Disclosed herein is a persistent memory (PMEM)-based distributed memory object system, referred to as the PMEM DMO system, that provides affordable means of integrating low-latency PMEM spaces with other devices, including servers that do not directly support PMEM. One embodiment comprises providing a cluster of servers with PMEM storage (PMEM servers) and connecting the PMEM servers to a plurality of applications servers using a low-latency network, such as a remote direct memory access; background processes on each of the application servers are tasked to perform input/output operations for the application servers to locally materialize objects from and synchronize/persist objects to the remote PMEM spaces on the PMEM servers. Data materialized from the PMEM servers is stored to the local cache of the application server for use. Also disclosed are data eviction policies for clearing the local cache of the application servers to make space for new data read.

A method of writing data into a memory device comprising utilizing a pipeline to process write operations of a first plurality of data words addressed to a plurality of memory banks, wherein each of the plurality of memory banks is associated with a counter. The method also comprises writing a second plurality of data words and associated memory addresses into an error buffer, wherein the error buffer is associated with the plurality of memory banks and wherein further each data word of the second plurality of data words is either awaiting write verification associated with a bank from the plurality of memory banks or is to be re-written into a bank from the plurality of memory banks. Further, the method comprises maintaining a count in each of the plurality of counters for a respective number of entries in the error buffer corresponding to a respective memory bank.

A memory access command, column address and plurality of write data values are received within an integrated-circuit memory chip via external signaling links. In response to the memory access command, the integrated-circuit memory chip (i) decodes the column address to select address-specified sense amplifiers from among a plurality of sense amplifiers that constitute a sense amplifier bank, (ii) reads first data, constituted by a plurality of read data values, out of the address-specified sense amplifiers, and (iii) overwrites the first data within the address-specified sense amplifiers with second data constituted by one or more of the write data values and by one or more of the read data values.

Subject matter disclosed herein relates to management of a memory device.

A method is described that includes deciding to enter a lower power state, and, shutting down a memory channel in a computer system in response where thereafter other memory channels in the computer system remain active so that computer remains operative while the memory channel is shutdown.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing topological scheduling on a machine-learning accelerator having an array of tiles. One of the methods includes performing, at each time step of a plurality of time steps corresponding respectively to columns within each of a plurality of wide columns of the tile array, operations comprising: performing respective multiplications using tiles in a respective tile column for the time step, computing a respective output result for each respective tile column for the time step including computing a sum of results of the multiplications for the tile column, and storing the respective output result for the tile column in a particular output RAM having a location within the same tile column and on a row from which the output result will be read by a subsequent layer of the model.

In certain aspects, one or more solid-state storage devices (SSDs) are provided that include a controller and non-volatile memory coupled to the controller. The non-volatile memory can include one or more portions configured as main memory or cache memory. When data stored in the main memory is written to the cache memory for processing, the data in the main memory is erased. In certain aspects, storage systems are provided that include one or more of such SSDs coupled to a host system. In certain aspects, methods are provided that include: receiving, by a first such SSD, a first command to write data to memory; determining that the data is stored in a main memory and is to be written to the cache memory for processing; writing the data to the cache memory; and erasing the data from the main memory.

A semiconductor chip comprising memory controller circuitry having interface circuitry to couple to a memory channel. The memory controller includes first logic circuitry to implement a first memory channel protocol on the memory channel. The first memory channel protocol is specific to a first volatile system memory technology. The interface also includes second logic circuitry to implement a second memory channel protocol on the memory channel. The second memory channel protocol is specific to a second non volatile system memory technology. The second memory channel protocol is a transactional protocol

An electronic device may include a semiconductor memory. The semiconductor memory may include a stack in which a plurality of dielectric layers and a plurality of first electrodes are alternately stacked over a substrate in a vertical direction relative to the substrate; a hole pattern passing through the stack in the vertical direction and having a polygonal shape when viewed in a plan view; a plurality of second electrodes disposed on respective sidewalls of the hole pattern; and a plurality of variable resistance layers interposed between the plurality of second electrodes and the plurality of horizontal electrodes.

Subject matter disclosed herein relates to management of a memory device.