摘要:
A circuit and method for programming and control of an integrated circuit includes a control pin receiving an applied input voltage selected from a set of predetermined programming voltages and an on-chip control voltage decode circuit to select one of multiple programming states for the integrated circuit based on the applied input voltage. In one embodiment, an off-chip voltage divider is used to establish the set of predetermined programming voltages. The on-chip control voltage decode circuit includes a voltage divider to generate comparison voltage levels for detecting the voltage level of the input voltage for selecting the desired programming state. The comparison voltage levels include voltages having voltage values that are midway between pairs of adjacent programming voltages. The voltage decode circuit includes a control circuit receiving comparison results from comparators and generating an output control signal for selecting the desired digital state based on the comparison results.
摘要:
A circuit coupled to an input-output bond pad (I/O pad) in an integrated circuit including an input buffer, an output buffer and a pad management circuit. The pad management circuit receives a first data signal, a first output enable signal, and a configuration signal indicative of the connection state of the I/O pad, and generates a second data signal and a second output enable signal. When the configuration signal indicates the I/O pad is to be connected to a package pin, the pad management circuit couples the first data signal as the second data signal and couples the first output enable signal as the second output enable signal. When the configuration signal indicates the I/O pad is to be left unconnected, the pad management circuit asserts the second output enable signal and generates the second data signal having a predetermined value.
摘要:
A device for performing numerical value conversion of a digital input value in a first unit to a second, natural unit where the digital input value is a digitized value of a first measurement parameter includes a look-up table storing an array of coefficients for performing the numerical value conversion for multiple measurement parameters. The look-up table is indexed using a first parameter indicative of the first measurement parameter to provide a selected coefficient. The device further includes an arithmetic logic unit (ALU) receiving the digital input value and the selected coefficient and performing the numerical value conversion based on a first equation and the selected coefficient to compute a digital output value. The device also includes a saturation-limit circuit coupled to receive the digital output value from the arithmetic logic unit and provide a predetermined output value when the digital output value exceeds a predetermined maximum value.
摘要:
A method and structure are provided that reduce the overall time of the read-erase-modify-write cycle time of non-volatile memories. Specifically, the erase operation of the read-erase-write cycle is avoided in certain circumstances. In one embodiment, the erase operation is skipped where a predetermined pattern is found in at least a portion the block. In another embodiment, the erase operation is skipped where a status of the block indicates that the erase operation can be skipped.
摘要:
A system and method for completing a read transaction between an initiator device and a host memory device in a computer system, in which the present invention optimizes the retry behavior of the initiator device and a target device. The system of the present invention includes a bus bridge device, wherein the bus bridge device includes a target device coupled to the initiator device via a bus; the host memory device coupled to the bus bridge device; and a timer mechanism coupled to the target device. The initiator device is adapted to initiate a present read transaction via the target device, such that an access is asserted between the initiator device and the target device. The timer mechanism is adapted to measure target latency for one or more read transactions preceding the present read transaction, and the timer mechanism is further adapted to use the target latency to calculate a dynamic target latency period. The target device is adapted to maintain the access to the initiator device during the dynamic target latency period. Thus, in accordance with the present invention, the target latency is dynamically measured and used to optimize the retry behavior of the initiator and target devices.
摘要:
A virtual contiguous system for combining multiple and arbitrarily-sized and aligned digital data packets from a PCI bus to a DSP circuit is disclosed. Information from the PCI bus is supplied directly to a plurality of FIFO RAM memory units. Each packet of digital data includes data packet descriptors identifying at least the start address for each data packet and the size of each data packet. The system utilizes this information to operate a read pointer and a write pointer to remove data from the FIFO RAM memory units on a sequential bit-by-bit basis and to supply said data packets to said RAM memory units by means of a write pointer operated by said control circuit. The information transfer is managed on the read side of the FIFO RAM memory units with minimal processing on the write side.
摘要:
An endian domain conversion circuit for converting data packets transmitted between two bus interfaces. The novel system advantageously eliminates any requirement for a large bit switch within the circuit's write data path. Instead, endian conversion intelligence is placed into the read data path. Double words (dwords) are individually received from an incoming data packet and bytes are parallel stored into the same byte location of several different first-in-first-out (FIFO) memories. In one example, the dwords are 32-bits each and the number FIFO memories used is four. An entire input data packet is received in this manner, incrementing the write address of the FIFO memories for each dword. Depending on the type of endian domain conversion required, if at all, endian conversion control circuitry of the present invention controls the manner in which the four exemplary FIFO memories are read (via a read pointer) and the manner which their data is supplied over the output bus to generate the output data. In one embodiment, a byte stream is generated over the output bus. Alternatively, dwords are sent over the output bus in proper endian domain format. Data descriptors located in a data packet header define the endian input domain format, the expected endian output domain format, the data packet size and the start address in system memory of the input data packet. The novel system is well suited to process arbitrarily sized data packets as well as data packets starting at arbitrary byte boundaries.
摘要:
A predictive arbitration system for interfacing a plurality of peripheral component interconnect (PCI) agents coupled to a first PCI bus with a second PCI bus. In one embodiment, the present predictive arbitration system includes a first PCI bus adapted to transmit data signals. A plurality of PCI agents are coupled to the first PCI bus. A predictive arbiter is coupled to both the first PCI bus and a second PCI bus. The predictive arbiter is also coupled to the plurality of PCI agents. The predictive arbiter is configured to receive requests for access to the first or second PCI bus from any of the plurality of PCI agents. The predictive arbiter, upon receiving requests for access, transmits one of the requests to a second arbiter coupled to the second PCI bus, wherein the selected and transmitted request originates from a selected one of the plurality of PCI agents. The predictive arbiter is also adapted to receive a grant signal from the second arbiter in response to the selected and transmitted request. The predictive arbiter further comprises a predictive arbitration system for enabling a grant line coupled to the selected one of the plurality of PCI agents before the grant signal is received from the second arbiter.
摘要:
A reprogrammable state machine which allows the state flow and control outputs to be reprogrammed without requiring modification of the state machine. The reprogrammable state machine uses a reprogrammable logic unit to generate the state transitions and output transitions for each state of the reprogrammable state machine. A memory control unit is used to program the state machine reprogrammable logic unit with default settings for the state transitions and output transitions for each state of the reprogrammable state machine. The memory control unit is also used to reprogram the state machine reprogrammable logic unit with modified settings for the state transitions and output transitions for each state of the reprogrammable state machine which needs to be modified.
摘要:
The present invention is a desktop personal computer (PC) system having peripheral device bus mastering. The system has four main elements: a Direct Memory Access (DMA) controller, a hardware state machine, a bus controller, and a device controller. The device controller may be an IDE hard disk controller which is able to generate long streams of data in an intermittent fashion wherein any single stream of data is targeted to a number of different host memory locations. The device controller may also be an ECP parallel port controller which interfaces with a number of different peripheral devices over a parallel bus wherein each peripheral device appears to the system as a separate and independent data path.