A method for managing memory leaks in a memory device includes grouping, by a garbage collection system, a plurality of similar memory allocations of the memory device into one or more Unique Fixed Identifiers (UFIs); identifying, by the garbage collection system, one of the one or more UFIs having a highest accumulated memory size and adding each of the plurality of memory allocations in the identified one of the one or more UFIs into a Potential Leak Candidate List (PLCL); identifying, by the garbage collection system, the memory leaks in the memory device by identifying unreferenced memory addresses associated with the plurality of memory allocations in the PLCL; and releasing, by the garbage collection system, the identified unreferenced memory addresses associated with the plurality of memory allocations corresponding to the memory leaks into the memory device.

Memory devices and methods of operating memory devices in which maintenance operations can be scheduled on an as-needed basis for those memory portions where activity (e.g., operations in excess of a predetermined threshold) warrants a maintenance operation are disclosed. In one embodiment, an apparatus comprises a memory including a memory location, and circuitry configured to determine a count corresponding to a number of operations at the memory location, to schedule a maintenance operation for the memory location in response to the count exceeding a first predetermined threshold, and to decrease the count by an amount corresponding to the first predetermined threshold in response to executing the scheduled maintenance operation. The circuitry may be further configured to disallow, in response to determining that the count has reached a maximum permitted value, further operations at the memory location until after the count has been decreased.

Methods, systems, and devices for host-configurable error protection are described. A host system may receive an indication of a set of logical addresses supported by the memory system and available for use by the host system. The host system may divide the set of logical addresses into subsets of logical addresses. Each subset of logical addresses may be associated with a different type of data. The host system may determine an error protection configuration for a subset of logical addresses based at least in part on the type of data associated with the subset of logical addresses. The host system may then send to the memory system an indication of the subset of logical addresses and an indication of the error protection configuration for the subset of logical addresses.

A device in an interconnect network is provided. The device comprises an end point processor comprising end point memory and an interconnect network link in communication with an interconnect network switch. The device is configured to issue, by the end point processor, a request to send data from the end point memory to other end point memory of another end point processor of another device in the interconnect network and provide, to the interconnect network switch, the request using memory addresses from a global memory address map which comprises a first global memory address range for the end point processor and a second global memory address range for the other end point processor.

A caching system including a first sub-cache and a second sub-cache in parallel with the first sub-cache, wherein the second sub-cache includes a set of cache lines, line type bits configured to store an indication that a corresponding cache line of the set of cache lines is configured to store write-miss data, and an eviction controller configured to flush stored write-miss data based on the line type bits.

A storage device capable of maintaining consistency of data for the same address may include a memory device including a plurality of memory blocks, a buffer memory device including a plurality of cache buffers temporarily storing data previously received from a host, and a memory controller configured to receive a write request and a write data from the host and configured to control the buffer memory device and the memory device to store a previously received data, stored in one of the plurality of cache buffers with a logical address that matches a logical address of the write data, in the memory device before the write request is processed.

In an embodiment, a system may support programmable hashing of address bits at a plurality of levels of granularity to map memory addresses to memory controllers and ultimately at least to memory devices. The hashing may be programmed to distribute pages of memory across the memory controllers, and consecutive blocks of the page may be mapped to physically distant memory controllers. In an embodiment, address bits may be dropped from each level of granularity, forming a compacted pipe address to save power within the memory controller. In an embodiment, a memory folding scheme may be employed to reduce the number of active memory devices and/or memory controllers in the system when the full complement of memory is not needed.

According to one embodiment, there is provided a memory system including a non-volatile memory and a controller. The non-volatile memory includes a plurality of physical blocks. The controller is connected to any of the plurality of physical blocks via a plurality of channels. The controller is configured to construct a plurality of logical blocks and, read or write data from or into any of the plurality of logical blocks constructed. The logical blocks are management units in which any of the physical blocks is grouped across the plurality of channels. The controller is configured to construct the plurality of logical blocks so that a first number of defective blocks and a second number of pseudo defective blocks for shortfall defective blocks with respect to a target number of defective blocks are distributed into the plurality of logical blocks.

A technical solution to the technical problem of how to reduce the undesirable side effects of offloading computations to memory uses read hints to preload results of memory-side processing into a processor-side cache. A cache controller, in response to identifying a read hint in a memory-side processing instruction, causes results of the memory-side processing to be preloaded into a processor-side cache. Implementations include, without limitation, enabling or disabling the preloading based upon cache thrashing levels, preloading results, or portions of results, of memory-side processing to particular destination caches, preloading results based upon priority and/or degree of confidence, and/or during periods of low data bus and/or command bus utilization, last stores considerations, and enforcing an ordering constraint to ensure that preloading occurs after memory-side processing results are complete.

According to one embodiment, a memory system includes a non-volatile memory and a controller. The controller controls writing of data to the non-volatile memory or reading of data from the non-volatile memory in response to a command from a host. The controller manages a first area and a second area in a memory space provided to the host, to which an area of the non-volatile memory is mapped. The first area is an area used by the host as a main memory. The second area is an area where valid data is stored.