Abstract: A Central Processing Unit (CPU) hotpatch circuit compares the run-time instruction stream against an internal cache. The internal cache stores embedded memory addresses with associated control flags, executable instruction codes, and tag information. In the event that a comparison against the current program counter succeeds, then execution is altered as required per the control flags. If no comparison match is made, then execution of the instruction that was accessed by the program counter is executed.

Abstract: A method and system for routing network-based data arranged in frames is disclosed. A host processor analyzes transferred bursts of data and initiates an address and look up algorithm for dispatching the frame to a desired destination. A shared system memory existing between a network device, e.g., an HDLC controller, working in conjunction with the host processor, receives data, including any preselected address fields. The network device includes a plurality of ports. Each port includes a FIFO receive memory for receiving at least a first portion of a frame. The first portion of the frame includes data having the preselected address fields. A direct memory access unit transfers a burst of data from the FIFO receive memory to the shared system memory. A communications processor selects the amount of data to be transferred from the FIFO receive memory based on the desired address fields to be analyzed by the host processor.

Abstract: A method, apparatus and network device for controlling the flow of network data arranged in frames and minimizing congestion is disclosed. A status error indicator is generated within a receive FIFO memory indicative of a frame overflow within the receive FIFO memory. In response to the status error indicator, an early congestion interrupt is generated to a host processor indicative that a frame overflow has occurred within the receive FIFO memory. The incoming frame is discarded and the services of received frames are enhanced by one of either increasing the number of words of a direct memory access (DMA) unit burst size, or modifying the time-slice of other active processes.

Abstract: A method and system for routing network-based data arranged in frames is disclosed. A host processor analyzes transferred bursts of data and initiates an address and look up algorithm for dispatching the frame to a desired destination. A shared system memory existing between a network device, e.g., an HDLC controller, working in conjunction with the host processor, receives data, including any preselected address fields. The network device includes a plurality of ports. Each port includes a FIFO receive memory for receiving at least a first portion of a frame. The first portion of the frame includes data having the preselected address fields. A direct memory access unit transfers a burst of data from the FIFO receive memory to the shared system memory. A communications processor selects the amount of data to be transferred from the FIFO receive memory based on the desired address fields to be analyzed by the host processor.

Abstract: A system and method for reducing transfer latencies in fencepost buffering requires that a cache is provided between a host and a network controller having shared memory. The cache is divided into a dual cache having a top cache and a bottom cache. A first and second descriptor address location are fetched from shared memory. The two descriptors are discriminated from one another in that the first descriptor address location is a location of an active descriptor and the second descriptor address location is a location of a reserve/lookahead descriptor. The active descriptor is copied to the top cache. A command is issued to DMA for transfer of the active descriptor. The second descriptor address location is then copied into the first descriptor address. The next descriptor address location from external memory is then fetched and placed in the second descriptor address location.

Abstract: A method, apparatus and network device for controlling the flow of network data arranged in frames and minimizing congestion, such as in the receive port of an HDLC controller is disclosed. A status error indicator is generated within a receive FIFO memory indicative of a frame overflow within the receive FIFO memory. In response to the status error indicator, an early congestion interrupt is generated to a host processor indicative that a frame overflow has occurred within the receive FIFO memory. The incoming frame is discarded and the services of received frames are enhanced by one of either increasing the number of words of a direct memory access (DMA) unit burst size, or modifying the time-slice of other active processes.

Abstract: A Central Processing Unit (CPU) hotpatch circuit compares the run-time instruction stream against an internal cache. The internal cache stores embedded memory addresses with associated control flags, executable instruction codes, and tag information. In the event that a comparison against the current program counter succeeds, then execution is altered as required per the control flags. If no comparison match is made, then execution of the instruction that was accessed by the program counter is executed.

Abstract: A system and method for reducing transfer latencies in fencepost buffering requires that a cache is provided between a host and a network controller having shared memory. The cache is divided into a dual cache having a top cache and a bottom cache. A first and second descriptor address location are fetched from shared memory. The two descriptors are discriminated from one another in that the first descriptor address location is a location of an active descriptor and the second descriptor address location is a location of a reserve/lookahead descriptor. The active descriptor is copied to the top cache. A command is issued to DMA for transfer of the active descriptor. The second descriptor address location is then copied into the first descriptor address. The next descriptor address location from external memory is then fetched and placed in the second descriptor address location.

Abstract: A method, apparatus and network device for controlling the flow of network data arranged in frames and minimizing congestion, such as in the receive port of an HDLC controller is disclosed. A status error indicator is generated within a receive FIFO memory indicative of a frame overflow within the receive FIFO memory. In response to the status error indicator, an early congestion interrupt is generated to a host processor indicative that a frame overflow has occurred within the receive FIFO memory. The incoming frame is discarded and the services of received frames are enhanced by one of either increasing the number of words of a direct memory access (DMA) unit burst size, or modifying the time-slice of other active processes.

Abstract: A method and network device are disclosed using a look-ahead watermark in a FIFO memory. In accordance with the present invention, a watermark interrupt is generated from a FIFO memory when data in the FIFO memory has crossed a watermark threshold. A data burst is transferred through a direct memory access unit to the FIFO memory. A look-ahead watermark flag is checked at the FIFO memory to determine if sufficient memory space exists inside the FIFO memory for an additional data burst, which is transferred through the direct memory access unit to the FIFO memory when the look-ahead watermark flag indicates that sufficient memory space is available.

Abstract: A Central Processing Unit (CPU) hotpatch circuit compares the run-time instruction stream against an internal cache. The internal cache stores embedded memory addresses with associated control flags, executable instruction codes, and tag information. In the event that a comparison against the current program counter succeeds, then execution is altered as required per the control flags. If no comparison match is made, then execution of the instruction that was accessed by the program counter is executed.

Abstract: A system and method for reducing transfer latencies in fencepost buffering requires that a cache is provided between a host and a network controller having shared memory. The cache is divided into a dual cache having a top cache and a bottom cache. A first and second descriptor address location are fetched from shared memory. The two descriptors are discriminated from one another in that the first descriptor address location is a location of an active descriptor and the second descriptor address location is a location of a reserve/lookahead descriptor. The active descriptor is copied to the top cache. A command is issued to DMA for transfer of the active descriptor. The second descriptor address location is then copied into the first descriptor address. The next descriptor address location from external memory is then fetched and placed in the second descriptor address location.

Abstract: A method and device of creating one or more buffer structures in a shared memory that exists between a host and a network device is disclosed. The method includes the step of storing within a block of shared memory an administration block having a base address and a descriptor ring parameter, which includes information relating to a descriptor ring and frame data buffer sizes. The base address of the administration block is written into the network device. An initialization command is then issued from the host to the network device. The network device reads the administration block and shared memory and one or more descriptors are constructed within the network device. Each descriptor points to a frame data buffer within shared memory. The descriptors are then stored.

Abstract: A method and network device are disclosed using a look-ahead watermark in a FIFO memory. In accordance with the present invention, a watermark interrupt is generated from a FIFO memory when data in the FIFO memory has crossed a watermark threshold. A data burst is transferred through a direct memory access unit to the FIFO memory. A look-ahead watermark flag is checked at the FIFO memory to determine if sufficient memory space exists inside the FIFO memory for an additional data burst, which is transferred through the direct memory access unit to the FIFO memory when the look-ahead watermark flag indicates that sufficient memory space is available.

Abstract: A method and network device are disclosed using a look-ahead watermark in a FIFO memory. In accordance with the present invention, a watermark interrupt is generated from a FIFO memory when data in the FIFO memory has crossed a watermark threshold. A data burst is transferred through a direct memory access unit to the FIFO memory. A look-ahead watermark flag is checked at the FIFO memory to determine if sufficient memory space exists inside the FIFO memory for an additional data burst, which is transferred through the direct memory access unit to the FIFO memory when the look-ahead watermark flag indicates that sufficient memory space is available.

Abstract: A method and device of creating one or more buffer structures in a shared memory that exists between a host and a network device is disclosed. The method includes the step of storing within a block of shared memory an administration block having a base address and a descriptor ring parameter, which includes information relating to a descriptor ring and frame data buffer sizes. The base address of the administration block is written into the network device. An initialization command is then issued from the host to the network device. The network device reads the administration block and shared memory and one or more descriptors are constructed within the network device. Each descriptor points to a frame data buffer within shared memory. The descriptors are then stored.

Abstract: A method and system of controlling the transfer of data arranged in frames between a host and network device, such as an HDLC controller, having a shared system memory is disclosed. A frame is received within frame data buffers of the shared system memory. A single frame can span more than three frame data buffers. A descriptor ring has respective descriptors that describe and point to a respective frame data buffer and ownership by either the host or device. The descriptors for an associated frame data buffer that received a frame are placed together to form a descriptor chain having first and last descriptors. Only the first and last descriptors are updated within the descriptor chain to grant ownership of first and last descriptors and any intermediate descriptors to a desired host or device to enhance bus utilization.

Abstract: A method and apparatus for controlling data flow of data communications in a network are provided. A method preferably includes dynamically varying a minimum frame slot number, transmitting at least bytes of data from a frame of data of a slot, and determining the end of the frame of data. The method also preferably includes determining that the number of bytes of data within the frame is less than the current minimum frame slot number and transmitting flag bytes within the slot until the combination of the number of bytes and flag bytes equals the current minimum frame slot number. An apparatus preferably includes a transmitter for transmitting at least bytes of frames of data of a data slot, a byte counter responsive to the transmitter for counting the number of bytes in a frame of transmitted data, and a flag counter responsive to the transmitter for counting the number of flag bytes transmitted within a frame of transmitted data.

Abstract: A Central Processing Unit (CPU) hotpatch circuit compares the run-time instruction stream against an internal cache. The internal cache stores embedded memory addresses with associated control flags, executable instruction codes, and tag information. In the event that a comparison against the current program counter succeeds, then execution is altered as required per the control flags. If no comparison match is made, then execution of the instruction that was accessed by the program counter is executed.