A data transfer system including a first memory and a processor includes a second memory and a DMA controller. The processor performs RMW on data which has a size less than a cache line size and in which a portion of a cache line (a unit area of the first memory) is a write destination. Output target data is transferred from an I/O device to the second memory. Thereafter, the DMA controller transfers the output target data from the second memory to the first memory in one or a plurality of transfer unit sizes by which the number of occurrences of RMW is minimized.

A flash memory initialization method executed by a flash memory initialization device to initialize a flash memory device having a flash memory and a flash memory controller includes: determining an acceptable maximum number N of candidate addresses; determining a number M of different capacity sizes; classifying the candidate addresses into M portions; determining a difference value between two address values of any two adjacent addresses among the m-th portion of candidate addresses; determining multiple address values of the m-th portion of candidate addresses according to the difference value; and determining actual addresses of the m-th portion of candidate addresses according to the multiple address values; and controlling the flash memory controller to write the boot up information into at least one storage location corresponding to at least one of the m-th portion of candidate addresses according to the actual addresses.

Apparatuses and methods can be related to configuring interface protocols for memory. An interface protocol can define the commands received by a memory device utilizing pins of an interface of a memory device. An interface protocol used by a memory device can be implemented utilizing a decoder of signals provided through the pins of the memory device. The decoder utilized by a memory device can be selected by setting a mode register of the memory device.

A method comprising: allocating a first memory pool and a second memory pool, the first memory pool being allocated to a first application, and the second memory pool being allocated to a second application; receiving a first request for additional memory, the first request being submitted by the second application; assigning a portion of the first memory pool to the second application, the portion of the first memory pool including a set of memory chunks that are part of the first memory pool, the assigning of the portion including updating a first data structure portion to associate the second application with set of memory chunks; and notifying the second application that the portion of the first memory pool has been assigned to the second application.

A method for dynamic memory scheduling with enhanced bank-group batching is described. The method includes determining a read-bank group-spread of each rank, as a number of bank-groups of each respective rank targeted by at least one read instruction. The method further includes determining a write-bank group-spread of each rank, as a number of bank-groups of each rank targeted by at least one write instruction. The method also includes stalling a current batch of read instructions in a rank when the read-bank group-spread of the rank is less than a predetermined value. The method further includes stalling a current batch of write instructions in a rank when the write-bank group-spread of the rank is less than the predetermined value.

Disclosed embodiments relate to systems and methods to dually write micro-ops to a micro-op queue. A processor includes a micro-op cache communicatively coupled, via a first write port, to a micro-op queue, and a legacy fetch and decode pipeline communicatively coupled, via a second write port, to the micro-op queue, the processor to determine whether the micro-op cache stores a thread, the thread comprising a micro-op to be written to the micro-op queue, determine whether the legacy fetch and decode pipeline stores the thread if the micro-op cache does not store the thread, and write, via the micro-op queue, the micro-op from the thread to the micro-op queue responsive to the determination of whether the micro-op cache or the legacy fetch and decode pipeline stores the thread.

An X16 nonvolatile memory has 16 input/output (I/O) ports, identified as I/O ports [15:0], and adopts a conversion method, which allows the memory to operate in an X16 mode or in an X8 mode. The method includes receiving a first user command that is sent by an upper computer and belongs to a user mode; determining a disabling command for a module path of the high-bit I/O ports [15:8] according to the first user command; and executing the disabling command and disabling the module path for controlling the high-bit I/O ports [15:8] of the memory so as to operate in an X8 mode.

A memory controller controls access to a flash memory including a plurality of physical blocks, each of which includes a plurality of pages, based on a command assigned from a host system. The memory controller allocates a physical block within the flash memory in a prescribed search range as a prescribed physical block where management information is written, writes the management information necessary for accessing the flash memory to the prescribed physical block, and operates to search for the prescribed physical block when second firmware is read from the flash memory. The writing information, including the management information, is written to the prescribed physical block in a same format regardless of a type of flash memory. Information written to pages is sequentially read at prescribed page intervals in the prescribed search range in searching for the prescribed physical block.

A method for performing power management in a memory device, the associated memory device and the controller thereof, and the associated electronic device are provided. The memory device includes a non-volatile (NV) memory including at least one NV memory element. The method may include: during an initialization phase of the memory device, detecting whether a host device supports communications corresponding to a first communications protocol; and before detecting that the host device supports communications corresponding to the first communications protocol, controlling a physical layer (PHY) circuit within the memory device to keep staying at a power off state to save power, wherein the PHY circuit supports communications corresponding to the first communications protocol.

A system includes a memory and multiple processors. The memory further includes a shared section and a non-shared section. The processors further include at least a first processor and a second processor, both of which read-only access to the shared section of the memory. The first processor and the second processor are operable to execute shared code stored in the shared section of the memory, and execute non-shared code stored in a first sub-section and a second sub-section of the non-shared section, respectively. The first processor and the second processor execute the share code according to a first scheduler and a second scheduler, respectively. The first scheduler operates independently of the second scheduler.