Abstract: Bus address, function and system information in relation to bus requests are maintained in a centralized location (702). Parallel access to the centralized data is facilitated through the use of pointers to the centralized location. Bus transaction operations needing access to the centralized data are simultaneously connected to the data through the use of the pointer control (610), rather than requiring the data to be sequentially transmitted to the bus transaction operations as required.

Abstract: Method and device for reading data from a semiconductor device, where tR is a read operation time, tT is a buffer transfer time, and tH is a host transfer time, where at least two of tR, tT, and tH may be overlapped to reduce a total transfer time.

Abstract: Various approaches for allocating storage for a file are disclosed. In one approach, in response to each call to allocate an available portion of storage, one of a plurality of allocation approaches is selected based on a value of a file attribute associated with the file. If a first one of the allocation approaches is selected, a portion of storage is selected for storage of data using an approach that emphasizes storage of data in sequential physical storage. If a second one of the allocation approaches is selected, a portion of storage using an approach that emphasizes maintaining concurrent access to the file.

Abstract: A memory arrangement is provided, which has a programmable memory and a first buffer memory associated with the programmable memory, to which buffer memory, in the case of a command access, at least one command following the accessed command is written. A second buffer memory may also be provided, to which buffer memory, in the case of a data access, at least one datum following the accessed datum is written. Also provided is a method for reading from a memory arrangement during program execution, wherein presence of a command access or a data access recognized, and a command following the accessed command is written to a first buffer memory and a datum following the accessed datum is written to a second buffer memory. Thus, in this manner, a separate buffer memory is described for data accesses, and thus the content of the buffer for command accesses is not overwritten or destroyed when data accesses occur during the program execution.

Abstract: An integrated circuit comprising a memory cell array capable of simultaneously performing data read and write operations is provided. The integrated circuit to which inputs and outputs (IOs) are separately provided and to which a write address and a read address are simultaneously input during one period of a clock signal comprises a plurality of memory blocks, the memory blocks comprising a plurality of sub-memory blocks, a plurality of data memory blocks corresponding to the memory blocks, and a tag memory controlling unit, which writes data to the memory blocks or reads data from the memory blocks in response to the write address or the read address, wherein access to the same sub-memory block is not simultaneously performed when the write address and the read address are the same.

Abstract: Briefly, a system and a method to efficiently track changes in memory or storage areas, for example, in cache memories of computers and electronic systems. A method in accordance with an exemplary embodiment of the invention includes, for example, updating a tracking list with an address and/or a corresponding address to be updated of a changed entry in an intermediate memory. A system in accordance with an exemplary embodiment of the invention may include, for example, a tracking unit to track the locations of potential data discrepancies between a reference memory and an intermediate memory.

Abstract: State information in a processor is managed using a lookup table that has multiple memory circuits, each with multiple entries. Items of state information belonging to a first state version are stored in a first group of the entries, with each entry in the first group being in a different one of the memory circuits. To create an updated state version, the items of state information are copied in parallel from the first group of entries to a second group of entries, with each entry in the second group is in a different one of the memory circuits. The copy in the second group of the item being updated is then replaced with the updated value.

Abstract: A method and apparatus for enqueuing and dequeuing packets to and from a shared packet memory, while avoiding collisions. An enqueue process or state machine enqueues packets for a communication connection (e.g., channel, queue pair, flow). A dequeue process or state machine operating in parallel dequeues packets and forwards them (e.g., to an InfiniBand node). Packets are stored in the shared packet memory, and status/control information is stored in a control memory that is updated for each packet enqueue and packet dequeue. Prior to updating the packet and/or control memory, each process interfaces with the other to determine if the other process is active and/or to identify the other process' current communication connection. If the enqueue process detects a collision, it pauses (e.g., for a predetermined number of clock cycles). If the dequeue process detects a collision, it selects a different communication connection to dequeue.

Abstract: Methods, computer programs, information handling systems, and state machines for performing an atomic write to a data block area are disclosed. The atomic write is an in-place write> The method includes receiving one or more data blocks to write to the data block area; and for each data block received: writing the data block to the depot slot; and writing the data block to the data block area after the data block write to the depot slot is completed.

Abstract: Atomic operations may be implemented on a processor system having a main memory and two or more processors including a power processor element (PPE) and a synergistic processor element (SPE) that operate on different sized register lines. A main memory address containing a primitive is divided into a parity byte and two or more portions, wherein the parity byte includes at least one bit. A value of the parity byte determines which of the two or more portions is a valid portion and which of them is an invalid portion. The primitive is of a memory size that is larger than a maximum size for atomic operation with the PPE and less than or equal to a maximum size for atomic operation with the SPE. Read with reservation and conditional write instructions are used by both the PPE and SPE to access or update a value of the atomic.

Abstract: A multiple computer system is disclosed in which n computers (M1, M2 . . . Mn) each run a different portion of a single application program written to execute only on a single computer. The local memory of each computer is maintained substantially the same by updating all computers with every change made to addressed memory locations. Contention can arise when the same memory location is substantially simultaneously updated by two or more machines because of transmission delays and latency of the communications network interconnecting all the computers. Contention detection and resolution is disclosed. A count value (99) indicative of the cumulative number of times each memory location has been updated is utilized. Contention is indicated if the currently stored count value and the incoming updating count value are the same. A method of echo suppression and a method of echo rejection are disclosed.

Abstract: A multiple computer system is disclosed in which n computers (M1, M2 . . . Mn) each run a different portion of a single application program written to execute only on a single computer. The local memory of each computer is maintained substantially the same by updating all computers with every change made to addressed memory locations. Contention can arise when the same memory location is substantially simultaneously updated by two or more machines because of transmission delays and latency of the communications network interconnecting all the computers. In particular a method of data consolidation which permits contention detection and resolution is disclosed. A count value indicative of the cumulative number of times each memory location has been updated is utilized. Contention is indicated if the currently stored count value and the incoming updating count value are the same.

Abstract: The invention relates to a semiconductor memory module having a plurality of memory chips arranged in at least one row and at least one buffer chip which drives and receives clock signals and command and address signals to the memory chips and data signals to and from the memory chips via a clock, address, command and data bus inside the module and which forms an interface to an external primary memory bus. The semiconductor memory module has an even number of buffer chips arranged on it and all of the memory chips are connected to two respective buffer chips at least by one signal line type from a signal group and just to one of the two buffer chips by the remaining signal lines from the group.

Abstract: A multiple computer system is disclosed in which n computers (M1, M2 . . . Mn) each run a different portion of a single application program written to execute only on a single computer. The local memory of each computer is maintained substantially the same by updating all computers with every change made to addressed memory locations. Contention can arise when the same memory location is substantially simultaneously updated by two or more machines because of transmission delays and latency of the communications network interconnecting all the computers. In particular a method of broadcast memory updating with contention detection and resolution is disclosed which utilizes either a single or plural count value(s) and/or single or plural resolution value(s) for multiple memory locations. The count value is indicative of the number of the sequence of occasions on which a memory location has been updated.

Abstract: A method and system for maintaining a best-case demand redispatch of an instruction to allow for maximizing the time a rejected thread may execute in lookahead execution mode, while maintaining the smallest L1 cache miss penalty supported by the memory subsystem. In response to a demand miss, a load/store unit sends a fetch request to the next level cache. The cache line of the demand miss is examined to identify the critical sector. Once the critical sector is identified, a best-case data return time is determined based on the fastest time the next level cache is able to return the critical sector of the cache line. The load/store unit then sends a speculative warning to the dispatch unit to coincide with the best-case data return, wherein the speculative warning prepares the dispatch unit to resend the instruction for execution as soon as data is available to the processor core.

Abstract: The present invention makes it possible to inexpensively and quickly execute a process of rewriting data stored in a memory, thus reducing the power consumption of an information processing apparatus. In connection with a conventional Read-Modify-Write function, an information processing apparatus 1 first issues a write instruction, and after all the write commands in the write instruction have been issued, issues read commands from the read instruction. That is, the read commands are issued immediately after the write commands without issuing a precharge command from the write instruction or an active command from the read instruction. This serves to avoid executing the precharge and active commands between instructions which commands are unwanted for accesses to the same row address. The adverse effect of a CAS latency can also be avoided. Therefore, it is possible to inexpensively and quickly execute the process of rewriting data stored in the memory.

Abstract: Embodiments of the present invention include a data output circuit that can read data in parallel from a plurality of latches in a pipeline circuit. Even-numbered data and odd-numbered data are simultaneously output over a single clock cycle, and are then converted into DDR data and are then serially output. By moving data in this manner, embodiments of the invention can reduce the number of necessary control signals by as much as 50% over conventional data output circuits.

Abstract: The invention features a method for transferring data to programming engines using multiple memory channels, parsing data over at most two channels in the memory channels, and establishing at most two logical states to signal completion of a memory transfer operation.

Abstract: Embodiments of the present invention provide a media drive capable of improving command processing performance by, when a plurality of commands is queued, shortening seek time and rotational latency, and also effectively making use of the shortened period of time. In one embodiment, a HDD includes a queue capable of storing a plurality of commands, and a queue manager for optimizing the execution order of the plurality of commands on the basis of whether or not the execution of each command requires access to a medium. The queue manager determines the execution order so that medium access processing of accessing a disk for execution, and data transfer processing of transferring data between the HDD and a host, are executed in parallel with each other. For example, read processing and transfer processing are executed in parallel with each other. The read processing is adaptive to read out a read command, data of which does not exist in the cache, from the disk into the cache.

Abstract: In a data processing system in which a host processing apparatus and a storage subsystem are connected via a channel interface, the present invention makes it possible to expand the number of logical device addresses in excess of the device address limitations of the channel interface, and also enhances the performance of parallel access processing for the same logical device. When an access request is generated for a logical device, the host processing apparatus stores the logical device address to be accessed in a prefix command of a channel command word (CCW) for the access request, sets this CCW in a device information block of a frame which complies with the channel interface, sets a parallel access identifier for identifying a plurality of accesses for the same device in a device address of this frame, and then sends this frame to the storage subsystem.

Abstract: Described herein are a method and system for memory access. As the complexity of digital signal processing applications increases, designs may require multiple memory chips. To optimize the bandwidth of the data being accessed from the memory chips, blocks of data are read alternatively from each memory chip. The size of a block of data is determined by the bit width of a word and the number or memory arrays in a chip.

Abstract: A memory controller is connected with a first memory requiring refresh and a second memory not requiring refresh, both of which share part of a bus, comprising: a first memory controller that conducts access control and auto-refresh control for the first memory; a second memory controller that conducts access control for the second memory; and an arbiter that adjusts the timing of outputting a signal generated for the first memory and another signal generated for the second memory to a bus, wherein, with a judgment that the signal from the first memory controller is an auto-refresh request, a refresh request signal for the first memory is outputted even while the second memory is being accessed.

Abstract: A memory device for multichannel continuous or fixed burst mode operation includes multiple burst address counter circuits and associated control logic to minimize latency which would otherwise occur in multichannel operation.

Abstract: This invention is a system and method for simulating performance of one or more data storage systems. This invention may be used in many useful ways including for configuring or modeling a data storage environment, problem isolation, and general design.

Abstract: A technique for recalling data objects stored on media. A queue is created for each medium on which data objects are located, where each request to recall a data object is placed on the queue corresponding to the medium on which the data object is located. A queue is “active” when its corresponding medium is mounted and being used for recall; otherwise the queue is “non-active.” A thread is created for each active queue, where the thread retrieves from a medium the requested items on the active queue. When plural drives are available for mounting and reading media, plural queues may be active concurrently, so that the plural queues' respective threads may recall items from the plural media in parallel. Preferably, the requests on each queue are organized in an order such that the offset locations of the requested items form two monotonically increasing sequences.

Abstract: A memory controller for managing memory requests from a plurality of requesters to a plurality of memory banks is disclosed. The memory controller includes an arbiter, a first path controller, a second path controller, and a synchronizer. The arbiter is configured to receive the memory requests from the plurality of requesters and identify requests for processing responsive to the requested memory banks. The first and second path controllers are coupled to the arbiter and the plurality of memory banks with the first path controller configured to process the first memory request and the second path controller configured to process the second memory request. The synchronizer is coupled between the first path controller and the second path controller for synchronizing the first and second path controllers such that the first and second memory requests processed by the first and second path controllers, respectively, do not conflict.

Abstract: A serial communications architecture for communicating between hosts and data store devices. The Storage Link architecture is specially adapted to support communications between multiple hosts and storage devices via a switching network, such as a storage area network. The Storage Link architecture specifies various communications techniques that can be combined to reduce the overall cost and increase the overall performance of communications. The Storage Link architecture may provide packet ordering based on packet type, dynamic segmentation of packets, asymmetric packet ordering, packet nesting, variable-sized packet headers, and use of out-of-band symbols to transmit control information as described below in more detail. The Storage Link architecture may also specify encoding techniques to optimize transitions and to ensure DC-balance.

Abstract: A method of accessing an integrated circuit memory device can include reading from an address in a first memory sub-block during a first clock cycle. The address of a first data memory block address mapped to the first memory sub-block can be written to during the first clock cycle. The address of a second data memory block address mapped can be written to the second memory sub-block during a second clock cycle immediately subsequent in time to the first clock cycle. Related device are disclosed.

Abstract: In a data processing system having a memory control device including at least two mirrored memory ports, a method, system, and article of manufacture for processing read requests are disclosed herein. In accordance with the method of the present invention, a read request is received on a system interconnect coupling read requestors with memory resources. The received read request is issued only to a specified one of the at least two mirrored memory ports within the memory control device. In response to detecting an unrecoverable error resulting from the read request issued to the one mirrored memory port, the received read request is issued to an alternate of the at least two mirrored memory ports.

Abstract: Transactions are granted concurrent access to a data item through the use of an optimistic concurrency algorithm. Each transaction gets its own instance of the data item, such as in a cache or in an entity bean, such that it is not necessary to lock the data. The instances can come from the data or from other instances. When a transaction updates the data item, the optimistic concurrency algorithm ensures that the other instances are notified that the data item has been changed and that it is necessary to read a new instance, from the database or from an update instance.

Abstract: An instruction memory shared by a number of processing units has a plurality of individually accessible sections. A software program in the instruction memory is distributed among the memory sections. Sequential parts of the software program are in sequential sections. The software program may have a common portion which is repeated in each of the memory sections. Arbiter logic may control which of the processing units accesses which of the memory sections in each memory access cycle.

Abstract: A storage device includes a plurality of memories storing data; and a controller controlling the memories, the controller performing in parallel in a number of the memories, the number being specified by a supplied specifying signal, one of a data writing process for writing data supplied from a connection destination device to which the storage device is connectable and a data reading process for reading data requested by the connection destination device.

Abstract: A method of serializing administrative operations on virtual volumes includes operating a storage system to maintain a plurality of virtual volumes that share a pool of block storage, where each of the virtual volumes containing data stored on one or more physical storage devices. Administrative access to each of the virtual volumes is controlled individually by imposing serialization on administrative operations directed to each virtual volume.

Abstract: A method and apparatus for managing write-to-read turnarounds in an early read after write memory system are presented. Memory controller logic identifies a write operation's bank set, allows a different bank set read operation to issue prior to the write operation's completion, and allows a same bank set read operation to issue once the write operation completes. The memory controller includes operation counter logic, operation selection logic, operation acceptance logic, command formatting logic, and memory interface logic. The operation counter logic receives new-operation-related signals from the operation acceptance logic and, in turn, provides signals to the operation selection logic and the operation acceptance logic as to when to issue a read operation that corresponds to either an even DRAM bank or an odd DRAM bank.

Abstract: A method and apparatus to avoid collisions between row activate and column read or column write commands is presented. A memory controller includes control logic, activate allowed logic, and last column counter logic. The control logic sends particular values to the activate allowed logic and the last column counter logic at the beginning of a read or write operation, such as a new command load value, a read count value, and a write count value. In turn, the control logic receives an activate allowed signal from the activate allowed logic, which indicates the times at which a new activate command may be issued. As a result, the memory controller allows an activate command to commence on “even” command cycles or anytime after the last outstanding column command has been issued.

Abstract: A cache memory system may be is organized as a set of numbered banks. If two clients need to access the cache, a contention situation may be resolved by a contention resolution process. The contention resolution process may be based on relative priorities of the clients.

Abstract: A storage area network simulator, operable to simulate an exchange of calls emanating from a SAN management application to a plurality of manageable entities, allows analyzing SAN management application response to a particular configuration. A capture tool discovers manageable entities interconnected in a particular SAN experiencing undesirable operation. The capture tool provides exemplary calls to an agent, and gathers responses. The exemplary calls enumerate expected responses from the various manageable entities responsive to the agent. The gathered responses take the form of an XML markup script. A simulation plug-in is operative as an interface module (e.g. plug-in) for a test agent in a test environment, such as the management application test facility. The test agent employs the simulation plug-in as the API plug-in for calls emanating from the test agent.

Abstract: The present invention provides a pre-fetch controller and a method thereof for efficiently pre-fetching data from a memory device. The method includes initializing a counter value; fetching a data from the memory and subtracting the counter value by a first value when a pre-fetching is activated; adding a second value to the counter value when a cache hit occurs; comparing the counter value with a first threshold value; and when the counter value is smaller than the first threshold value, stopping pre-fetching the data from the memory.

Abstract: Concurrent read access and exclusive write access are provided in a shared memory architecture to permit one or more devices in the shared memory architecture to maintain read access to a block of memory such as a cache line while one device has exclusive permission to modify that block of memory. By doing so, a device that has permission to modify may make updates to its copy of the block of memory without invalidating other copies of the block of memory, and potentially enabling other devices to continue to read data from their respective copies of the block of memory without having to retrieve the updated copy of the block of memory.

Abstract: System and method for the managing of suspend requests in flash memory devices. The system includes a microcontroller performing a modify operation on a flash memory array, a memory coupled to the microcontroller and storing suspend sequence code for causing a suspension of the modify operation when executed by the microcontroller, and suspend circuitry that receives a suspend request from a user to suspend the modify operation and starts the execution of the suspend sequence code.

Abstract: A nonvolatile semiconductor memory device transmits/receives data to/from a data input/output terminal every j bits (e.g., eight bits). Each of memory cells in a memory cell array can hold data of n bits in correspondence to 2n threshold levels. A write data conversion circuit generates write data from bit data input from the same data input/output terminal in a set of a plurality of data of j bits input at different timings.

Abstract: A memory system includes a plurality of nonvolatile memory chips (CHP1 and CHP2) each having a plurality of memory banks (BNK1 and BNK2) which can perform a memory operation independent of each other and a memory controller (5) which can control to access each of said nonvolatile memory chips. The memory controller can selectively instruct either a simultaneous writing operation or an interleave writing operation on a plurality of memory banks of the nonvolatile memory chips. Therefore, in the simultaneous writing operation, the writing operation which is much longer than the write setup time can be performed perfectly in parallel. In the interleave writing operation, the writing operation following the write setup can be performed so as to partially overlap the writing operation on another memory bank. As a result, the number of nonvolatile memory chips constructing the memory system of the high-speed writing operation can be made relatively small.

Abstract: A memory architecture design and strategy is provided using memory devices that would normally be considered disadvantageous, but by accommodating the data input, output, and other peripheral controller services, overall performance in this mode is optimized. The surprising result is that even though the choice of memory is inappropriate for the task based on the precepts of the prior art, the overall memory system is effective. Bank switching in DDR-SDRAM can be utilized to achieve technological feasibility without resorting to, for example, SRAM.

Abstract: A memory card has a plurality of non-volatile memories and a main controller for controlling the operation of the non-volatile memories. The main controller performs an access control to the non-volatile memories in response to an external access instruction, and an alternate control for alternating an access error-related storage area of the non-volatile memory with other storage area. In the access control, the speeding up of the data transfer between flash memories is achieved by causing the plurality of non-volatile memories to parallel access operate. In the alternation control, the storage areas is made alternative for each non-volatile memory in which an access error occurs.

Abstract: Disclosed is a semiconductor memory device which shortens an external access time when there is contention between an external access and an internal access. The semiconductor memory device includes an arbiter which receives a first entry signal for entering a first access mode (external access) and a second entry signal for entering a second access mode (internal access) and determines priority of the first and second access modes in accordance with an order of receipt of the first and second entry signals. The arbiter sequentially generates a first mode trigger signal corresponding to the first entry signal and a second mode trigger signal corresponding to the second entry signal in accordance with the determined priority. The arbiter executes the first access mode by priority over the second access mode when the arbiter is supplied with the first entry signal with a predetermined period after the second access mode has been determined to have priority.

Abstract: A method, system and computer program product for creating and dynamically selecting an arbiter design within a data processing system on the basis of command history is disclosed. The method includes selecting a first arbiter for current use in arbitrating between requestors for a resource. During operation of said data processing system, an arbiter selection unit detects requests for the resource and selects a second arbiter in response to the detected requests for the resource.

Abstract: In a virtual ground memory array, sneak currents between input/output groups of sensed cells may be reduced by providing at least one column of programmed cells between the input/output groups. The sneak currents may arise when cells in each of two adjacent I/O groups are sensed (or programmed) at the same time.

Abstract: Even if a plurality of tasks that access a plurality of data areas each having the different control method are operated in parallel and the access requests are generated almost simultaneously, the simultaneous accesses to the memory device can be prevented and also a plurality of tasks can be operated in parallel while maintaining a real-time characteristic since the access request contained in the tasks are divided into partial request units by the access-request mediating portion to switch the access requests.

Abstract: A method, apparatus, and computer program product includes serially receiving, from a source, a plurality of forward messages each addressed to one of a plurality of destinations; receiving a plurality of availability signals, each availability signal indicating that one of the destinations is available to accept a forward message; simultaneously sending a forward message to each available destination; simultaneously receiving, after a predetermined period of time, a plurality of reverse messages from the destinations, each reverse message corresponding to one of the forward messages simultaneously sent to an available destination; and serially sending the reverse messages to the source.

Abstract: A data transfer control device including: a buffer controller which allocates a plurality of pipe regions in a packet buffer and controls access to the packet buffer; and a transfer controller which controls data transfer between the pipe regions and corresponding endpoints. The transfer controller performs processing of pausing data transfer between the pipe regions and the endpoints, the buffer controller performs reconstruction processing which includes at least one of deletion, addition, and size change of the pipe regions after the completion of the pause processing, and then the transfer controller resumes the paused data transfer after the reconstruction processing of the pipe regions. Data in the pipe regions before the reconstruction processing is copied to the pipe regions after the reconstruction processing while preventing the data from being erased.