored in the shared memory cache.

Abstract: In one embodiment, an apparatus comprises a queue comprising a plurality of entries and a control unit coupled to the queue. The control unit is configured to allocate a first queue entry to a store memory operation, and is configured to write a first even offset, a first even mask, a first odd offset, and a first odd mask corresponding to the store memory operation to the first entry. A group of contiguous memory locations are logically divided into alternately-addressed even and odd byte ranges. A given store memory operation writes at most one even byte range and one adjacent odd byte range. The first even offset identifies a first even byte range that is potentially written by the store memory operation, and the first odd offset identifies a first odd byte range that is potentially written by the store memory operation.

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: A memory access method intended for a memory required to provide an interval of a predetermined number of clock cycles or longer between successive occurrences of access when the same bank is successively accessed, and that eliminates an idle time between successive occurrences of access to allow for improved performance. Pieces of data are written into 0th, the first, the second, and the third banks, respectively. No idle time is caused between successive occurrences of access because different banks are successively accessed. Since a burst length of each of the pieces of data is eight, an interval of 16 cycles which is longer than 15 cycles is provided between a start of writing of first data and a start of second writing of data. Accordingly, no idle time is caused also between completion of writing of the first data and start of writing of the second data.

Abstract: Methods and apparatus provide for a Dynamic Interleaver to modify the interleaving distribution spanning physical memory modules. Specifically, dynamic interleaving provides the ability to increase the number of interleaved physical memory modules when a current interleaved group of memory locations is experiencing heavy use. By increasing the number of interleaved memory locations, a system can make optimal use of memory by allowing more parallel accesses to physical memory during the period of heavy utilization. However, if the current interleaved group of memory locations experience low use, the Dynamic Interleaver can choose to interleave across fewer physical memory modules and apply power management techniques to those memory locations that are no longer being accessed. Prior to “re-interleaving” interleaved memory locations, the Dynamic Interleaver migrates data out of the current interleaved memory locations.

Abstract: A backup method relies on a single secondary storage device, such as a tape storage device, which emulates multiple secondary storage devices. The emulated secondary storage devices are coupled to data sources. Data which is received from the data sources is tagged with respective unique identifiers, interleaved and stored on a removable storage medium, such as a tape. This facilitates maximum usage of the media access bandwidth of the single secondary storage device.

Abstract: An object-based storage system comprising a host system capable of executing applications for and with an object-based storage device (OSD). Exemplary configurations include a call interface, a physical layer interface, an object-based storage solid-state device (OSD-SSD), and are further characterized by the presence of a storage processor capable of processing object-based storage device algorithms interleaved with processing of physical storage device management. Embodiments include a storage controller capable of executing recognition, classification and tagging of application files, especially including image, music, and other media. Also disclosed are methods for initializing and configuring an OSD-SSD device.

Abstract: In one embodiment, an authentication module includes: a memory module that a plurality of data elements of an input interleaved signal are written to and read from; and a memory access controller configured to write the data elements of the input interleaved signal to the memory module sequentially in accordance with address information in a specific writing order commonly set between different signal formats of interleaved signals, and read the data elements written to the memory module from the memory module sequentially in accordance with address information in a specific reading order commonly set between the different signal formats, and output the read data elements as a restore signal.

Abstract: A memory system, in particular a buffered memory system, e.g., a fully buffered memory system, a method for operating a memory system, and a device for use with a memory system is disclosed. The memory system may include a first buffered memory module, and a second buffered memory module, wherein the first and the second buffered memory modules are adapted to be accessed in parallel. According to a further embodiment of the invention, a device is provided which is adapted to map consecutive accesses to the first or the second memory module to a parallel access of both the first and the second memory module.

Abstract: A RAM mapping table is restored from flash memory using plane, block, and page addresses generated by a physical sequential address counter. The RAM mapping table is restored following a plane-interleaved sequence generated by the physical sequential address counter using interleaved bits extracted from the lowest bits of the logical block index. These plane-interleave bits are split into a LSB and a MSB, with middle physical block bits between the LSB and MSB. The physical sequential address counter generates a physical block number by incrementing the plane-interleave bits before the middle physical block bits, and then relocating the MSB to above the middle physical block bits. This causes blocks to be accessed in a low-high sequence of 0, 1, 4096, 4097, 2, 3, 4098, 4099, etc. in the four planes of flash memory. Background recycling and ECC writes are also performed.

Abstract: An interleaving apparatus may include a first buffer unit configured to buffer input data in units having a size of a sector to generate sector unit data, an encoding unit configured to encode the sector unit data and generate a plurality of parity codes based on the encoding, a second buffer unit configured to interleave the sector unit data and the parity codes and generate interleaving data based on the interleaving, the second buffer unit including a plurality of output buffers configured to store the interleaving data, and an output unit configured to output the interleaving data.

Abstract: Time and frequency de-interleaving of interleaved data in an Integrated Services Digital Broadcasting Terrestrial (ISDB-T) receiver includes exactly one random access memory (RAM) buffer in the ISDB-T receiver that performs both time and frequency de-interleaving of the interleaved data and a buffer address calculation module for generating buffer address in the buffer. The system performs memory sharing of the time and frequency de-interleaver for ISDB-T receivers and reduces the memory size required for performing de-interleaving in an ISDB-T receiver and combines the frequency and time de-interleaver buffers into one RAM thereby reducing the memory size.