Abstract: Garbage collection is performed according to an estimated number of valid pages. A storage device estimates a valid page count at a future time based on a valid page count at each of past time steps and a present time step using a neural network model and selects a victim block that undergoes the garbage collection from memory blocks based on an estimated valid page count. A memory block having a lowest estimated valid page count or having an estimated valid page count having a maintaining tendency is selected as the victim block or a memory block having the estimated valid page count having a decreasing tendency is excluded from selecting the victim block.

Abstract: The storage device and storage virtualization system include a non-volatile memory device, and a memory controller configured to generate at least one virtual device corresponding to a physical storage area of the non-volatile memory device, and convert a virtual address for the virtual device into a physical address in response to an access request.

Abstract: A method of operating a storage device to perform a garbage collection operation on a nonvolatile memory device having a plurality of memory blocks, the storage device configured to operate based on a multi-stream scheme such that a plurality of data is written into the plurality of memory blocks based on which of a plurality of streams is associated with the plurality of data. The method may include selecting at least two memory blocks among the plurality of memory blocks as victim memory blocks such that the victim memory blocks are configured to store data associated with a same stream of the plurality of streams; and performing the garbage collection operation on the victim memory blocks.

Abstract: A storage device includes a non-volatile memory including a plurality of memory blocks. The storage device performs an alignment operation in response to receipt of an align command. The alignment operation converts a received logical address of a logical segment into a physical address and allocates the physical address to a physical block address corresponding to a free block. The storage device is further configured to performs a garbage collection in units of the physical block address that indicates one memory block.

Abstract: In a data management method for a storage device, the storage device includes a nonvolatile memory device including a plurality of memory blocks. A TRIM-after-COPY command is received from an external host such that a data compaction operation is performed on a first storage region. Valid data stored in the first storage region are internally copied into a second storage region based on the TRIM-after-COPY command. A TRIM operation is performed based on the TRIM-after-COPY command to update a logical-to-physical address mapping table and a valid page bitmap.

Abstract: In a method of operating a storage device, the storage device includes a plurality of memory blocks. A data write request and target data to be written are received. Using a data classifier, such as a neural network model, the target data is assigned to a stream selected from a plurality of streams based on a data property of the target data. The target data is written into a memory block assigned to a stream selected for assignment of the target data, such that target data that has been assigned to a stream are written into the one or more memory blocks assigned to the stream.

Abstract: Garbage collection is performed according to an estimated number of valid pages. A storage device estimates a valid page count at a future time based on a valid page count at each of past time steps and a present time step using a neural network model and selects a victim block that undergoes the garbage collection from memory blocks based on an estimated valid page count. A memory block having a lowest estimated valid page count or having an estimated valid page count having a maintaining tendency is selected as the victim block or a memory block having the estimated valid page count having a decreasing tendency is excluded from selecting the victim block.

Abstract: A computing device includes a processor and a non-volatile dual in-line memory module (NVDIMM) connected to the processor. The NVDIMM includes a first memory having a first processing speed and a first storage capacity, a second memory having a second processing speed lower than the first processing speed and a second storage capacity larger than the first storage capacity, and a controller that evicts or fetches data between the first memory and the second memory. When the processor recognizes a first situation to evict data or a second situation to prefetch data, the processor transmits a command including first information of a logical address of data associated with the first situation or the second situation, second information of a length of the data associated with the first situation or the second situation, and third information indicating the first situation or the second situation to the NVDIMM.

Abstract: A storage device includes a main storage including a plurality of nonvolatile memory devices, the main storage device configured to store data; and a storage controller configured to control the main storage. The storage controller is configured to, divide a plurality of memory blocks of the plurality of nonvolatile memory devices into a plurality of banks, assign each one of the plurality of banks into one of a) a plurality of sets and b) one free bank, each of the plurality of sets including at least one bank, perform data migration operation to transfer the data among the sets by using the one free bank in response to an input/output (I/O) request from an external host device while securing a specific I/O execution time, and control the data migration operation such that the I/O request is independent of the data migration operation.

Abstract: An electronic system includes a host device and a storage device including a first memory device of a volatile type and a second memory device of a nonvolatile type. The first memory device is accessed by the host device through a memory-mapped input-output interface and the second memory device is accessed by the host device through a block accessible interface. The storage device provides a virtual memory region to the host device such that a host-dedicated memory region having a first size included in the first memory device is mapped to the virtual memory region having a second size larger than the first size.

Abstract: A solid state drive including: a plurality of non-volatile memories, each of the non-volatile memories including a channel, the channel including at least one way connected to a die; a host interface which receives stream data and stream information from a host; and a resource allocator which allocates the stream data to super blocks of the plurality of non-volatile memories on the basis of the stream information, wherein a first super block includes a first unit super block, and the first unit super block includes a block of a first die corresponding to a first channel and connected to a plurality of ways included in the first channel.

Abstract: Provided are a semiconductor device and a semiconductor system. A semiconductor device includes a non-volatile memory; a device interface circuit which receives an input/output (I/O) request from a host; and a device controller which executes a data access according to the I/O request on the non-volatile memory, and transmits an interrupt to the host a predetermined time before completion of the data access.

Abstract: A storage device includes: a non-volatile memory including a first memory area and a second memory area, and a memory controller configured to receive a request from a first client device to upload a first multimedia file, generate a second multimedia file including a base layer and at least one enhancement layer by transcoding the first multimedia file from an original format to a scalable format, and control the non-volatile memory to store the second multimedia file in the non-volatile memory.

Abstract: In a data management method for a storage device, the storage device includes a nonvolatile memory device including a plurality of memory blocks. A TRIM-after-COPY command is received from an external host such that a data compaction operation is performed on a first storage region. Valid data stored in the first storage region are internally copied into a second storage region based on the TRIM-after-COPY command. A TRIM operation is performed based on the TRIM-after-COPY command to update a logical-to-physical address mapping table and a valid page bitmap.

Abstract: A method of operating a storage device to perform a garbage collection operation on a nonvolatile memory device having a plurality of memory blocks, the storage device configured to operate based on a multi-stream scheme such that a plurality of data is written into the plurality of memory blocks based on which of a plurality of streams is associated with the plurality of data. The method may include selecting at least two memory blocks among the plurality of memory blocks as victim memory blocks such that the victim memory blocks are configured to store data associated with a same stream of the plurality of streams; and performing the garbage collection operation on the victim memory blocks.

Abstract: A computing device includes a processor and a non-volatile dual in-line memory module (NVDIMM) connected to the processor. The NVDIMM includes a first memory having a first processing speed and a first storage capacity, a second memory having a second processing speed lower than the first processing speed and a second storage capacity larger than the first storage capacity, and a controller that evicts or fetches data between the first memory and the second memory. When the processor recognizes a first situation to evict data or a second situation to prefetch data, the processor transmits a command including first information of a logical address of data associated with the first situation or the second situation, second information of a length of the data associated with the first situation or the second situation, and third information indicating the first situation or the second situation to the NVDIMM.

Abstract: Provided are a method and a system for transmitting data between storage devices over peer-to-peer (P2P) connections of peripheral component interconnect-express (PCIe). The method, performed when a first storage device receives a data request from a host, includes caching data of another storage device via PCIe connection in response to the data request, and transmitting the cached data to the host. The first storage device is configured to convert a logical address received with the data request to a physical address of a memory region of a second storage device, to store data transmitted from the second storage device via the PCIe connection in a second data cache according to the converted physical address, and to perform a cache replacement scheme for the data stored in the second data cache.

Abstract: A method of operating a universal flash storage (UFS) device communicating with a UFS host via a link is provided. The method determines in the UFS device whether a warm reset of the link is necessary while the UFS device is communicating with the UFS host via the link. Upon determining that the warm reset of the link is necessary, the UFS device initiates the warm reset of the link.

Abstract: A storage device, a directory entry lookup method for the storage device, and a host running the method can provide a quick directory entry lookup. The host includes an interface for exchanging data with the storage device which stores a multi-level hash table comprising directory entries of each directory, and a file system module receiving a file lookup command designating a target directory and a target filename, calculating a hash value which reflects the target filename and a lookup level, and searching for a directory entry which comprises the target filename in a bucket corresponding to the hash value from among buckets at the lookup level which are included in a multi-level hash table of the target directory. If the search for the directory entry fails, the file system module increases the lookup level and again calculates the hash value and searches for the directory entry for the target filename.

Abstract: A method of operating a universal flash storage (UFS) device communicating with a UFS host via a link is provided. The method determines in the UFS device whether a warm reset of the link is necessary while the UFS device is communicating with the UFS host via the link. Upon determining that the warm reset of the link is necessary, the UFS device initiates the warm reset of the link.