Abstract: A synchronous flash memory includes an array of non-volatile memory cells. The memory array is arranged in rows and columns, and can be further arranged in addressable blocks. Data communication connections are used for bi-directional data communication with an external device(s), such as a processor or other memory controller. The memory can output data from storage registers on the data communication connections during a series of clock cycles to provide a burst of register data. The memory can also provide the register data in accordance to a defined clock latency value. The register data can include status data, operating setting data, manufacture identification, and memory device identification.

Abstract: A system balances bandwidth used by a data stream. The system receives data in the data stream and partitions the data into bursts. The system then identifies whether a size of a current one of the bursts is less than a size of a maximum burst associated with the data stream and schedules an additional burst in the data stream when the current burst size is less than the maximum burst size. The system transmits the current burst and the additional burst to balance bandwidth used by the data stream.

Abstract: An apparatus enables the reordering of a block of n-bit words output from a plurality of memory cells according to information in certain address bits before outputting at least one n-bit word from a memory device while ignoring those certain address bits before inputting at least one n-bit word into the plurality of memory cells. The apparatus may additionally comprise examining at least two of the least significant bits of a column address and wherein the reordering is responsive to the examining. Thus, for reads a specific 8 bit burst is identified by the most significant column address bits while the least significant bits CA0–CA2 identify the most critical word and the read wrap sequence after the critical word. For writes, the burst is identified by the most significant column addresses with CA0–CA2 being “don't care” bits assumed to be 000.

Abstract: A data transfer control system receives a command packet ORB (SBP-2) transferred through a bus BUS1 (IEEE1394), and issues a command included in the ORB to a device connected with a bus BUS2 (ATA (IDE)/ATAPI). The data transfer control system sets a sufficiently large fixed DMA data length irrespective of the type of the issued command, and instructs start of DMA transfer to or from the device connected with the bus BUS2. The data transfer control system aborts the DMA transfer when a device connected with BUS2 informs of completion of command processing. As the fixed DMA data length, a value greater than a storage capacity of a storage or a value greater than a data length which can be designated by a command is employed. The data transfer control system issues a command included in the ORB to a device connected with the bus BUS2 without decoding the command.

Abstract: A bus that may be used in an integrated circuit chip. The bus generally comprises a master interface, a slave interface, and a control logic. The master interface may be configured to (i) receive an early command signal having a predetermined timing relationship to a first clock edge and (ii) present a bus wait signal proximate a second clock edge. The slave interface may be configured to (i) present a command signal a delay after the first clock edge and (ii) receive a slave wait signal. The control logic may be configured to (i) register the early command signal to generate the command signal and (ii) convert the slave wait signal into the bus wait signal.

Abstract: A digital image storage system includes a digital camera having a first terminal for data communication in accordance with a data communication interface standard and an adapter for the digital camera for communicating with the digital camera. The adapter has a second terminal for data communication in accordance with the same data communication interface standard as in the first terminal. The digital image storage system further includes a data storage having a third terminal for data communication in accordance with the same data communication interface standard as in the first terminal. The data storage is capable of communicating with the digital camera by way of the adapter through a connection between the third and the second terminals and also capable of directly communicating with the digital camera through a connection between the third and the first terminals.

Abstract: Schemes for determining whether all of the fragments of a datagram are received are described herein. The schemes described herein can allocate fifteen bits of memory to one or more counters to facilitate a determination of whether all of the fragments of a datagram are received.

Abstract: A method includes reordering a non-linear burst transaction initiated by a processor targeting a peripheral bus to a linear order, and retrieving the linear burst from the peripheral bus.

Abstract: A small card adaptor into which a small card is inserted so as to be connected to a personal computer includes a small card identifying portion for identifying the kind of the inserted small card, and a controller for receiving an instruction issued by the personal computer based on the kind of the small card identified by the small card identifying portion and transferring the received instruction to the small card.

Abstract: A data transfer method for a Universal Serial Bus (USB) device is provided. The data transfer rate of a bulk transfer transmission in the USB is detected first for selecting a transfer transmission having a better data transfer rate between the bulk transfer transmission in the USB and an interrupt transfer transmission in the USB, so as to ensure the data transfer bandwidth in the USB is better utilized by the USB device.

Abstract: The invention relates to an apparatus and a method for accessing memories having a time-variant response over a PCI bus by using two-stage DMA transfers. The invention provides a method for executing a read request over a PCI bus by transferring the requested data from a main memory of a PCI card to a device located on the PCI bus, comprising the steps of obtaining an access request from a read access queue, transferring, by a first DMA transfer, the requested data from the main memory to a buffer memory on the PCI card, and transferring, by a second DMA transfer, the data from the buffer memory to the device.

Abstract: A network driver provides additional transmit commands to a network interface when the number of transmit commands at the network interface falls below a specified threshold.

Abstract: A system and method for transferring data over an external transmission medium. A host computer is coupled to a device through a serial bus. A transfer object is configurable to encapsulate data transfer-related functionality, providing a generic interface for transmission of data over a variety of external transmission media and protocols. A user makes one or more transfer requests. Transfer objects corresponding to each request are built and linked together to form a sequential chain. The requests of the transfer objects are executed sequentially. If the current transfer object is the first in the chain, the request is executed on a current thread at passive level or higher, otherwise the request is executed on a system (kernel) thread at dispatch level. When a response to the request returns, control is returned to the current transfer object. The process is repeated until all transfer objects are processed.

Abstract: A communications control circuit includes: a common work RAM storing communications data; an address register; a data-set-count register; an information register; an address counter; a data set counter; a RAM control circuit reading transmission data from a common memory in response to a transmission data request, writing reception data to the common memory in response to a reception data request, and generating a counter clock; a transmission circuit; a reception circuit; and a communications controller setting the address counter to an address upon transmission/reception and a counter to a number of sets of data, and if transmission/reception has been successful, writing the address back to the address register and the number of sets of data back to the register.

Abstract: In one embodiment, a method may include, if an amount of data requested to be transferred by a data transfer request according to a first protocol exceeds a maximum data transfer amount permitted to be requested by a single data transfer request according to a second protocol, generating one data transfer request according to the second protocol and a data structure, and modifying, at least in part, another data structure. This data transfer request may request transfer of a portion of the data. The data structure may include one or more values identifying, at least in part, another portion of the data. The modifying may be based, at least in part, upon the one or more values. The other data structure may include, prior to being modified, one or more other values indicating, at least in part, one or more parameters of the one data transfer request.

Abstract: A synchronous bus system that enables the bus lengths between devices to be extended such that the timing budget is more than one clock cycle. A reset process resets the transmission and reception circuitry and both circuitry function according to prespecified parameters relative to the deassertion of the reset signal such that the amount of logic required to latch and sample the data is minimized. As the timing budget is not limited to one clock cycle, devices can be spaced further apart providing more physical space for devices. Furthermore, skew sensitivity is reduced as to the skew is distributed over multiple clock periods.

Abstract: The method and apparatus presented are targeted to improve the performance of moving data between memory portions connected by a system bus where writes have higher performance than reads, such as the PCI bus. Due to the PCI bus design, read requests from memories connected across the PCI bus take a significantly longer time to complete than performing a write operation under the same circumstances. The present invention uses the faster write operations across the PCI bus, and queue management techniques, to take advantage of the relative speed of writes in a PCI system. The overall result is significant performance enhancement, which is especially useful in service aware networks (SAN) where operation at wired-speed is of paramount importance.

Abstract: A multiprocessor switching device substantially implemented on a single CMOS integrated circuit is described in connection with a descriptor-based packet processing mechanism for use in efficiently assigning and processing packets to a plurality of processors. A plurality of descriptors associated with each packet transfer are written back to memory in order, divided into subset groups and assigned to processors, where each processor searches the assigned subset for EOP and associated SOP descriptors to process.

Abstract: A data bus bridge circuit and method are provided for coupling a slave device with a data bus in a system in which data words are transferred between a master device and the slave device over the data bus. The bridge circuit removes master-induced stalls of burst transfers by converting those burst transfers into a plurality of separate, independent sub-bursts.

Abstract: Logic (also called “re-ordering semaphore”) issues semaphore grants to access a shared resource in an order different from the order in which semaphore requests for accessing the shared resource are received. The re-ordering semaphore needs to receive a semaphore release between any two semaphore grants. There is no limit on the duration between a semaphore grant and a semaphore release, so that a task that receives a semaphore grant can use the shared resource for any length of time. In one embodiment, each request is associated with a number indicative of the order in which grants are to be issued, and the re-ordering semaphore uses this number in deciding which request is to be granted. The number can be a sequence number that is indicative of the order of arrival of packets that generated the requests.

Abstract: Techniques to buffer and present chunks are disclosed. In some embodiments, a first interface may receive chunks of a first cache line, and a second interface may receive chunks of a second cache line. A buffer may store chunks of the first cache line in a first chunk order and may store chunks of the second cache line in a second chunk order. A control unit may present a requester via the second interface with one or more chunks of the first cache line from the buffer.

Abstract: An improved descriptor system is provided in which read pointers indicate to a host and a peripheral the next location to read from a queue of descriptors, and write pointers indicate the next location to be written in a queue. The system also allows an incoming descriptor to point to a plurality of data frames for transfer to the host processor, wherein the peripheral need not read a new descriptor each time a frame is to be transferred to the host.

Abstract: Embodiments are provided in which a method is described for transferring data in a digital system including a first bus, a second bus, a PCI-X bridge coupling the first and second buses, and a first device and a second device residing on the first and second buses, respectively. The first bus has the same or higher bandwidth than that of the second bus. According to the method, the PCI-X bridge immediately starts or resumes forwarding split completion data from the first device to the second device if the first device starts or resumes split completion data transfer to the PCI-X bridge at the beginning of a block (i.e., the start or resume byte address has the form of 128N). If the first device starts transfer to the PCI-X bridge not at the beginning of a block, the PCI-X bridge refrains from forwarding split completion data until (a) the first device sends the data byte at the beginning of the next block to the PCI-X bridge or (b) the byte transfer count is exhausted, whichever occurs first.

Abstract: A memory device may be implemented to respond to and one or more command encodings that specify different burst lengths than the burst length indicated by the current burst length setting for the memory device. For example, a memory device may include a memory array and a mode register configured to store a value indicating a current burst length. The memory array may be configured to perform a first burst access having a first burst length in response to receiving a first command encoding and to perform a second burst access having a second burst length, which does not equal the current burst length, in response to receiving a second command encoding. A memory controller may be implemented to generate to and one or more command encodings that specify different burst lengths than the burst length indicated by the current burst length setting for a targeted memory device.

Abstract: A computer system component serves as a burst mode data transfer proxy for bridging a bus operable in burst transfer mode and a single transfer mode bus. FIFOs, associated with respective DMA channels, provide a shared area for assembling and disassembling bursts on behalf of subsystems on the single transfer mode bus. The component also performs DMA functions.

Abstract: The present invention includes a method and device for controlling the data length of read and write operations performed on a memory device. The method includes determining a first number of channels available to a memory controller operatively coupled to the memory device; determining a second number representative of the number of populated channels; calculating a burst length based on the first and second numbers; and programming the memory controller to use the burst length as the data length of read and write operations performed on the memory device.

Abstract: A buffer switch comprises a data memory that stores a plurality of data. A cache memory comprises a plurality of FIFO mini-queues each storing a plurality of descriptors each corresponding to a respective one of the plurality of data. An output memory comprises a plurality of output queues. A burst writer simultaneously transfers M ones of the plurality of descriptors stored in a corresponding one of the plurality of mini-queues to at least a corresponding one of the plurality of output queues. The burst writer accesses the output memory, when the output memory is available, once for every M ones of the plurality of descriptors.

Abstract: A head and tail caching system. The system includes a tail FIFO memory having a tail input to receive incoming data. A memory is included that is operable to store data that is output from the tail FIFO and output the stored data at a memory output. A multiplexer is included having first and second multiplexer inputs coupled to the tail FIFO and the memory, respectively. The multiplexer has a control input to select one of the multiplexer inputs to coupled to a multiplexer output. A head FIFO memory receives data from the multiplexer output, and outputs the data on an output data path. A controller is operable to transfer one or more blocks data having a selected block size from the tail FIFO to the memory and from the memory to the head FIFO, to achieve a selected efficiency level.

Abstract: When a master device resets, flush commands are issued to a flush master register in the slave devices. A comparator compares the identification of the master device associated with the flush command to an identification of the master device associated with data for return by the slave device. A gate is responsive to the comparator to flush data from the data register that are pending for return.

Abstract: A method comprising reordering a block of n-bit words output from a memory array according to information in certain address bits before outputting at least one n-bit word from a memory device and ignoring said certain address bits before inputting at least one n-bit word into said memory array. The method may additionally comprise examining at least two of the least significant bits of a column address and wherein said reordering is responsive to said examining step. Thus, for reads a specific 8 bit burst is identified by the most significant column address bits while the least significant bits CA0-CA2 identify the most critical word and the read wrap sequence after the critical word. For writes, the burst is identified by the most significant column addresses with CA0-CA2 being “don't care” bits assumed to be 000.

Abstract: The asynchronous data burst transfer circuit includes a data burst transfer oscillation circuit which outputs n strobe signals of mutually different phases, plural parallel-serial conversion circuits which convert n-bit parallel signals into serial signals, and plural serial-parallel conversion circuits which convert serial signals into n-bit parallel signals. The parallel-serial conversion circuits convert every n-bit parallel signals of data read from a memory into serial signals based on the strobe signals, and transfer the serial signals. The serial-parallel conversion circuits convert the received serial signals into n-bit parallel signals based on the strobe signals, thereby obtaining the parallel signals as the original data.

Abstract: An electrically alterable semiconductor memory comprises at least two substantially independent memory banks, and a first control circuit for controlling operations of electrical alteration of the content of the memory. The first control circuit permits the selective execution of an operation of electrical alteration of the content of one of the at least two memory banks. The memory also comprises second control circuit that permits, simultaneously with said operation of electrical alteration of the content of one of the at least two memory banks, a burst mode, page mode, or standard read operation for reading the content of the other memory bank.

Abstract: A slave device includes a command FIFO that stores commands for a device controller on a first-in, first-out basis to execute a read or write transaction. Commands are received from the data bus by an input register which supplies write commands to a dynamic stage register. A multiplexer couples the dynamic stage register and the input register to the command FIFO so that only the initial command of a single or multi-beat write burst is written to the command FIFO from the dynamic stage register. Consequently, separate write commands are not stored for each data beat, resulting in minimal areal size for the integrated circuit chip containing the command FIFO. Instead, a counter counts the number of beats in the multi-beat burst, so that when the last beat is received, the initial command and the beat count are supplied to the command FIFO.

Abstract: A method for facilitating transfer of data between a master block and a slave block through a bus. The method includes ascertaining a transfer size of the data. The method also includes designating a first possible transfer size in a set of possible transfer sizes a chosen transfer size, the set of possible transfer sizes including possible transfer sizes ranging from 20 to 2n, where 2n at least equals to the largest transfer size desired between the master block and the slave block, the first possible transfer size presenting the largest possible transfer size in the set of possible transfer sizes that is less than or equal to the transfer size. The method additionally includes transferring a first data portion of the data from the master block to the slave block, the first data portion having a size that is equal to the chosen transfer size.

Abstract: A data processing system enables faster exchange of data between data processing units having a CPU, and simplifies the writing of a data exchange program for the data processing units. A data processing apparatus 3 has a communication unit 4 with a first storage unit 31 and a second storage unit 32. The first storage unit 31 is used for sending data from the first data processing unit 1 to the second data processing unit 2. The second storage unit 32 is used for sending data from the second data processing unit 2 to the first data processing unit 1. Data can therefore be asynchronously exchanged between the data processing units without coordinating control of CPU operations in the data processing units, and control of data communication between the data processing units is simplified.

Abstract: A memory controller for a multi-byte burst memory device may control access to memory based on parameters set up by a client. These parameters may include a byte address and a byte count that indicates the number of bytes the client is requesting from memory. These values, and an integer representing the number of bytes in a burst-accessed word, may be operated on to produce a word that may be used to identify valid bytes in the burst-accessed word.

Abstract: In a first embodiment, an applications programming interface (API) implements and manages isochronous and asychronous data transfer operations between an application and a bus structure. During an asynchronous transfer the API includes the ability to transfer any amount of data between one or more local data buffers within the application and a range of addresses over the bus structure using one or more asynchronous transactions. An automatic transaction generator may be used to automatically generate the transactions necessary to complete the data transfer. The API also includes the ability to transfer data between the application and another node on the bus structure isochronously over a dedicated channel. During an isochronous data transfer, a buffer management scheme is used to manage a linked list of data buffer descriptors.

Abstract: Embodiments of the invention provide a multi-chip system that includes a first and a second semiconductor memory device. The memory devices are mounted in a single package. The multi-chip system has a continuous burst read mode of operation, in which a read operation can be successively carried out without latency even though an address region moves from the first semiconductor memory device to the second memory device.

Abstract: A system and method for transmitting parallel data from a source to a destination over a plurality of high speed serial lines operates reliably even in the presence of data skew. The high speed data transmission system includes a protocol generator, a de-skew circuit, and a plurality of high speed serial lines coupled between the protocol generator and the de-skew circuit. Respective serial representations of parallel data words are transmitted to the destination over a plurality of serial data lines, and a clock signal is transmitted to the destination over a clock line in parallel with the serial data lines. The clock signal has at least one data bit of each parallel data word encoded thereon. The de-skew circuit aligns regenerated parallel data words using the respective data bits encoded on the clock signal to eliminate skew among the data bits, and regenerates the parallel data from the aligned parallel data words.

Abstract: A method and system for an I/O coupling channel to operate in a plurality of modes. The first mode is the new mode providing peer operation with many times more message passing facilities as the old mode. The second mode is used to connect the new channels through a converter to multiple old channels. In this mode, the new channel distributes its message passing resources among the multiple sink ports of the converter that are attached to old channels. The converter keeps no state information and only adjusts line speeds, routs outbound packets, and adds source information to inbound packets. The new channel operating in old compatibility mode gives the illusion to the software of multiple separate channels, one for each converter sink port.

Abstract: Methods and associated structure for providing a substitute, predetermined, fixed length when transferring burst transactions from one device to another through a bridge device where the burst transaction has an indefinite length specified. In one exemplary preferred embodiment, an AMBA AHB bus bridge slave device recognizes initiation of burst transactions of a indefinite length and translates the indefinite length burst transactions on the first bus into appropriate bus transactions for application to a second bus or device having a predetermined fixed length for the transferred the burst transactions. In a second embodiment, a slave device acting as a bridge receives a burst of indefinite length and translates the bus request into one with a predetermined fixed length for application to a device controller.

Abstract: A DMA controller arbitrates and selects a DMA control information signal received from at least one of a plurality of DMA request blocks and accesses an SDRAM on the basis of the selected DMA control information signal. In the DMA controller, an SDRAM controller detects using a detector the number of possible sequential accesses on the basis of a DMA start address signal, compares using a comparator this number of possible sequential accesses with the burst DMA request number designated by a BSTNUM signal, selects not larger one of the two numbers, and sets the number of sequential DMAs to be actually executed to the selected number. Accordingly, with a simple configuration, sequential access is made possible starting from an arbitrary address.

Abstract: A method and an architecture capable of adaptively accessing data and instructions are provided, in which a plurality of data transfer levels are predefined and a current data transfer level is used for accessing data and instructions of a memory. Each data transfer level corresponds to a length of a continuous data transfer via an interface between the memory and a cache device. Thus, the invention can dynamically adjust the current data transfer level based on burst lengths actually occurred as a processor kernel accesses data/instructions.

Abstract: A system and method for reducing the number of memory accesses by a hardware device to a descriptor memory is disclosed. Methods, systems and articles of manufacture consistent with the present invention enable software to embed a subsequent descriptor it is posting in the descriptor memory into a current descriptor listed in the descriptor memory. Additionally, hardware is configured to transmit a data packet associated with the current descriptor to a recipient device. When hardware receives an acknowledgment message from the recipient device associated with the transmitted data packet, it fetches the current descriptor to update a completion code within the current descriptor using a Read-Modify-Write (RMW) transfer sequence. As part of the RMW memory operation, hardware may use the embedded copy of the subsequent descriptor within the current descriptor to transmit the next data packet associated with the subsequent descriptor.

Abstract: A novel method of reading descriptors by a network interface is provided in a computer system having a host CPU and a memory containing descriptors arranged in a list. The method includes reading at least two descriptors in a single PCI bus transaction. The network interface comprises a PCI interface for providing connection to the system via a PCI bus, and descriptor management logic for reading descriptors from the memory via the PCI interface. The descriptor management logic is configured for reading more than one descriptor in a single PCI read transaction. After reading a first descriptor, the descriptor management logic reads a second descriptor following the first descriptor regardless of whether the second descriptor is owned by the network interface or the host CPU. The network interface performs a read operation to read a message buffer associated with the second descriptor if this descriptor is owned by the network interface.

Abstract: Disclosed is device and method for improved burst communication on a USB bus. In one embodiment, a USB Ethernet adapter device uses the USB Interrupt Channel to send a message to an Ethernet class driver, via the host USB stack, that the Ethernet adapter device has data to transmit on the USB. The interrupt message preferably includes the size of the data packet to be transmitted or the number of packets to send. The class driver responds by instructing the USB stack to configure a new Transfer Descriptor having buffer pointers of sufficient size for the data packet. The USB Host Controller then processes the Transfer Descriptor, thereby inviting the Ethernet adapter device to transmit its data and responsively storing the data in the predetermined buffer.

Abstract: A method and apparatus for a burst mode write in a shared bus architecture comprising detecting a write data burst, determining if at least one memory unit is available to receive the write data burst, writing the write data burst to the at least one memory unit if the at least one memory unit is available to receive data. Storing a first portion of the write data burst in a buffer, concurrently with activating the at least one memory unit to receive data, if the at least one memory unit is not available to receive data; writing a second portion of the write data burst to the at least one memory unit when the at least one memory unit is available to receive data, and writing the first portion of the write data burst from the buffer to the at least one memory unit after writing the second portion of the write data burst.

Abstract: A method and system of memory management incorporates multiple banks of memory devices organized into independent channels wherein each bank of memory devices contains duplicate data. A tree memory controller controls data read and write accesses to each of the banks in each of the channels. A bank queue for each bank in each channel keeps track of bank availability. When read or write requests are received at the tree memory controller, the controller checks the availability of each bank in a channel, identifies a first available bank, and executes the read request from the first available bank. In response to a write request, the controller blocks all read requests once it has confirmed that data to be written is complete for the selected memory word length. As soon as each bank queue for read requests is empty, the controller initiates burst mode transfer of the completed data word to all banks concurrently.

Abstract: A method and an architecture capable of programming and controlling access of data and instructions are provided. There are provided a plurality of data transfer levels, in which a current data transfer level is used for accessing data and instructions from an external memory. Each data transfer level corresponds to a length of a continuous data transfer via an interface between the memory and a high-speed access device. The current data transfer level is dynamically adjusted based on data format accessed by a processor kernel or a result of instruction decoding performed by the processor kernel.

Abstract: The management and use of replicated distributed transactions is facilitated. A distributed synchronous transaction system protocol is provided to manage the replication of distributed transactions for client application instances. The distributed synchronous transaction system allows transactions to be replicated without having the client application instances be aware of other instances to receive the transaction. Further, if a failure occurs during processing of a distributed replicated transaction, the distributed synchronous transaction system manages the recovery of the failure.