Abstract: Providing memory bandwidth compression using multiple last-level cache (LLC) lines in a central processing unit (CPU)-based system is disclosed. In some aspects, a compressed memory controller (CMC) provides an LLC comprising multiple LLC lines, each providing a plurality of sub-lines the same size as a system cache line. The contents of the system cache line(s) stored within a single LLC line are compressed and stored in system memory within the memory sub-line region corresponding to the LLC line. A master table stores information indicating how the compressed data for an LLC line is stored in system memory by storing an offset value and a length value for each sub-line within each LLC line. By compressing multiple system cache lines together and storing compressed data in a space normally allocated to multiple uncompressed system lines, the CMC enables compression sizes to be smaller than the memory read/write granularity of the system memory.

Abstract: A method for scheduling read commands, performed by a processing unit, contains the following steps: Logical read commands are received from a master device via a first access interface, where each logical read command requests to read data of a logical address. First physical storage locations of mapping segments associated with the logical addresses are obtained from a high-level mapping table, and a second access interface is directed to read the mapping segments from the first physical storage locations of a storage unit. Second physical storage locations associated with the logical addresses are obtained from the mapping segments, and the second access interface is directed to read data from the second physical storage locations of the storage unit. The first access interface is directed to clock the data of the logical addresses out to the master device.

Abstract: A system comprising a processor and a memory storing instructions that, when executed, cause the system to identify a plurality of dump units associated with a translation table in a storage device, determine a plurality of snapshot markers associated with the plurality of dump units, calculate a first value of a first snapshot marker from the plurality of snapshot markers in the storage device, identify a second snapshot marker from an additional source, the second snapshot marker having a second value satisfying the first value, retrieve a dump unit associated with the second snapshot marker from the additional source, and reconstruct the translation table using the dump unit.

Abstract: A memory system includes a memory device. The memory device includes a substrate. A memory array defines a plurality of pages, each page including a data area for storing data and a spare area for storing a program/erase (PE) count value, the PE count value indicating a number of PE cycles performed on the page. A PE count circuit is configured to perform a PE count read operation on a target page. A host determines whether to perform a data write operation on the target page or another PE count read operation on a new target page based on a result of the PE count read operation. PE cycles of a page are controlled by the PE count read operation. The memory array and the PE count circuit are formed in different layers of the substrate.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments for booting an application from multiple memories. An embodiment operates by executing in place from a first memory a first portion of the application, loading a second portion of the application from a second memory, and executing the second portion of the application.

Abstract: Data is received from a sensing device for storage in at least one memory of a Data Storage Device. It is determined whether to cache the received data in at least one cache memory of the DSD based on at least one of the sensing device sending the data and information related to the received data.

Abstract: A facility and cache machine instruction of a computer architecture for specifying a target cache cache-level and a target cache attribute of interest for obtaining a cache attribute of one or more target caches. The requested cache attribute of the target cache(s) is saved in a register.

Abstract: In an embodiment, a processor includes at least one core to execute instructions and a memory controller coupled to the at least one core. In turn, the memory controller includes a spare logic to cause a dynamic transfer of data stored on a first memory device coupled to the processor to a second memory device coupled to the processor, responsive to a temperature of the first memory device exceeding a thermal threshold. Other embodiments are described and claimed.

Abstract: A technique for managing data storage applies both inline software compression and inline hardware compression in a data storage system, using both types of compression together. The data storage system applies inline software compression for compressing a first set of newly arriving data and applies inline hardware compression for compressing a second set of newly arriving data. Both sets of data are directed to a data object, and the data storage system compresses both sets of data without first storing uncompressed versions thereof in the data object.

Abstract: According to one embodiment, a storage device includes a plurality of nonvolatile semiconductor memories, a sensor and a controller. The sensor is configured to measure a temperature of the nonvolatile semiconductor memories. The controller is configured to receive data from a host, determine a rewriting interval of the data and write the data to, of the nonvolatile semiconductor memories, a nonvolatile semiconductor memory having a temperature corresponding to the rewriting interval.

Abstract: A method includes, in one non-limiting embodiment, sending a request from a mass memory storage device to a host device, the request being one to allocate memory in the host device; writing data from the mass memory storage device to allocated memory of the host device; and subsequently reading the data from the allocated memory to the mass memory storage device. The memory may be embodied as flash memory, and the data may be related to a file system stored in the flash memory. The method enables the mass memory storage device to extend its internal volatile RAM to include RAM of the host device, enabling the internal RAM to be powered off while preserving data and context stored in the internal RAM.

Abstract: An apparatus for pooling memory resources across multiple nodes is described herein. The apparatus includes a shared memory controller, wherein each node of the multiple nodes is connected to the shared memory controller. The apparatus also includes a pool of memory connected to the shared memory controller, wherein a portion of the pool of memory is allocated to each node of the multiple nodes.

Abstract: A processor-implemented method for copying a source file to a destination file using a virtual memory manager (VMM) of a computer operating system is provided. The method includes receiving, by the VMM, a request to copy the source file to a destination file. The method further provides that based on the status of the virtual page, performing at least one of moving the virtual page to the destination file, copying the virtual page to the destination file, reading the virtual page into memory, and ignoring the virtual page.

Abstract: A storage system may implement dynamic configuration of data volumes. Client utilization of a data volume in a storage system may be tracked or monitored. Based on the utilization of the data volume, configuration recommendations to reconfigure the data volume according to data volume offerings may be determined. The data volume may be configured according to an authorized configuration recommendation. In some embodiments, these recommendations may be provided to a client and selection of the configuration recommendation to perform may be received. In some embodiments, a configuration recommendation may be automatically performed based on previously provided authorization to configure the data volume.

Abstract: Described are a system and method to control interface timing and/or voltage operations of signals transmitted between devices. A processor may be coupled through one or more bus interfaces of a bus to one or more corresponding interface timing and/or voltage comparison circuits and corresponding interface timing and/or voltage adjustment circuits.

Abstract: Methods and systems for managing data storage in a non-volatile memory system are disclosed. The method may include receiving data, determining a data classification for the received data from a predetermined plurality of data classifications, writing the received data to an open block having only data of a same data classification as the determined data classification and, upon completely programming the open block, associating an epoch indicator where the epoch indicator defines a time period within which the block was created. When a block reclaim trigger is detected, only data within a same data classification and epoch may be reclaimed. An incrementing epoch indicator identifies a predetermined time granularity and is assigned to data such that earlier data and newer data are distinguishable. A system to implement the method may include a non-volatile memory and a controller configured to track and apply epoch and data-type classification information for data.

Abstract: Embodiments of the present invention relate to multiple parallel lookups using a pool of shared memories by proper configuration of interconnection networks. The number of shared memories reserved for each lookup is reconfigurable based on the memory capacity needed by that lookup. The shared memories are grouped into homogeneous tiles. Each lookup is allocated a set of tiles based on the memory capacity needed by that lookup. The tiles allocated for each lookup do not overlap with other lookups such that all lookups can be performed in parallel without collision. Each lookup is reconfigurable to be either hash-based or direct-access. The interconnection networks are programmed based on how the tiles are allocated for each lookup.

Abstract: Embodiments of the present invention relate to multiple parallel lookups using a pool of shared memories by proper configuration of interconnection networks. The number of shared memories reserved for each lookup is reconfigurable based on the memory capacity needed by that lookup. The shared memories are grouped into homogeneous tiles. Each lookup is allocated a set of tiles based on the memory capacity needed by that lookup. The tiles allocated for each lookup do not overlap with other lookups such that all lookups can be performed in parallel without collision. Each lookup is reconfigurable to be either hash-based or direct-access. The interconnection networks are programmed based on how the tiles are allocated for each lookup.

Abstract: An electronic device may include first and second semiconductor chips. The first semiconductor chip may include a processor and a first memory. The second semiconductor chip may include a second memory. The first memory and second memory may be configured to exchange first data and second data with the processor, respectively. The processor may be configured to exchange target data processed or to be processed with the first and second memories. The processor may be configured to determine the target data as the first data if the number of accesses of the target data is equal to or greater than a first reference value. The processor may be configured to determine the target data as the second data if the number of accesses of the target data is less than the first reference value.

Abstract: A chip multiprocessor may include a first cluster and a second cluster, each having multiple cores of a processor, multiple co-located cache slices, and a memory controller. The processor stores directory information in a memory to indicate cluster cache ownership of a first address space to the first cluster. In response to a request to change the cluster cache ownership of the first address space to a second address space of the second cluster, the processor provides a quiesce period during which to block new read or write requests to the first cluster and the second cluster; drain read or write requests issued on the first cluster and the second cluster; and remove the block on new read or write requests. The processor may also update the directory information to change the cluster cache ownership of the first address space to the second address space of the second cluster.