A system includes a plurality of host processors and a plurality of HMC devices configured as a distributed shared memory for the host processors. An HMC device includes a plurality of integrated circuit memory die including at least a first memory die arranged on top of a second memory die and at least a portion of the memory of the memory die is mapped to include at least a portion of a memory coherence directory; and a logic base die including at least one memory controller configured to manage three-dimensional (3D) access to memory of the plurality of memory die by at least one second device, and logic circuitry configured to determine memory coherence state information for data stored in the memory of the plurality of memory die, communicate information regarding the access to memory, and include the memory coherence information in the communicated information.

A processor memory mapped boot system includes a processing system having a processor memory subsystem, and a memory system having at least one memory device. A Basic Input/Output System (BIOS) engine is coupled to the processing system and the memory system, and is configured to begin boot operations and detect a boot memory mode setting for the processor memory subsystem. The BIOS engine configures a memory space that includes the at least one memory device and the processor memory subsystem. In response to detecting the boot memory mode setting, the BIOS engine will configured the processor memory subsystem to provide a first memory region of the memory space. The BIOS engine will then complete boot operations utilizing the processor memory subsystem providing the first memory region of the memory space.

A computer-implemented method for memory macro disablement in a cache memory includes identifying a defective portion of a memory macro of a cache memory bank. The method includes iteratively testing each line of the memory macro, the testing including attempting at least one write operation at each line of the memory macro. The method further includes determining that an error occurred during the testing. The method further includes, in response to determining the memory macro as being defective, disabling write operations for a portion of the cache memory bank that includes the memory macro by generating a logical mask that includes at least bits comprising a compartment bit, and read address bits.

Volatile memory devices may be on a first memory module that is coupled to a memory controller by a first signal path. A nonvolatile memory device may be on a second memory module that is coupled to the first memory module by a second signal path. A memory transaction for the nonvolatile memory device may be transferred from the memory controller to at least one of the volatile memory devices using the first signal path and data associated with the memory transaction is to be written from at least one of the volatile memory devices to the nonvolatile memory device using the second signal path and a control signal. A durability circuit may generate the control signal based on a comparison of a number of write transactions to a particular memory location with a threshold value.

A distributed storage system comprises a first module and a second module. The first module processes read requests for an address range, to send to the second module. The first module receives an address associated with a read request for a data page stored on the second module. A method searches a table on the first module for a content-based signature of the data page based on the address and provides the data page from a first module read cache if the content-based signature is in the read cache, where content-based signatures in the table are associated with the address range.

Disclosed herein is an apparatus and method for a key value store snapshot for a distributed memory object system. In one embodiment, a method includes forming a system cluster comprising a plurality of nodes, wherein each node includes a memory, a processor and a network interface to send and receive messages and data; creating a plurality of sharable memory spaces having partitioned data, wherein each space is a distributed memory object having a compute node, wherein the sharable memory spaces are at least one of persistent memory or DRAM cache; storing data in persistent memory, the data having a generation tag created from a generation counter and a doubly linked list having a current view and a snapshot view, the data further being stored in either a root or a persisted row; creating a snapshot comprising a consistent point-in-time view of key value contents within a node and incrementing the generation counter; copying the snapshot to a second node; regenerating an index for the key value contents within the node; and logging updates since the snap was applied to update copied data in the second node.

An information processing system including a processor, a memory, and a plurality of drives, wherein when a write request of new data is received, the processor stores the new data in the memory, transmits a response for the write request to a transmission source of the write request, reads old data updated by the new data from a first drive of the plurality of drives and old parity related to the old data from a second drive of the plurality of drives according to transmission of the response, store the old data and the old parity in the memory, generates new parity related to the new data from the new data, the old data, and the old parity stored in the memory, and stores the new data in the first drive to store the new parity in the second drive.

An approach is disclosed that tracks memory transactions by a node. The approach establishes a transaction processing state corresponding to common virtual addresses accessed by a processing threads. Transactions are executed by the threads. A selected transaction is allowed to complete. In response to detecting a conflict in the transaction processing state, completion of a non-selected transaction is inhibited.

A system includes a plurality of host processors and a plurality of HMC devices configured as a distributed shared memory for the host processors. An HMC device includes a plurality of integrated circuit memory die including at least a first memory die arranged on top of a second memory die and at least a portion of the memory of the memory die is mapped to include at least a portion of a memory coherence directory; and a logic base die including at least one memory controller configured to manage three-dimensional (3D) access to memory of the plurality of memory die by at least one second device, and logic circuitry configured to determine memory coherence state information for data stored in the memory of the plurality of memory die, communicate information regarding the access to memory, and include the memory coherence information in the communicated information.

Volatile memory devices may be on a first memory module that is coupled to a memory controller by a first signal path. A nonvolatile memory device may be on a second memory module that is coupled to the first memory module by a second signal path. A memory transaction for the nonvolatile memory device may be transferred from the memory controller to at least one of the volatile memory devices using the first signal path and data associated with the memory transaction is to be written from at least one of the volatile memory devices to the nonvolatile memory device using the second signal path and a control signal. A durability circuit may generate the control signal based on a comparison of a number of write transactions to a particular memory location with a threshold value.