Abstract: A high availability storage system is provided in a server. The server includes a plurality of storage controllers. The storage controllers may be connected to storage enclosures that house the physical devices. If one controller fails, the second controller assumes command of the drive array handled by the failed controller with no interruption of server operation or loss of data. The controllers are connected to the physical drives via a channel or bus, such as a small computer systems interface bus. When two or more teaming controllers are active, the channel or bus may be split to increase throughput. A team driver is provided to direct and redirect requests to the appropriate controllers. The team drive may detect a failed controller, rejoin the bus, and assign control of all logical or physical drives to the remaining active controller. The team driver may also detect a new controller being added to the system, slit the bus, and divide the logical drives between the teaming controllers.

Abstract: A semiconductor memory device is capable of simultaneously reading data and refreshing data and checking whether a data restoring function is operating normally. A data inputting circuit receives data inputted from an external circuit. A parity generating circuit generates parity data from the data input from the data inputting circuit. A memory stores the data input from the data inputting circuit and the parity data generated by the parity generating circuit. A refreshing circuit refreshes the memory. A reading circuit reads the data from the memory. A restoring circuit restores data to be refreshed by the refreshing circuit from other data read normally and corresponding parity data, while the reading circuit is reading data. A data outputting circuit outputs the data read by the reading circuit and the data restored by the restoring circuit. A parity outputting circuit directly reads and outputs the parity data stored in the memory.

Abstract: A system and method for refreshing data in a dynamic random access memory (“DRAM”) is provided, where the system includes a data memory having a plurality of memory banks, a map memory in signal communication with the data memory for translating an internal address of each of the plurality of memory banks into a corresponding external address, a map comparator in signal communication with the map memory for selectively enabling a memory bank in accordance with its external address, a refresh address generator in signal communication with the map comparator for selectively refreshing the enabled memory bank in accordance with its external address, and a refresh counter in signal communication with the refresh address generator for signaling a refresh in accordance with the maximum required refresh time of the enabled memory bank; and where the corresponding method includes determining the maximum required refresh period for each of the memory banks, respectively, prioritizing the memory banks in accordance wit

Abstract: A processor having a limited amount of local memory for storing code and/or data utilizes a program stored in external memory. The program stored in external memory is configured into blocks which can be loaded individually into the local memory for execution. Queuing the individual blocks of code allows the program to be executed by the processor and also facilitates loading of the subsequent code to be executed. A semaphore system can be utilized to indicate which blocks of local memory are available/unavailable. The system can support the interaction of multiple independent programs in external memory.

Abstract: Servers in a network cluster can each store a copy of a data item in local cache, providing read access to these copies through read-only entity beans. The original data item in the database can be updated through a read/write entity bean one of the cluster servers. That cluster server has access to an invalidation target, which contains identification information relating to copies of the data item stored on servers in the cluster. Once the read/write bean updates the data item in the database, an invalidate request can be sent or multicast to all cluster members, or to any read-only bean or server contained in the invalidation target. Each server or read-only bean receiving the request knows to drop any copy of the data item in local cache, and can request a current copy of the data item from the database.

Abstract: A controller comprising a pipeline including a plurality of connected sequential elements wherein a first sequential element is connected to one or more transaction sources; a flow control logic including at least one resource utilization value register; resource allocation logic responsive to a transaction valid signal and one or more adjustment inputs, and comparison logic having a threshold value and a transaction control signal output connected to the one or more transaction sources; pipeline control logic having an adjustment output connected to the resource allocation logic; and a resource control logic having an output connected to an adjustment input of the resource allocation logic.

Abstract: A computer system includes a home node and one or more remote nodes coupled by a node interconnect. The home node includes a local interconnect, a node controller coupled between the local interconnect and the node interconnect, a home system memory, a memory directory including a plurality of entries, and a memory controller coupled to the local interconnect, the home system memory and the memory directory. The memory directory includes a plurality of entries that each provide an indication of whether or not an associated data granule in the home system memory has a corresponding cache line held in at least one remote node. The memory controller includes demand invalidation circuitry that, responsive to a data request for a requested data granule in the home system memory, reads an associated entry in the memory directory and issues an invalidating command to at least one remote node holding a cache line corresponding to the requested data granule.

Abstract: A non-uniform memory access (NUMA) computer system includes at least one remote node and a home node coupled by a node interconnect. The home node contains a home system memory and a memory controller. In response to receipt of a data request from a remote node, the memory controller determines whether to grant exclusive or non-exclusive ownership of requested data specified in the data request by reference to history information indicative of prior data accesses originating in the remote node. The memory controller then transmits the requested data and an indication of exclusive or non-exclusive ownership to the remote node.

Abstract: A hierarchically organized, compilable semiconductor memory circuit having multiple levels with simultaneous access and cache loading. A first level memory portion and at least a next level memory portion are provided as part of the semiconductor memory circuit, wherein the memory portions are associated with separate Data In (DIN) and Data Out (DOUT) buffer blocks for effectuating data operations. DIN buffer blocks of the first level and intermediate levels, if any, are provided with multiplexing circuitry that is selectively actuatable for providing data accessed in the next level memory portion to Local Data In (LDIN) driver circuitry, whereby the accessed data is simultaneously loaded into the first and intermediate levels. Accordingly, extra clock cycles are saved from cache loading of the data used for subsequent memory operations.

Abstract: A single integrated circuit microcontroller 10 including embedded erasable/programmable non-volatile memory 12 having a read protection. Microcontroller 10 can operate within a special mode in which external circuits may access memory 12 by use of input/output pins 18. When microcontroller 10 activates this special mode, a read protection flag 13 within memory 12 is checked. The read protection flag 13 may be set during production of the microcontroller 10 after instructional data or firmware has been installed onto memory 12. If the read protection flag 13 has been set, the contents of memory 12 are erased or reprogrammed prior to allowing access to memory 12. In this manner, external circuits cannot access instructional data or firmware that is stored in memory 12.

Abstract: In order to enable an area of each logical volume to be expanded while continuously using the logical volume and to integrate separate logical volumes in a single continuous area, a storage has logical volume control means for controlling the construction of a logical volume, a logical volume number map in which logical volume construction information is described, and copy means for copying the logical volume. By allowing two or more inner logical numbers to be described per external logical number in the logical volume number map, improved flexibility in combining the logical volumes in the storage is achieved. By copying a plurality of separate logical volumes into a physical continuous area by the copy means, the logical volumes are integrated.

Abstract: A multiprocessor system and method includes a processing sub-system including a plurality of processors and a processor memory system. A network is operable to couple the processing sub-system to an input/output (I/O) sub-system. The I/O sub-system includes a plurality of I/O interfaces each operable to couple a peripheral device to the multiprocessor system. The I/O interfaces each include a local memory operable to store a copy of data from the processor memory system for use by a corresponding peripheral device and to delete the copy at a first time event. A directory for the processor is operable to identify the data as owned upon providing the copy to the I/O sub-system and to identify the data as unowned at a second time event.

Abstract: A Snoop Filter for use in a multi-node processor system including different nodes of multiple processors and corresponding processor caches is provided with a Pseudo Least-Recently-Used (PLRU) replacement algorithm to identify a least-recently-used (PLRU) line from the plurality of lines in the cache array for update to reflect lines that are replaced in the processor caches.

Abstract: The present invention relates to a cache directory configuration method and an information processing device that implements the same. In an embodiment of this invention, each cache directory is divided up into a plurality of units that can be operated in a parallel manner. A plurality of search requests can be processed by each cache directory concurrently. Thus this embodiment allows the hardware requirements for the cache directory to be restricted while providing cache directory search performance higher than that of the conventional technology.

Abstract: A method and system for controlling an access to a first memory arrangement and a second memory arrangement. The method and system are adapted for controlling access to the first memory arrangement and to the second memory arrangement. A token is passed from a device associated with the first memory arrangement if the access to at least one portion of the first memory arrangement is completed, and the access to the portion of the memory arrangement is disabled. Then, upon a receipt of the token, the access to at least one portion of the second memory arrangement is enabled.

Abstract: A method and apparatus for minimizing memory required for storing non-binary width data structures is disclosed. The non-binary width data structure is segmented into plural segments. The segments are stored in a plurality of memory blocks. Mapper logic maps a logical address to a physical address in the memory blocks to access non-binary width entries in the non-binary width data structure stored in the memory blocks.

Abstract: A peripheral device interface control chip having a cache system therein and a method of synchronization data transmission between the cache system and an external device in a computer system. The cache system and data synchronization method can be applied to the peripheral device interface control chip having a data buffer and a peripheral device interface controller. The data buffer is located inside the control chip for holding data stream read from a memory unit so that data required by the peripheral device is provided. When the data stream is still valid, the data stream is retained. The peripheral device interface controller is installed inside the control chip. The peripheral device interface controller detects if the data stream inside the data buffer includes the data required by the peripheral device and whether the data stream is still valid or not.

Abstract: A system, method, and computer program product for detecting a first memory in a first node and detecting a second memory in a second node coupled to the first node. The system, method, and computer program product ensure that a first set of contiguous addresses is mapped to a portion of the first memory where the first set of contiguous addresses each have a value lower than a four gigabyte address, and ensure that a second set of contiguous addresses is mapped to a portion of the second memory where the second set of contiguous addresses each have a value lower than the four gigabyte address.

Abstract: A processor (300) in a distributed shared memory system (10) has ownership of a cache line. The processor modifies the cache line and wishes to update the home memory (17) of the cache line with the modification. The processor (300) generates a return request for routing by a processor interface (24). Meanwhile, a second processor (400) wishes to obtain ownership of the cache line and sends a read request to a memory directory (22) associated with the home memory (17) of the cache line. The memory directory (22) generates an intervention request towards the processor interface (24) corresponding to the last known location of the cache line. The processor interface (24) has now forwarded the return request to the memory directory (22) but subsequent to the read request from the second processor (400).

Abstract: A method, computer program product, and distributed data processing system for lazy deregistration of memory regions. Specifically, the present invention is directed to memory regions that are written to and from by an Integrated Protocol Suite Offload Engine (IPSOE) in accordance with a preferred embodiment of the present invention. A mechanism is provided for lazy deregistration of memory regions once the region is no longer required for a specific data transfer being carried out by the IPSOE. Rather than deregistering a memory region after a data transfer has been carried out, the memory region remains registered for some selected period of time. After that selected period of time passes, the region is then deregistered. If a second data transfer using this memory region occurs while the memory region is still registered, the registration overhead is avoided for this second data transfer.