Abstract: A mechanism is provided for firehose dumping modified data in a static random access memory of a hard disk drive to non-volatile memory of the hard disk drive during a power event. Responsive an indication of a power event in the hard disk drive, hard disk drive command processing is suspended. A token is set in the non-volatile storage indicating that flash memory in the non-volatile memory contains modified data. A portion of a static random access memory cache table containing information on the modified data in the static random access memory is copied to the flash memory. The modified data from the static random access memory is then copied to the flash memory. Responsive to a determination that the power event that initiated the copy of the modified data in the static random access memory to the flash memory is still present, the hard disk drive is shut down.

Abstract: Managing write-to-read turnarounds in an early read after write memory system is presented. Memory controller logic identifies a write operation's bank set, allows a different bank set read operation to issue prior to the write operation's completion, and allows a same bank set read operation to issue once the write operation completes. The memory controller includes operation counter logic, operation selection logic, operation acceptance logic, command formatting logic, and memory interface logic. The operation counter logic receives new-operation-related signals from the operation acceptance logic and, in turn, provides signals to the operation selection logic and the operation acceptance logic as to when to issue a read operation that corresponds to either an even DRAM bank or an odd DRAM bank.

Abstract: A memory profiling system profiles memory objects in volatile memory and identifies memory objects as candidates to be stored and read directly from nonvolatile memory. The profiling system monitors memory accesses via page faults and identifies a memory object to be loaded in volatile memory. The profiling system uses page faults to determine a page fault type and a write frequency for the memory object, and determines the memory object's memory access type. The profiling system determines whether the object's memory access type meets the capabilities of the nonvolatile memory technology. If the memory access type meets the nonvolatile memory technology capabilities, the profiling system identifies the memory object as a candidate to be transitioned to and read directly from nonvolatile memory (e.g., NOR and PCM). The profiling system stores the memory object candidates in nonvolatile memory such that the memory objects are read directly from nonvolatile memory.

Abstract: A processing system for use in an electronic device is disclosed. The processing system includes a memory unit, an application processor connected to the memory unit, and a baseband processor connected to the memory unit and the application processor. The memory unit is configured for storing information of the electronic device. The application processor is configured for handling applications of the electronic device. The baseband processor is configured for providing communication capabilities for the electronic device. The application processor includes a temperature detector configured for detecting the temperature of the application processor. When the sensed temperature of the application processor is higher than a predetermined temperature, the baseband processor is instructed by the application processor to share workload of the application processor.

Abstract: A computer memory, having one or more of a semiconductor memory device having an internal memory array comprising a plurality of semiconductor dynamic random access memory (DRAM) cells arranged in a matrix of rows and columns, and provided as a memory module rank of such memory devices arranged in an array on a DIMM of one or more of said semiconductor memory device on a substrate which can be coupled via a memory device data interface to a memory system as a memory subsystem, each of said memory device having a low power shut-down state that can be activated using a common memory data interface. Control of power to a DRAM issues over the data interface two commands to a DRAM power control command decode, a power-state program signal and a power-state reset signal as a power-state control commands to control the power state of said DRAM, and to activate for READ/WRITE a memory cell as a normal active or spare device.

Abstract: The present invention provides a memory controller which includes a host interface connected to a host apparatus and receives a first data write-in unit of reception data, a memory interface connected to nonvolatile semiconductor memory in which is written a second data write-in unit of data larger than the first data write-in unit of data, and transmits the first data write-in unit of write-in data, and a central processing unit, which writes the reception data in a temporary write-in block of the nonvolatile semiconductor memory via the memory interface, reads out from the temporary write-in block the write-in data corresponding to area data when a total amount of reception data received by the host interface has reached amount of the second data write-in unit of the area data, and writes the area data including the read-out write-in data in a target block different from the temporary write-in block.

Abstract: A method of changing a program for controlling a disk drive that includes an EEPROM. The method includes storing a program block to a disk area such that the program block is associated with a second area for storing the program block that is not utilized for a read operation from the disk area. The method also includes storing a program block that is associated with a first area to an area that includes at least a portion of the second area in the EEPROM such that the first area contained a program block that is utilized for a read operation from the disk area. In addition, the method includes changing the program block in the first area after storing to the second area. Moreover, the method includes storing to the second area the program block that is not utilized for a read operation from the disk area after storing to the first area.

Abstract: The present invention discloses a flash memory storage system, comprising at least one RAID controller; a plurality of flash memory cards electrically connected with the RAID controller; and a cache memory electrically connected with the RAID controller and shared by the RAID controller and the flash memory cards. The cache memory efficiently enhances the system performance. The storage system may comprise more RAID controllers to construct a nested RAID architecture.

Abstract: In one embodiment, the present invention includes an instruction decoder that can receive an incoming instruction and a path select signal and decode the incoming instruction into a first instruction code or a second instruction code responsive to the path select signal. The two different instruction codes, both representing the same incoming instruction may be used by an execution unit to perform an operation optimized for different data lengths. Other embodiments are described and claimed.

Abstract: A method of memory management for an apparatus having a non-volatile memory and a volatile memory includes the steps of forming a tree structure of entries in the volatile memory, in which the tree structure has a left branch and a right branch, and a difference of heights of the left branch and the right branch is equal to or less than one; and accessing an entry in the volatile memory through the tree structure.

Abstract: A bus-connected device includes a data storage element, a physical layer and a controller. The data storage element stores user data and multiple adaptations for multiple platform protocols. The physical layer uses at least a portion of a selected one of the multiple platform protocols to access the user data. The controller controls and communicates with the data storage element using a controller communication protocol that is neutral relative to the multiple platform protocols.

Abstract: A system communicating processors is provided. The system comprises a first processor, a second processor, a SRAM and a DMA unit. The DMA unit further comprises a detection unit to determine whether the SRAM is accessed by the second processor, wherein when the SRAM is not accessed by the second processor, the access control of the SRAM is transferred to the DMA unit, and data communication between the first processor and the second processor is transmitted by the DMA unit.

Abstract: Methods and apparatus involve booting a computing device from a flash device. The flash device has memory partitions, including a read-only and a read/write partition. The read-only includes an operating system for use by the computing device and defines an initial system state. The read/write is configured to store a delta from the initial system state. Upon booting the computing device subsequent to an initial boot, the delta and the initial system state together define the whole system state. In other features, a write engine from the read-only partition tracks changes to the initial system state and writes some, but not all of the changes back to the read/write partition thereby minimizing a number of writes to the flash memory. In this manner, the speed of the flash memory can be used to quickly boot/reboot a computing device, while avoiding the wear limits associated with writing to flash devices.

Abstract: Methods and apparatus to improve throughput and efficiency in memory devices are described. In one embodiment, a memory controller may include scheduler logic to issue read or write requests to a memory device in an optimal fashion, e.g., to maximize bandwidth and/or reduce latency. Other embodiments are also disclosed and claimed.

Abstract: Embodiments of the invention provide a memory device that may be accessed by a plurality of controllers or processor cores via respective ports of the memory device. Each controller may be coupled to a respective port of the memory device via a data bus. Each port of the memory device may be associated a predefined section of memory, thereby giving each controller access to a distinct section of memory without interference from other controllers. A common command/address bus may couple the plurality of controllers to the memory device. Each controller may assert an active signal on a memory access control bus to gain access to the command/address bus to initiate a memory access.

Abstract: In one embodiment, a memory system is disclosed. The memory system has at least one memory chip having an address and data interface coupled to an internal address and data bus, and a memory controller and interface chip also having a an address and data interface coupled to the address and data interface of the at least one memory chip via an internal address and data bus. The at least one memory chip, the memory controller and interface chip and the internal address and data bus are disposed within a common chip package. The memory controller and interface chip has an external interface configured to be coupled to a standard memory bus via external contacts of the common chip package.

Abstract: Embodiments of the invention are generally directed to systems, methods, and apparatuses for in-band data mask bit transmission. In some embodiments, one or more data mask bits are integrated into a partial write frame and are transferred to a memory device via the data bus. Since the data mask bits are transferred via the data bus, the system does not need (costly) data mask pin(s). In some embodiments, a mechanism is provided to enable a memory device (e.g., a DRAM) to check for valid data mask bits before completing the partial write to the DRAM array.

Abstract: Embodiments of an I/O module, processing platform, and method for extending a memory interface are generally described herein. In some embodiments, the I/O module may be configured to operate in a memory module socket, such as a DIMM socket, to provide increased I/O functionality in a host system. Some system management bus address lines and some unused system clock signal lines may be reconfigured as serial data lines for serial data communications between the I/O module and a PCIe switch of the host system.

Abstract: The present invention discloses a portable computing device (100) including a processor (102), alternate memory (106), and a DRAM memory (108). Under normal operating conditions, providing full functionality of the device, a full code instantiation in the DRAM is executed, providing operating system, user interface and application execution functionality. A reduced code instantiation (114) which duplicates certain elements of the operating system, user interface, and application code is maintained in the low power memory. When a condition occurs that dictates or allows, execution is switched from the full code instantiation to the reduced code instantiation, and the DRAM is shut off.

Abstract: A microprocessor includes one or more N-way caches and a way prediction logic that selectively enables and disables the cache ways so as to reduce the power consumption. The way prediction logic receives an address and predicts in which one of the cache ways the data associated with the address is likely to be stored. The way prediction logic causes an enabling signal to be supplied only to the way predicted to contain the requested data. The remaining (N?1) of the cache ways do not receive the enabling signal. The power consumed by the cache is thus significantly reduced.

Abstract: A memory system (250) includes a plurality of memory devices (260) adapted to be coupled to an interface (140), an indicator (272) for indicating a type of the plurality of memory devices (260), and an override circuit (280) having a first terminal adapted to be coupled to the interface (140), a second terminal coupled to the plurality of the memory devices (260), and a control input for receiving a control signal. The override circuit (280) is responsive to the control signal to alter an operation of the memory system (250).

Abstract: In one embodiment, the present invention includes a method for selecting first data received in a first die of a multi-chip package (MCP) from a second die of the MCP via an intra-package link for output from a selector during a first clock period of a first clock signal, selecting second data transmitted from the second die to the first die for output from the selector during a second clock period, and transmitting the first and second data from the MCP via an external link. Other embodiments are described and claimed.

Abstract: A flash memory based storage device may utilize magnetoresistive random access memory (MRAM) as at least one of a device memory, a buffer, or high write volume storage. In some embodiments, a processor of the storage device may compare a logical block address of a data file to a plurality of logical block addresses stored in a write frequency file buffer table and causes the data file to be written to the high write volume MRAM when the logical block address of the data file matches at least one of the plurality of logical block addresses stored in the write frequency file buffer table. In other embodiments, upon cessation of power to the storage device, the MRAM buffer stores the data until power is restored, after which the processor causes the buffered data to be written to the flash memory under control of the flash memory controller.

Abstract: Systems and methods for streaming video over multiple HTTP channels are provided. The client may have control over the channels, allowing the client to control the amount and source of data received. Data requested by the client may be separated into a set of layers, with each layer being assigned to a separate channel. The client may adjust the number of layers requested based on a variety of factors. Layers may be requested from multiple remote sources, providing the client with additional control over the specific bandwidth profile of received data.

Abstract: A computer system includes a CPU and a system on chip (SoC) processor electronically connected with the CPU in the computer system. The CPU and the SoC processor do not work simultaneously. The CPU processes work and a service when the computer system is powered on. The SoC processor continues processing the work and the service that are unfinished after the computer system is shut down.

Abstract: Solid-state memory and mechanical disk memory can be used together to create a reliable storage unit with desirable performance characteristics. Initially, memory can be entered to the solid-state memory until filled as well as backed-up upon the mechanical disk memory. After the solid-state memory fills, less used information can be deleted from the solid-state memory yet retained upon the mechanical disk such that the less used information is not lost. To determine information use, an algorithm can be employed, such as an exponential algorithm.

Abstract: An electronic system with time-sharing bus includes a controller, a storage element, a first electronic element, and a shared bus. The controller receives a command to generate a set of enable signals and a set of operation signals. The storage element has a first set of input ends coupled to the controller for receiving a first enable signal of the set of enable signals. The first electronic element has a first input end coupled to the controller for receiving a second enable signal of the set of enable signals. The shared bus is coupled between the controller and the storage element, and is coupled between the controller and the first electronic element. The shared bus provides the set of operation signals to the storage element while the first electronic element is disabled and provides the set of operation signals to the first electronic element while the storage element is disabled.

Abstract: A stacked memory apparatus operating with a compound read buffer is disclosed. The stacked memory apparatus includes an interface device having a main buffer and a plurality of memory devices each having a device read buffer. Systems incorporating one or more stacked memory apparatuses and related method of performing a read operation are also disclosed.

Abstract: In a particular embodiment, a controller is adapted to perform a garbage collection operation to remove redundant data, to predict a performance parameter associated with performance of the garbage collection operation, and to abort the garbage collection operation when the predicted performance parameter exceeds a threshold.

Abstract: In one embodiment, a data storage system includes a solid state data storage device and a memory controller in signal communication with the solid state data storage device. The memory controller includes a processor, a local memory, and an accelerator coupled between the processor and the local memory. The accelerator includes logic circuitry configured to perform data management for the local memory.

Abstract: The present invention discloses a control method of a multi-channel hybrid density memory storage device for access a user data. The storage device includes a plurality of low density memories (LDM) and high density memories (HDM). The steps of the method comprises: first, determining where the user data transmitted; then, using one of two error correction circuits which have different error correction capability to encode or decode the user data.

Abstract: An integrated buffer device. One embodiment provides a receiving unit and a logic unit to control the operation of the buffer device based on a setting signal.

Abstract: In a system, a memory bus has a first bus segment coupled to a memory controller that includes control logic and a first memory device, a second bus segment coupled to a second memory device, and a switch to selectively couple and decouple the first bus segment and the second bus segment in response to control information from the control logic. Note that the control logic may output control information to the switch to selectively decouple the first bus segment and the second bus segment to effect a change in an electrical length of the memory bus to enable data transfer with respect to the first memory device at a first data rate. Additionally, the control logic may output control information to the switch to selectively couple the first bus segment and the second bus segment to effect another change in the electrical length of the memory bus to enable data transfer with respect to the second memory device at a second data rate that is slower than the first data rate.

Abstract: An accelerator device including a cache memory, a controller that is electrically coupled to the cache memory, a host computer connecter that is electrically coupled to the controller, and a removable storage device connector that is electrically coupled to the controller. The accelerator device can be electrically coupled to a host computer via the host computer connector. The accelerator device can also be electrically coupled to a removable storage device via the removable storage device connector. When the accelerator device is electrically coupled to the host computer and the removable storage device is electrically coupled to the accelerator device, the controller caches data sent from the host computer to the removable storage device in the cache memory prior to the data being sent from the accelerator device to the removable storage device.

Abstract: A memory access apparatus and a display using the same are provided. The memory access apparatus includes a dynamic memory, a plurality of clients and a memory management unit. The dynamic memory is used to store a plurality of memory data. The clients access the dynamic memory and each client has a priority. The memory management unit executes an access action of the clients for the dynamic memory respectively according to the priorities thereof. Besides, the memory management unit has at least one buffer area built therein. The buffer area is used to temporarily store a plurality of buffer data generated while the access action is performed.

Abstract: A technique to increase transfer rate of command and address signals via a given number of command and address pins in each of one or more integrated circuit memory devices during a clock cycle of a clock signal. In one example embodiment, the command and address signals are sent on both rising and falling edges of a clock cycle of a clock signal to increase the transfer rate and essentially reduce the number of required command and address pins in each integrated circuit memory device.

Abstract: Disclosed is a store and forward device that reduces latency. The store and forward device allows front end devices having various transfer protocols to be connected in a single path through a RAM, while reducing latency. Front end devices that transfer data on a piecemeal basis are required to transfer all of the data to a RAM prior to downloading data to a back end. Front end devices that transfer data in a single download begin the transfer of data out of a RAM as soon as a threshold value is reached. Hence, the latency associated with downloading all of the data into a RAM 118 and then transferring all of the data out of the RAM is eliminated.

Abstract: A dynamic random access memory device (DRAM) receiver circuit includes an input to receive a data signal, and also includes decision circuitry to make a decision about the received data signal based on a present sampled data signal and a coefficient value corresponding to at least one of a previously sampled data signals.

Abstract: A Registered DIMM (RDIMM) system with reduced electrical loading on the data bus for increases memory capacity and operation frequency. In one embodiment, the data bus is buffered on the DIMM. In another embodiment, the data bus is selectively coupled to a group of memory chips via switches.

Abstract: A system comprises a general-purpose memory, a lockable memory, a memory management unit, and a processor. The general-purpose memory includes data for a first set of addresses. The lockable memory includes data for a second set of addresses. The memory management unit selectively writes data to one of the general-purpose memory and the lockable memory and selectively locks the lockable memory by preventing writes to the lockable memory. The processor instructs the memory management unit to unlock the lockable memory before requesting a write to one of the second set of addresses.

Abstract: A microcomputer includes a first CPU, a first bus, a first memory, a second CPU, a second bus, and a second memory. The first memory and the second memory are arranged in address spaces individually managed by the first CPU and the second CPU corresponding to the memories. An address translation circuit is provided. When a task so programmed to have a data area in the first memory is transferred to the second memory and executed by the second CPU, the address translation circuit carries out the following processing: the address translation circuit translates an address outputted from the second CPU so that access to the first memory by the task becomes access to the second memory. As a result, the number of access cycles is reduced and degradation in computing capability is avoided when a task is transferred between CPUs for load sharing.

Abstract: One embodiment of the present invention sets forth an abstracted memory subsystem comprising abstracted memories, which each may be configured to present memory-related characteristics onto a memory system interface. The characteristics can be presented on the memory system interface via logic signals or protocol exchanges, and the characteristics may include any one or more of, an address space, a protocol, a memory type, a power management rule, a number of pipeline stages, a number of banks, a mapping to physical banks, a number of ranks, a timing characteristic, an address decoding option, a bus turnaround time parameter, an additional signal assertion, a sub-rank, a number of planes, or other memory-related characteristics. Some embodiments include an intelligent register device and/or, an intelligent buffer device. One advantage of the disclosed subsystem is that memory performance may be optimized regardless of the specific protocols used by the underlying memory hardware devices.

Abstract: The method controls processing units (10) in a distributed computer system. At least one stream (4) of messages (2) is sent by a client unit (14) to each of the processing units (10). Each message (2) includes an identifier, member of an ordered group. The messages (2) are sent in sequence of their identifier. A controlling unit (12) sends a request (6) for performing an action to the processing units (10). The request (6) includes a trigger, member of the ordered group. If the identifier of a received message (2) is equal to or larger than the trigger, the processing unit (10) triggers the action. The method also relates to a system for controlling processing units (10), to a processing unit (10), and to a controlling unit (12).

Abstract: The invention relates generally to computer memory access. Embodiments of the invention provide a multi-level page-walk apparatus and method that enable I/O devices to execute multi-level page-walks with an out-of-order memory controller. In embodiments of the invention, the multi-level page-walk apparatus includes a demotion-based priority grant arbiter, a page-walk tracking queue, a page-walk completion queue, and a command packetizer.

Abstract: A bridge circuit includes a bus, a memory interface module, a memory control module, and an external storage control module. The memory interface module receives a memory address from a processor via a memory interface and outputs the memory address to the bus. The memory address corresponds to one of a plurality of address regions of an address space of the processor. The memory control module receives the memory address via the bus and communicates with a memory when the memory address corresponds to a first one of the plurality of address regions. The external storage control module receives the memory address via the bus and communicates with an external storage device when the memory address corresponds to a second one of the plurality of address regions.

Abstract: In the present invention, a memory, and in particular, a NOR emulating memory comprises a memory controller having a non-volatile memory for storing program code to initiate the operation of the memory controller. The controller has a first bus for receiving address signals from a host device and a second bus for interfacing with a RAM memory, and a third bus for interfacing with a NAND memory. A volatile RAM memory is connected to the second bus. A NAND memory is connected to the third bus. The controller receives commands and a first address from the first bus, and maps the first address to a second address in the NAND memory, and operates the NAND memory in response thereto. The RAM memory serves as cache for data to or from the NAND memory. The controller also maintains data coherence between the data stored in the RAM memory as cache and the data in the NAND memory.

Abstract: In a memory device to store information, the device includes a memory core to store information, a memory controller to control storage and retrieval of the information, and a regulator coupled to the memory controller and the memory core, wherein the regulator is operable to adjust an internal voltage to the memory core in response to commands from the memory controller.

Abstract: A computerized data storage system includes at least one storage device including a nonvolatile writable medium; a cache memory operatively coupled to the storage port and including a data storing area and a data management controller and a storage port. The storage port is operable to connect to a host computer, receive and send I/O information required by the host computer. The storage port is also operable to receive a request to read data, and, in response to the request to read data, the storage port is operable to send the data stored in the data storing area of the cache memory. The storage port is further operable to receive a request to write data, and, in response to the request to write data, the storage port is operable to send the write data to the data storing area of the cache memory.

Abstract: A method for implementing prioritized refresh of a multiple way, set associative DRAM based cache includes identifying, for each of a plurality of sets of the cache, the existence of a most recently used way that has not been accessed during a current assessment period; and for each set, refreshing only the identified most recently used way of the set not accessed during the current assessment period, while ignoring the remaining ways of the set; wherein a complete examination of each set for most recently used ways therein during the current assessment period constitutes a sweep of the cache.

Abstract: Managing write-to-read turnarounds in an early read after write memory system is presented. Memory controller logic identifies a write operation's bank set, allows a different bank set read operation to issue prior to the write operation's completion, and allows a same bank set read operation to issue once the write operation completes. The memory controller includes operation counter logic, operation selection logic, operation acceptance logic, command formatting logic, and memory interface logic. The operation counter logic receives new-operation-related signals from the operation acceptance logic and, in turn, provides signals to the operation selection logic and the operation acceptance logic as to when to issue a read operation that corresponds to either an even DRAM bank or an odd DRAM bank.