Abstract: A bridge logic unit provides an interface between a microprocessor coupled to a processor bus, a main memory coupled to memory bus, and a peripheral device coupled to a peripheral bus, such as a PCI bus. To maintain coherency, the bridge logic unit disables write posting in certain specific situations, and flushes posted write transactions before allowing certain read requests to be serviced. More specifically, in one embodiment when a PCI device performs a read to main memory, which may be implemented within the bridge as delayed read, the bus bridge blocks CPU to PCI transactions and flushes any posted CPU to PCI transactions pending in the bridge. The bus bridge enables CPU to PCI posting after the pending CPU to PCI transactions have been flushed and after the snoop phase of a snoop cycle corresponding to the memory read operation completes.

Abstract: A computer is provided having a bus interface unit coupled between a CPU bus and a mezzanine bus, or PCI bus. The bus interface unit includes a plurality of input buffers which can be selectively connected and disconnected in a dynamic fashion according to active and inactive signals forwarded thereto. Signals forwarded to the bus interface unit from the CPU are classified according to the transaction phase of CPU bus activity. If signals associated with one particular transaction phase are active, then input buffers attributed to signals of other transaction phases can be deactivated. It is preferred that input buffers associated with signals of a request and arbitration phase be maintained active and coupled to power regardless of the present transaction phase unless the computer enters a powered down mode, such as sleep, idle or standby.

Abstract: A computer having a bus interface unit coupled between a CPU bus and a PCI bus and/or a bus interface unit coupled between a PCI bus and memory and or I/O space. The clocking to the configuration space of the bus interface unit can be inhibited to conserve power in two ways. The first approach relies on an input/output address space containing a configuration address register. An enable bit or flag within the configuration address register can be set to allow a determination of the various PCI devices and to configure those devices linked to the PCI bus. Subsequent to computer boot up or initialization, the enable bit can be disabled to disallow further accesses to the configuration address space of the PCI device or PCI compliant bus interface unit. Disabling the enable bit further inhibits or disconnects a clocking signal from sequential logic within the configuration address space to minimize power consumption of the north bridge during its normal operation.

Abstract: A computer system includes a secondary bus bridge device in a portable computer and a another secondary bus bridge device in an expansion base to which the portable computer connects (docks). A peripheral in the expansion base may initiate a delayed cycle to read or write data to memory through a primary bus bridge device that also couples to a CPU. Both secondary bus bridge devices include an arbiter for controlling arbitration of a peripheral bus that connects both secondary bridge devices. The arbiter in the secondary bridge of the portable computer determines which of the arbiters will have arbitration control of the expansion bus to run cycles. When read data is available, in the case of a delayed read cycle initiated by a peripheral device in the expansion base, the primary bridge strobes a delayed cycle control signal to the arbiter in the portable computer which then gives arbitration control to the arbiter in the expansion base.

Abstract: A computer system includes a bus bridge which provides an interface between a main memory and a peripheral bus such as a PCI bus. A peripheral bus interface unit is provided which supports delayed transactions. When a PCI bus master effectuates a read cycle to read data from main memory on the PCI bus, the peripheral bus interface detects the read cycle and terminates or retries the transaction on the PCI bus. The peripheral bus interface further requests the read data from main memory and places the read data in a buffer. When the PCI master device re-attempts the read transaction, the peripheral interface provides the read data directly from its delayed read buffer. When the peripheral bus interface retries the PCI master that establishes a delayed read operation, the peripheral bus interface asserts a control signal referred to the delayed cycle signal.

Abstract: A computer is provided having a bus interface unit which is coupled between a peripheral bus and a dedicated graphics bus. The graphics bus can be linked to the bus interface unit by an AGP, while the peripheral bus can be linked to the bus interface unit by a PCI. Arbitration for the AGP bus can determine when mastership is granted to an AGP master (i.e., graphics accelerator/controller). Until mastership is granted, the AGP target is powered down to a low power state where power consumption within the bus interface unit is minimal. It is not until the AGP master achieves mastership that the graphics target (core logic and memory controller) within the bus interface unit is placed in an operational (fully powered) state. The computer therefore employs a bus interface unit which can be dynamically switched from a high power state to a low power state and vice versa, depending upon accesses to the graphics target.

Abstract: A computer system includes a CPU and a memory device coupled through a North bridge logic device. The computer also includes a South bridge logic device coupled to the North bridge by a primary bus. The South bridge waits as long as possible before asserting a flush request (FLUSHREQ) control signal to the North bridge. The South bridge asserts the FLUSHREQ signal to the North bridge after a peripheral device coupled to the South bridge requests access to the primary bus to run a cycle. The South bridge first flushes a write queue before asserting the FLUSHREQ signal to the North bridge. In response to the FLUSHREQ control signal, the North bridge flushes one or more of its own internal write queues in preparation for the upcoming peripheral device cycle.

Abstract: A PCI bridge is configured to perform delayed read operations in response to a memory read initiated on the PCI bus. Normally, the PCI bridge is configured to discard delayed read data read from main memory following a predetermined discard count time after the PCI master establishing the delayed read operation is retried on the PCI bus. The computer system further includes a secondary bus bridge such as an ISA bridge for providing an interface between the PCI bus and an ISA bus. When an ISA device desires to read data from the main memory, the ISA bridge asserts a flush request signal. The PCI bridge responsively flushes any pending CPU to PCI transactions pending within the PCI bridge. When the flushing operation is complete, the PCI bridge asserts an acknowledge signal. A PCI arbiter for arbitrating ownership of the PCI bus may increase a level of arbitration priority provided to the ISA bridge in response to assertion of the acknowledge signal.

Abstract: Arbitration circuitry in a computer system having a plurality of arbiters for arbitrating requests from bus masters on a PCI bus and an EISA bus. Each of the PCI and EISA buses have a plurality of masters. The PCI bus utilizes a modified LRU arbitration scheme, while the EISA bus utilizes a rotating priority scheme. The arbiter on the EISA bus includes a first level of arbitration and a second level of arbitration. The first level is assigned a plurality of requester types to determine the priority between the requestor types. Certain of the first level requestor types include a plurality of devices. If one of those certain requestor types wins priority on the first level arbitration cycle, a second level arbitration is performed to determine the priority between the plurality of devices.

Abstract: A PCI repeater coupled between a primary bus and a secondary bus includes logic to allow downstream and upstream bursting across the repeater. The PCI repeater echoes transactions in either an upstream or downstream direction, and does not need any additional address decode logic. The buses are coupled to an arbiter so that only one bus master has control of the bus. During a burst operation, the PCI repeater causes the arbiter to cease providing grant signals to prospective bus grantees. The signal is removed only after the transaction has completed on both sides of the PCI repeater to ensure that the PCI repeater is ready for a next transaction.

Abstract: To assure that memory and/or I/O cycles will run correctly after a PCI device configuration cycle that changes memory and/or I/O mapping, in a multi-processor P6 computer system that pipelines instructions. The memory and I/O cycles are suspended on the processor bus until the configuration cycle has been completed. A signal is generated within the address decode logic to prevent address decoding from taking place if a PCI device is being configured. During the configuration transactions, other pipelined transaction cycles are snoop stalled until the PCI configuration write has been completed.

Abstract: An arbiter which allows retried requests to have high priority in subsequent arbitrations by not changing priority on a granted, but aborted, access to the bus and yet prevents the aborted requestor from thrashing the bus by masking its bus request signal until the data is available. Further, should an access to main memory be retried, all bus requests except the one from the memory system are masked to provide the memory system the highest effective priority to allow any flushing operations to occur. The masking of the various bus requests allows the arbiter to control access to a PCI standard bus without requiring that specific signals be added. The arbiter further includes modified priority LRU techniques and provides a locking requestor with an additional, highest priority position if retried.

Abstract: An improved arbitration scheme including multiple arbiters for arbitrating access to a PCI bus and an ISA bus. The PCI arbiter controls access to the PCI bus by various bus masters, including the CPU/main memory subsystem, various other PCI bus masters, an enhanced DMA or EDMA controller, and an 8237-compatible DMA controller. The PCI arbiter utilizes a modified LRU arbitration scheme. Further, an SD arbiter exists to arbitrate access to the data portion (SD) of the ISA bus. The various devices that may request the SD bus include the EDMA controller, a PCI master in a PCI-to-ISA operation, the DMA controller, an ISA bus master, and the refresh controller. The SD arbiter assigns the highest priority to the PCI bus, followed by the refresh controller, EDMA controller, and DMA controller or ISA bus masters. The DMA controller includes an arbiter for arbitrating between its channels.

Abstract: An improved arbitration scheme including multiple arbiters for arbitrating access to a PCI bus and an ISA bus. The PCI arbiter controls access to the PCI bus by various bus masters, including the CPU/main memory subsystem, various other PCI bus masters, an enhanced DMA or EDMA controller, and an 8237-compatible DMA controller. The PCI arbiter utilizes a modified LRU arbitration scheme. Further, an SD arbiter exists to arbitrate access to the data portion (SD) of the ISA bus. The various devices that may request the SD bus include the EDMA controller, a PCI master in a PCI-to-ISA operation, the DMA controller, an ISA bus master, and the refresh controller. The SD arbiter assigns the highest priority to the PCI bus, followed by the refresh controller, EDMA controller, and DMA controller or ISA bus masters. The DMA controller includes an arbiter for arbitrating between its channels.

Abstract: Three prioritization schemes for determining which of several CPUs receives priority to become bus master of a host bus in a multiprocessor system, and an arbitration scheme for transferring control from one bus master to another. Each prioritization scheme prioritizes n elements, where a total of (n/2).times.(n-1) priority bits monitors the relative priority between each pair of elements. An element receives the highest priority when each of the n-1 priority bits associated with that element points to it. In the arbitration scheme, the current bus master of the host bus determines when transfer of control of the host bus occurs as governed by one of the prioritization schemes. The arbitration scheme gives EISA bus masters, RAM refresh and DMA greater priority than CPUs acting as bus masters, and allows a temporary bus master to interrupt the current bus master to perform a write-back cache intervention cycle.

Abstract: Three prioritization schemes for determining which of several CPUs receives priority to become bus master of a host bus in a multiprocessor system, and an arbitration scheme for transferring control from one bus master to another. Each prioritization scheme prioritizes n elements, where a total of (n/2).times.(n-1) priority bits monitors the relative priority between each pair of elements. An element receives the highest priority when each of the n-1 priority bits associated with that element points to it. In the arbitration scheme, the current bus master of the host bus determines when transfer of control of the host bus occurs as governed by one of the prioritization schemes. The arbitration scheme gives EISA bus masters, RAM refresh and DMA greater priority than CPUs acting as bus masters, and allows a temporary bus master to interrupt the current bus master to perform a write-back cache intervention cycle.

Abstract: An arbiter which allows retried requests to have high priority in subsequent arbitrations by not changing priority on a granted, but aborted, access to the bus and yet prevents the aborted requestor from thrashing the bus by masking its bus request signal until the data is available. Further, should an access to main memory be retried, all bus requests except the one from the memory system are masked to provide the memory system the highest effective priority to allow any flushing operations to occur. The masking of the various bus requests allows the arbiter to control access to a PCI standard bus without requiring that specific signals be added. The arbiter further includes modified priority LRU techniques and provides a locking requestor with an additional, highest priority position if retried.

Abstract: A computer system is provided which is compatible with existing programmable option select systems and which provides optional enhanced system setup capabilities. The enhanced system permits use of application software designed specifically for existing programmable option select systems which utilize limited system configuration data registers but further provides an optional mode accessed during system setup procedures wherein application software can access and utilize an expanded set of system setup configuration registers to enhance the performance of the computer system.