Persistent caching of memory-side cache content for devices, systems, and methods are disclosed and discussed. In a system including both a volatile memory (VM) and a nonvolatile memory (NVM), both mapped to the system address space, software applications directly access the NVM, and a portion of the VM is used as a memory-side cache (MSC) for the NVM. When power is lost, at least a portion of the MSC cache contents is copied to a storage region in the NVM, which is restored to the MSC upon system reboot.

Systems and methods disclosed herein include those that may receive a memory request including a requested memory address and may send the memory request directly to an address decoder associated with a stacked-die memory vault without knowing whether a repair address is required. If a subsequent analysis of the memory request shows that a repair address is required, an in-process decode of the requested memory address can be halted and decoding of the repair address initiated.

The present application provides a status output method in NAND flash memory, including, setting ALE signal, CLE signal and WE#, signal wherein ALE and/or CLE signal is set to be 1 and WE# signal is set to be 1; when a falling edge of the RE# is detected, outputting LUN status signal of the NAND flash memory. Further, there is provided a NAND flash memory, including I/O signal pins, which includes an ALE signal pin, an CLE signal pin, a WE# signal pin, and a RE# signal pin; wherein when the ALE signal output by the ALE pin and/or CLE signal output by the CLE pin is 1, and WE# signal output by the WE# pin is 1, once a falling edge of the RE# is detected, the LUN status signal of the NAND flash memory is detected.

Embodiments for a memory access broker system with application-controlled early write acknowledgment support. A memory access broker may be selectively enabled to facilitate early write acknowledgement (EWACK) operations and notification of failed EWACK write requests to one or more issuing applications such that the failed EWACK write requests are logged by the memory access broker for inspection by the one or more issuing applications.

In a data processing device including two sets of circuit pairs which are respectively duplicated in two clock domains which are asynchronous to each other, an asynchronous transfer circuit that transfers a payload signal is provided between the two sets of circuit pairs. The asynchronous transfer circuit includes two sets of a pair of bridge circuits which are respectively connected to the two sets of circuit pairs, and asynchronously transfers the payload signal and a control signal indicating a timing at which the payload signal is stable on a reception side. The two sets of a pair of bridge circuits and the payload signals can be duplicated, but the control signal is not duplicated, and the received payload signal is used for timing control to supply an expected same time difference, to the pair of duplicated circuits. This enables asynchronous transfer between circuits duplicated in the asynchronous clock domains.

Apparatuses, systems, and methods are disclosed for an output data path for non-volatile memory. A buffer may include a plurality of buffer stages. A buffer stage width may be a width of an internal bus for a non-volatile memory element. A buffer may include two or more read pointers, updated by an internal controller at different times in response to different portions of a clock signal. A parallel-in serial-out (PISO) component may receive data via an internal data path having a data path width equal to an internal bus width, and may output the data in a series of transfers controlled according to a clock signal, via an output bus having an output bus width narrower than an internal bus width. A PISO component may receive data from a portion of a buffer stage in response to an internal controller updating a read pointer to point to the buffer stage.

A semiconductor memory device includes a substrate that has a first main surface and a second main surface opposite to the first main surface, a first semiconductor chip which is mounted on the first main surface and includes a first register, a plurality of first input/output (IO) terminals, and a first circuit connected between the first IO terminals and the first register, and a second semiconductor chip which is mounted on the second main surface and includes a second register, a plurality of second input/output (IO) terminals, and a second circuit connected between the second IO terminals and the second register. The second circuit is connected to the second IO terminals through input lines and to the second register through output lines, and is configured to change a connection path between the input lines and the output lines in response to a connection change command.

Disclosed is a memory system including a memory device and a memory controller. The memory device includes a package of a first memory chip configured to receive input/output signals through first input/output pads and a second memory chip having second input/output pads connected to the first input/output pads by a mapping connection. The memory controller configured to provide the input/output signals to the memory device. The second memory chip is configured to receive input/output signals different from the input/output signals provided by the memory controller to the first memory chip due to the mapping connection. The first and second memory chips are configured to selectively ignore the input/output signals provided by the memory controller based on the mapping connection.

A storage device includes a plurality of nonvolatile memory devices each exchanging data by using a data strobe signal and a data signal, and a storage controller categorizing the plurality of nonvolatile memory devices into a plurality of groups and performing training in units of the plurality of groups. The storage controller performs data training on a first nonvolatile memory device selected in a first group of the plurality of groups and sets a delay of a data signal of a second nonvolatile memory device included in the first group by using a result value of the data training for the first nonvolatile memory device.

Techniques are provided for low-latency, high bandwidth graphics accelerator die and memory system. In an example, a graphics accelerator die can include a plurality of memory blocks for storing graphic information, a display engine configured to request and receive the graphic information from the plurality of memory blocks for transfer to a display, a graphics engine configured to generate and transfer the graphic information to the plurality of memory blocks, and a high-bandwidth, low-latency isochronous fabric configured to arbitrate the transfer and reception of the graphic information.