Abstract: Methods and systems for in-memory metadata reduction in cloud storage system are provided. According to an aspect, a method comprises receiving a first command to write a data stream to a storage device; writing the data stream into a plurality of fragments having logical addresses corresponding to physical addresses on the storage device; and generating an index for individual fragment of the plurality of fragments, the index indicating information to locate the physical addresses of the individual fragment. Individual records in the individual fragment have a same pre-set logical size and all individual records in the individual fragment are continuous, and the index indicates the information including at least: an offset value of the individual record in the individual fragment; the pre-set logical size of the individual record; and a pre-set physical size of the individual record.

Abstract: Systems and methods are disclosed for logging guest physical address for memory access faults. For example, a method for logging guest physical address includes receiving a first address translation request from a processor pipeline at a translation lookaside buffer for a first guest virtual address; identifying a hit with a fault condition corresponding to the first guest virtual address; responsive to the fault condition, invoking a single-stage page table walk with the first guest virtual address to obtain a first guest physical address; and storing the first guest physical address with the first guest virtual address in a data store, wherein the data store is separate from an entry in the translation lookaside buffer that includes a tag that includes the first guest virtual address and data that includes a physical address.

Abstract: A method for cache coherency in a reconfigurable cache architecture is provided. The method includes receiving a memory access command, wherein the memory access command includes at least an address of a memory to access; determining at least one access parameter based on the memory access command; and determining a target cache bin for serving the memory access command based in part on the at least one access parameter and the address.

Abstract: A memory operation method, a memory storage device, and a memory control circuit unit are disclosed. The memory operation includes following steps. First data is received from a host system. The first data is stored into a first physical unit which is mapped to a first logical unit. In a first operation mode, a target calculation is performed based on the first data and second data stored in a second physical unit to obtain third data, and the third data is different from the first data. The third data is stored into a third physical unit which is also mapped to the first logical unit. The third data is transmitted to the host system.

Abstract: One or more trim values associated with a set of blocks of a memory device are set according to a representative number of program erase cycles (PECs) for the set of blocks. Each block in the set of blocks was programmed within at least one of a specified time window or a specified temperature range. Responsive to executing a program operation on a block of the set of blocks according to the one or more trim values, an indicator is set to reflect the one or more trim values used during the execution of the program operation. Responsive to receiving a request to perform a read operation directed to the block of the set of blocks, a read offset value corresponding to the indicator is determined. The read operation is performed using the read offset value.

Abstract: Improved techniques are directed to managing a cache in an electronic environment in which a first processing core is configured to utilize a first set of queues to reclaim the pages of the cache and a second processing core is configured to utilize a second set of queues to reclaim the pages of the cache. The techniques include adding, to a queue in the first set of queues, an entry identifying access information of a page of the cache. The techniques further include accessing the page by a second processing core. The techniques further include, while the entry is in the first set of queues, updating the access information by the second processing core to indicate accessing the page by the second processing core.

Abstract: A serial data buffer integrated circuit comprises unidirectional host-side input and output ports, and unidirectional memory-side input and output ports. Scheduling logic generates memory device commands for writing to and reading from a memory device based on a set of host-side input packets received from a memory controller. A unidirectional serial host side input port receives host-side input packets from the memory controller. A unidirectional serial memory side output port transmits the memory device commands and the write data to the memory device based on the scheduled timing. A unidirectional serial memory side input port receives read data from the memory device in response to a read command, and a unidirectional serial host side output port transmits the read data to the memory controller within the timing constraints of the memory device.

Abstract: A method and apparatus for a speculative request indicator is described. A method includes providing, for a cache hierarchy, a messaging protocol used for transfer operations among agents in the cache hierarchy, the messaging protocol indicating acceptable cache coherency states for a cache block indicated in a request message and providing, in the messaging protocol for selection by an agent, a speculative request indicator when sending the request message, wherein the speculative request indicator differentiates between a demand request and a speculative request with respect to the cache block.

Abstract: Various example embodiments for supporting a multi-indexed micro-operations cache (MI-UC) in a processor are presented. Various example embodiments for supporting an MI-UC in a processor may be configured to support an MI-UC in which, for a UC line of the MI-UC, multiple indexes into the UC line, for multiple sets of micro-operations (UOPs) stored in the UC line based on decoding of multiple instructions, are supported.

Abstract: Exemplary methods, apparatuses, and systems include receiving a request to perform an operation in memory. A subdivision of the memory to which the request is directed is determined. A command completion time based upon a command type for the operation and which subdivision of the memory to which the request is directed is determined. A command is sent to the memory for the operation. A request is sent to the memory for a status of the command based upon the determined command completion time.

Abstract: The present disclosure includes apparatuses and methods related to memory alignment. An example method comprises performing an alignment operation on a first byte-based memory element and a second byte-based memory element such that a padding bit of the first byte-based memory element is logically adjacent to a padding bit of the second byte-based memory element and a data bit of the first byte-based memory element is logically adjacent to a data bit of the second byte-based memory element.

Abstract: Systems, apparatuses, and methods related to transferring data to a memory device based on importance are described. A memory apparatus includes a first memory device, a second memory device having a lower write latency than the first memory device, and a controller coupled to the first memory device and second memory device via a compute express link (CXL) interface. The controller is configured to assign an importance level to a write request based on data associated with the write request, a hierarchy of importance levels for different data types, and the second memory device having a lower write latency than the first memory device. The controller is further configured to transfer the data to the first memory device in response to the assigned importance level having a first value and transfer the data to the second memory device in response to the assigned importance level having a second value.

Abstract: There is a large latency and controller bandwidth associated with moving data between dies or between memory devices. The controller includes one or more flash interface modules (FIMs) that are utilized to write data to the memory device and read data from the memory device. Each of the one or more FIMs includes one or more switches. Each switch is utilized to transfer data from a source block to a destination block. Likewise, rather than using a memory external to the FIM to cache the data, the data is stored in a FIM cache and moved from the FIM cache to the relevant physical layer to be programmed to the destination block. Because data is not being transferred to the system memory, the latency and bandwidth associated with relocating data may be decreased.

Abstract: Disclosed are a controller and an operating method thereof. According to an embodiment of the present disclosure, a controller that controls a memory device, comprises: a host interface for determining a remaining resource index and outputting a task scheduling instruction when a data throughput determined based on data inputted/outputted between a host and the controller is lower than a maximum throughput required under a current workload pattern; and a processor for: selecting, in response to the task scheduling instruction, at least one of a plurality of internal tasks based on the remaining resource index and resource consumption indexes of the respective internal tasks, and performing the selected internal task while performing an input/output task.

Abstract: A pooled memory device includes plural memory devices and a controller. The plural memory devices include a first memory and a second memory with at least one power supply configured to control power supplied to each of the plural memory devices. The controller is coupled to an interconnect device which is configured to provide the plural memory devices to at least one external device as a logical device. The controller is configured to track available storage capacities of the first memory and the second memory and cut off power supplied to an unused memory among the first memory and the second memory.

Abstract: An apparatus with an additional storage element or field is provided where a subscription indicator is stored, indicating a subscription to a region of memory, and hence subscribing to a cache line corresponding to the region of memory. In response to a subscribed cache line being invalidated, the apparatus performs actions to re-fetch the cache line, and to store the cache line in the cache after a short delay. The subscription indicator may be stored in a variety of ways, and may include further information that influences the functionality of the present techniques. Such further information may be adjustable in order to dynamically control the functionality of the disclosed techniques for a particular implementation over time.

Abstract: Examples provide an application program interface or manner of negotiating locking or pinning or unlocking or unpinning of a cache region by which an application, software, or hardware. A cache region can be part of a level-1, level-2, lower or last level cache (LLC), or translation lookaside buffer (TLB) are locked (e.g., pinned) or unlocked (e.g., unpinned). A cache lock controller can respond to a request to lock or unlock a region of cache or TLB by indicating that the request is successful or not successful. If a request is not successful, the controller can provide feedback indicating one or more aspects of the request that are not permitted. The application, software, or hardware can submit another request, a modified request, based on the feedback to attempt to lock a portion of the cache or TLB.

Abstract: Techniques for compressing a data block involve adding a compression flag to a data block after the data block is decompressed by a protocol layer, the compression flag indicating that the data block is compressible or uncompressible. Such techniques further involve acquiring the compression flag of the data block. Such techniques further involve determining, in response to the compression flag of the data block indicating that the data block is compressible, to perform inline compression on the data block. Such techniques further involve preventing, in response to the compression flag of the data block indicating that the data block is uncompressible, the inline compression from being performed on the data block.

Abstract: Systems, apparatuses and methods may provide for technology that detects, via a processor external to a solid state drive (SSD), internal information associated with the SSD, detects background operations with respect to the SSD based on the internal information, wherein the background operations include one or more of current operations or predicted operations, and adjusts a hierarchical data placement policy based on the background operations.

Abstract: A memory system includes a memory device and a controller. The memory device includes a plurality of memory blocks for storing or outputting plural data entries and a first parity entry associated with the plural data entries. The controller a second parity entry based on a part of the plural data entries, an updated data entry which renews the part of the plural data entries, and the first parity entry, in response to an update event regarding the part of the plural data entries, allocate, for storing the second parity entry, a first memory block having least program-erase cycles among the plurality of memory blocks, allocate, for storing the updated data entry, a second memory block storing the first parity entry, and control the memory device to program the updated data entry and the second parity entry in the first memory block and the second memory block.