Abstract:
Embodiments of a method, device, and system for implementing multi-level memory with direct access are disclosed. In one embodiment, the method includes designating an amount of a non-volatile random access memory (NVRAM) in a computer system to be utilized as a memory alternative for a dynamic random access memory (DRAM). The method continues by designating a second amount of the NVRAM to be utilized as a storage alternative for a mass storage device. Then the method re-designates at least a first portion of the first amount of NVRAM from the memory alternative designation to the storage alternative designation during operation of the computer system. Finally, the method re-designates at least a first portion of the second amount of NVRAM from the storage alternative designation to the memory alternative designation during operation of the computer system.
Abstract:
Some embodiments of the invention use a command-based interface to control reads and writes with non-volatile memory devices. This may reduce the number of pins that are needed on each integrated circuit, and therefore reduce the cost and size of those integrated circuits. In some embodiments, an on-die cache buffer may be used to buffer data transfers between a high-speed memory bus and the slower speed non-volatile array.
Abstract:
In various embodiments, a plurality of non-volatile memory devices, such as NAND flash memory device, may be connected to a host controller device in a fanned out configuration that allows each of the plurality of memory devices to perform read and/or write operations simultaneously. Each non-volatile memory device may include high speed input circuitry and high speed output circuitry so that transfers to and from memory are not limited by the speed of the flash memory read/write interface.
Abstract:
Uncorrectable memory errors may be reduced by determining a logical array address for a set of memory arrays and transforming the logical array address to at least two unique array addresses based, at least in part, on logical locations of at least two memory arrays within the set of memory arrays. The at least two memory arrays are then accessed using the at least two unique array addresses, respectively.
Abstract:
Methods and apparatus related to PCMS (Phase Change Memory with Switch) write error detection are described. In one embodiment, a first storage unit stores a single bit to indicate whether an error corresponding to a write operation in any of one or more PCMS devices has occurred. Also, one or more storage units each store a plurality of bits to indicate whether the error corresponding to the write operation has occurred in a partition of a plurality of partitions of the one or more PCMS devices. Other embodiments are also disclosed and claimed.
Abstract:
Examples are disclosed for adaptive configuration of non-volatile memory. The examples include a mode register configured to include default and updated values to indicate one or more configurations of the non-volatile memory. The examples may also include discoverable capabilities maintained in a configuration table that may indicate memory address lengths and/or operating power states.