Intel Corporation

Jeffrey L Rabe

Zohar Bogin

Bruce A Young

Stephen Anthony Fischer

Norman J Rasmussen

Dave Carson

Nilesh V Shah

Sathyamurthi Sadhasivan

Serafin E Garcia

David J Harriman

James P Kardach

Jasmin Ajanovic

Daniel Nemiroff

Robert W Strong

Ajay V Bhatt

Aditya Sreenivas

Rajeev K Nalawadi

Amber D Huffman

Nicholas D Wade

James S Coke

Robert N Murdoch

Alberto J Martinez

Geetani R Edirisooriya

David D Lent

John P Lee

Stuart E Sailer

Dahmane Dahmani

Timothy M Dobbins

Satish Acharya

Stephen T Rowland

Jasper Balraj

Dave Smyth

Mitchell W Dale

Jackie Wensel

Ray Chen

A computer system provides a program access to a first register during real mode operation by using an index register and a data register, wherein the index register and the data register are located in real mode memory space and the first register is located outside of real mode memory space.

Index/data register pair for indirect register access

An address translation apparatus and method that can convert a limited-range memory address from a peripheral device to an expanded-range memory address on the fly. The invention can expand the limited address capability of a peripheral bus, such as a PCI bus with a 4 GB address range, to a much larger address capability, such as a 64 GB address range. This conversion can be performed on the fly by hardware, so that no appreciable delay in transfer time is created. The conversion can be performed by adding features to a conventional graphics controller interface, thus minimizing the impact on circuit complexity and system cost.

Remapping I/O device addresses into high memory using GART

An approach to selecting either an actual stepping revision ID value or a compatible revision ID value to be readable by a processor through a revision ID register.

Method and apparatus for identifying hardware compatibility and enabling stable software images

A method and apparatus for delivering APIC interrupts to a processor, and between processors, as FSB transactions. Interrupts and hardware signals, generated by a PCI device, are converted into an upstream memory write interrupt and further converted into an FSB interrupt transaction, received by a processor. Interrupts marked as lowest priority re-directable are redirected based on task priority information. Support for XTPR transactions to update XTPR registers is provided. Preferred ordering of XTPR update transactions and interrupts to be redirected is provided.

Method and apparatus for processing interrupts of a bus

A computer bus that enables bus mastering agents to send/receive a burst of data to/from a slave agent without determining in advance the number of data words to be transferred, or even the maximum number of data words that could be transferred. Either the master, the slave, or the bus arbiter can terminate the burst at any time with minimum overhead. Furthermore, either the master or the slave can throttle the speed of the data transfer by adding wait states. Distributed address decode is performed by each agent coupled to the bus. Each agent must claim a transaction directed toward it by the master. If no agent claims the transaction within a predetermined number of clock periods, a subtractive decode device may claim the transaction by default. The bus also includes a bus lock wherein each bus slave agent may be able to enter a locked state, and once in the locked state, reject all accesses except those initiated by the master agent that locked it. Signal line LOCK# is owned by only one master agent at a time. Although the LOCK# signal must be obtained by acquiring the bus while LOCK# is high, ownership of the line is maintained as long as LOCK# is held low. Therefore, a master agent can own the lock while another master uses the bus.

Locking protocol for peripheral component interconnect utilizing master

A computer system comprises a direct memory access (DMA) transfer unit and a plurality of DMA devices coupled by an external bus. The DMA transfer unit effectuates DMA transfers for the plurality of DMA devices. The DMA transfer unit contains a DMA controller, a bus arbiter, and a bus controller. The DMA controller and the bus controller generate a two-clock cycle DMA transfer. To effectuate a two-clock cycle DMA transfer, a requesting DMA device sets-up a DMA transfer with the DMA controller such that a DACK# signal is asserted during a first clock period. During a second clock period, the DMA controller sets-up the memory address. During a third clock period, the bus controller transitions a command signal on the external bus. Upon assertion of the command signal, valid data is asserted on the external bus. For demand and block mode operations, additional DMA transfers are executed in a two-clock cycle DMA transfer. The DMA controller and the bus controller also generate a three-clock cycle DMA transfer.

Method and apparatus for fast DMA transfer on an industry standard

A method and apparatus for regulating the deferral of a transaction issued on a bus by a processor in a computer system is disclosed. A bus transaction recorder coupled to the bus processes encoded signals from the transaction issued on the bus. A line coupled to the bus sends an indication signal when a pending transaction request is issued on the bus. A CPU latency timer times the current transaction on the bus when a new pending transaction is waiting on the bus. The CPU latency timer outputs an expiration signal when the transaction takes more than a predetermined amount of time to complete. A transaction processor unit is coupled to the bus transaction recorder, the line, and the CPU latency timer. The transaction processor unit defers the transactions issued on the bus when the transaction processor receives the indication signal indicating that a pending transaction is waiting to be issued on the bus, when the encoded signals from the transaction issued on the bus indicate that the transaction issued on the bus is a candidate for deferral, and when the CPU latency timer outputs the expiration signal.

Method and apparatus for dynamically deferring transactions

Signaling protocol for a peripheral component interconnect

Apparatus and a method for eliminating deadlock in a multibus computer system which system includes a primary bus, and a secondary bus, a bridge circuit for joining the primary bus to a bus master, and a second bridge circuit for joining the primary bus to the secondary bus. The invention causes the second bridge circuit to generate a first signal directed to the all bridge circuits to indicate that a bus master on the secondary bus desires access to the secondary bus. All bridge circuits holding data directed to a component on the secondary bus flushes all temporary storage means holding data directed to a component on the secondary bus. The bridge circuits then generate signals to indicate that flushing is complete and the bus master on the secondary bus is granted access to the secondary bus. In one embodiment, the second bridge tests to determine whether the bus master requesting access requires a guaranteed access time and generates a signal to flush temporary storage in the first bridge between memory and the bridge.

Deadlock avoidance mechanism and method for multiple bus topology

A buffer circuit for transferring data between a first slower narrower computer bus and a second wider faster computer bus which buffer circuit includes first and second buffers each capable of storing a plurality of bytes of data equivalent to the width of the second bus, a single address register for holding an address which represents data in either of the two buffers, the lowest order bit of the address register indicating to which one of the two buffers data is being written, first and second registers for storing indications of valid data in the first and second buffers, and a control circuit for controlling the filling of the first and the second buffers in accordance with the byte addresses furnished and the flushing of the first and the second buffers whenever a most significant byte of a buffer has valid data, whenever an attempt is made to write to a buffer address containing valid data, and whenever an attempt is made to load data to a buffer address different than an address in the address register so that sequences of bytes of data are typically accumulated in order in one buffer until an amount of data equal to that which may be transferred on the second wider faster bus is accumulated and then that buffer is flushed to the second wider faster bus while the other buffer is loaded with new data, and so that valid data is not overwritten even though non-sequential addresses are loaded.

Method and apparatus for sequencing buffers for fast transfer of data

A computer system having a responsive low-power mode and a full-power mode of operation. The computer system includes a power consumption controller, a processor and a communication device. The power consumption controller generates an interrupt signal in response to a low power event or a fully operational event. The power consumption controller also generates a clock control signal. The clock control signal is deasserted during the full-power mode of operation and alternatively asserted for a first duration and deasserted for a second duration during the low-power mode of operation. In response to an asserted clock control signal, the processor suppresses the internal clock signal to at least one functional block within the processor and in response to a deasserted clock control signal, the processor transmits the internal clock signal to at least one functional block within the processor. By transmitting the internal clock signal to at least one functional block within the processor during the low-power mode of operation, the processor may respond to communication signals from a communication device during the low-power mode of operation.

Method and apparatus for control of power consumption in a computer

A circuit for controlling interrupt request signal transmission in a computer system. An input receives an interrupt request from an external component. First circuitry coupled to the input generates a signal in response to the interrupt request from the external component. The signal causes a processor to switch to fully operational mode. Second circuitry coupled to the input generates an interrupt request signal to the processor in response to the interrupt request from the external component. A signal processing circuit coupled to the second circuitry suppresses transmission of the interrupt request signal to the processor until the signal is transmitted to the processor.

Method and apparatus for interrupt/SMI# ordering

A programmable arbiter providing for dynamic configuration of prioritization schemes is implemented using a simple, but effective structure. One or more arbiter banks are structured in a cascading manner. Each arbiter bank receives a predetermined number of the set of bus requests to be arbitrated. Each bank is separately programmed to provide a rotating or fixed priority scheme to evaluate the priority of the bus requests. Thus by separately programming the arbiter banks to operate in a fixed priority or rotating priority manner, a flexible, programmable arbiter is created which can operate according to a fixed, rotating or hybrid priority scheme and is adaptable to a variety of applications.

Arbiter and arbitration process for a dynamic and flexible prioritization

Bus arbitration with master unit controlling bus and locking a slave

Growing community of inventors

Gold River, CA, United States of America

Jeffrey L Rabe