Abstract: A system having a host unit and a plurality of stacked modules which are electrically connected to the host unit. The host unit communicates with the plurality of stacked modules through a RS-485 interface. Upon power up, each module of the plurality of stacked modules is powered and enumerated in sequence, allowing the host unit to know the sequence the plurality of stable modules are connected.

Abstract: An improved memory interface design is provided. In some implementations, an integrated circuit includes a first cache memory unit, a second cache memory unit located in parallel with the first cache memory unit, and a floorsweeping module configured to be able to select between the first cache memory unit and the second cache memory unit for cache requests, wherein the selection is based at least partially on the presence or absence of one or more manufacturing defects in the first cache memory unit or the second cache memory unit.

Abstract: A control method for a memory is provided. The memory includes a plurality of storage units, each storing a plurality of bits. In a read mode, a read command is provided to the memory. The value of a most significant bit (MSB) of each storage unit is obtained and recorded. The value of the most significant bits is output. The value of a neighboring bit of each storage unit is obtained and recorded. The neighboring bit neighbors the most significant bit. The value of the neighboring bits is output.

Abstract: A non-volatile semiconductor memory is disclosed comprising N memory devices each comprising a plurality of blocks, wherein each block comprises a plurality of memory segments accessed through an address. A searched is performed by issuing a read command for each of the N memory devices, wherein an address of each read command is separated by a distance determined in response to the search range of addresses and N, and the search range of addresses is greater than N. Data read from at least one of the memory devices is evaluated to determine whether the search has finished.

Abstract: A control method for a memory is provided. The memory includes a plurality of storage units, each storing a plurality of bits. In a read mode, a read command is provided to the memory. The value of a most significant bit (MSB) of each storage unit is obtained and recorded. The value of the most significant bits is output. The value of a neighboring bit of each storage unit is obtained and recorded. The neighboring bit neighbors the most significant bit. The value of the neighboring bits is output.

Abstract: According to one embodiment, a storage device comprises a first storage unit having blocks, each including pages, a second storage unit having a free block list, and a free page list, and a control unit. In write data in units of blocks, the control unit generates compressed data blocks by compressing the data in units of blocks, writes the compressed data blocks to the blocks which can be written in accordance with the information held in the free block list, holds, in the free page list, the information about pages existing in free areas which are provided in the blocks holding compressed data blocks and which holds no compressed data blocks. In write data in units of pages, the control unit writes the data in units of pages to pages existing in the free areas, in accordance with the information held in the free page list.

Abstract: A storage proxy monitors storage access operations. Different address alignments are identified between the storage access operations and data blocks in a storage media. A dominant one of the address alignments is identified. Data blocks are mapped into the storage media to remove the dominant address alignment. An array of counters can be used to track the address alignments for different storage access sizes and the address alignment associated with the highest number of storage access operations is used as the dominant address alignment.

Abstract: The present invention discloses methods for improving data-retrieval times from a non-volatile storage device. A method for preloading data to improve data-retrieval times from a non-volatile storage device, the method including the steps of: providing a cache memory for preloading the data upon a host-system request to read the data; determining that a plurality of data segments that constitute a non-contiguous data object, stored in the storage device such that at least one data segment is non-contiguous to a preceding data segment in the data object, are in a predictable sequence; and preloading a non-contiguous next data segment in the predictable sequence into the cache memory after loading a current data segment into a host system from the cache memory, wherein the next data segment is preloaded prior to the host-system request to read the next data segment.

Abstract: In one embodiment, a method is disclosed for allocating memory for a processor unit in a group of processing units. The method can include receiving a memory allocation request where the request can indicate a number of binary segments to be stored. The method can determine if the number indicates a nonstandard allocation, and locate an unallocated memory address based on a multiple of the number if the number indicates a nonstandard allocation. The method can also include locating an unallocated memory address from a pool of memory addresses, where the pool of addresses includes the integer multiples of the binary segments and excludes addresses that are two times the number of binary segments such that the address can be utilized to determine the allocation.

Abstract: A shared memory switch is provided for storing and retrieving data from BlockRAM (BRAM) memory of a PLD. A set of class queues maintain a group of pointers that show the location of the incoming “cells” or “packets” stored in the memory in the switch based on the time of storage in the BRAM. A non-blocking memory architecture is implemented that allows for a scalable N×N memory structure to be created (N=number of input and output ports). A write controller stripes the data across this N×N memory to prevent data collisions on read in or read out of data. The data is scheduled for read out of this N×N shared memory buffer based on priorities or classes in the class queues, with priorities being set by a user, and then data is read out from the BRAM.