According to one embodiment, a memory system includes a nonvolatile memory and a controller. The controller manages first account information to be used for authentication of a first account and second account information to be used for authentication of a second account. The controller receives third account information from a host device. When the third account information matches the first account information, the controller permits access to at least a partial storage area of the nonvolatile memory based on a request from the host device and transmits first data that includes the second account information to a first memory system.

Techniques for block storage using a hybrid memory device are described. In at least some embodiments, a hybrid memory device includes a volatile memory portion, such as dynamic random access memory (DRAM). The hybrid memory device further includes non-volatile memory portion, such as flash memory. In at least some embodiments, the hybrid memory device can be embodied as a non-volatile dual in-line memory module, or NVDIMM. Techniques discussed herein employ various functionalities to enable the hybrid memory device to be exposed to various entities as an available block storage device.

A method at a computing device for data management between a publisher and at least one subscriber, the method including receiving, at a system element, memory requirements from the publisher; creating a memory allocation of a pool of data objects for the publisher based on the received memory requirements; receiving, at the system element, consumption criteria from each of the at least one subscriber; and adjusting the memory allocation of the pool of data objects based on the consumption criteria received from the at least one subscriber.

In one embodiment, a method includes determining a data record partition size based on resources used for transferring data from a higher storage tier to one or more lower storage tiers. The method also includes determining which data records stored to the higher storage tier are suitable for export to the one or more lower storage tiers, determining a distribution mapping of the first memory, the distribution mapping indicating a relative distribution of storage locations for all of the data records that are stored to the higher storage tier, identifying all sets of contiguously stored data records on the higher storage tier that are suitable for export and greater in size than the data record partition size, logically sorting, in a descending order of size, the sets of contiguously stored data records, and sending a list of logically sorted sets of contiguously stored data records to an exporter.

There is provided an apparatus for receiving a request from a master to access an input address. Coarse grain access circuitry stores and provides a reference to an area of an output address space in dependence on the input address. One or more fine grain access circuits, each store and provide a reference to a sub-area in the area of the output address space in dependence on the input address. The apparatus forwards the request from the coarse grain access circuitry to one of the one fine grain access circuits in dependence on the input address.

A memory device includes first, second, third, and fourth memory cell groups and first and second transmitters. The first and second memory cell groups share first local lines. The third and fourth memory cell groups share second local lines. The first transmitter transmits first data to first global lines based on a read command. The first data is output from one of the first memory cell group and the second memory cell group on the first local lines. The second transmitter transmits second data to second global lines based on the read command. The second data is output from one of the third memory cell group and the fourth memory cell group on the second local lines. The number of the first global lines is different from the number of the second global lines.

An optional array in a memory includes an array having blocks each including an address word and a data word, and a boundary that is a position where a ratio between the numbers of unwritten blocks in M area and written blocks in W area is an integer ratio. The controlling process includes when a second write for writing a special value in a written block in the second area is invoked, executing a shrink process of shifting the boundary to shrink the first area; in a case where the first adjacent block at the boundary is a written block, storing an address of the first adjacent block and of a first link destination block forming a link with the write destination block in address words of the first link destination block and of the first adjacent block respectively to form a link.

Data transformation offloading in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (GPU) servers, including: storing, within the storage system, a dataset; identifying, in dependence upon one or more machine learning models to be executed on the GPU servers, one or more transformations to apply to the dataset; and generating, by the storage system in dependence upon the one or more transformations, a transformed dataset.

Data transformation caching in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (GPU) servers, including: identifying, in dependence upon one or more machine learning models to be executed on the GPU servers, one or more transformations to apply to a dataset; generating, in dependence upon the one or more transformations, a transformed dataset; storing, within one or more of the storage systems, the transformed dataset; receiving a plurality of requests to transmit the transformed dataset to one or more of the GPU servers; and responsive to each request, transmitting, from the one or more storage systems to the one or more GPU servers without re-performing the one or more transformations on the dataset, the transformed dataset.

Data transformation offloading in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (GPU) servers, including: storing, within the storage system, a dataset; identifying, in dependence upon one or more machine learning models to be executed on the GPU servers, one or more transformations to apply to the dataset; and generating, by the storage system in dependence upon the one or more transformations, a transformed dataset.