Intel Corporation

Matthew A Fisch

Michael W Rhodehamel

Nitin V Sarangdhar

Derek T Bachand

Chakrapani Pathikonda

Amit A Merchant

James M Brayton

Paul D Breuder

David Lawrence Hill

Javed Sabir Barkatullah

Chinna B Prudvi

James E Jacobson, Jr

Peter D MacWilliams

Konrad K Lai

Gurbir Singh

Wen-Hann Wang

Robert J Greiner

Stephen S Pawlowski

Mandar S Joshi

Ajay Malhotra

Wen Han Wang

In a method of processing a bus transaction, an address is retrieved from the bus transaction and referred to a queue of pending transaction. A match indicator signal is returned from the queue. If the match indicator signal indicates a match, a snoop probe for the bus transaction is blocked.

Snoop blocking for cache coherency

A 2/N mode clock generator that generates bus clock signals through the use of bus clock enable signals selecting bus clock pulses that are in phase and out of phase with a core clock signal. The clock generator maintains synchronization between the bus clock signal and the core clock signal so that they are always in a predetermined phase relationship.

Core clock correction in a 2/n mode clocking scheme

A prefetching control system provided for a processor. The prefetching queue may include an arbiter, a cache queue and a prefetch queue. The arbiter issues requests including read requests. Responsive to a read request, the cache queue issues a control signal. The prefetch queue receives the control signal and an address associated with the read request. When the received address is a member of a pattern of read requests from sequential memory locations, the prefetch queue issues a prefetch request to the arbiter.

Prefetch queue responsive to read request sequences

A 2/N mode dock generator that generates bus clock signals through the use of bus clock enable signals selecting bus clock pulses that are in phase and out of phase with a core clock signal. The clock generator maintains synchronization between the bus clock signal and the core clock signal so that they are always in a predetermined phase relationship.

Core clock correction in a 2/N mode clocking scheme

A data control method in a microprocessor is disclosed. According to the method, a request is generated on an external bus for data to be read to the processor. The requested data is read from the external bus to an intermediate memory in the processor and, thereafter, read from the intermediate memory to a destination. When the intermediate memory is full, the read of data from the external bus is stalled until the intermediate memory is no longer full. Typically, stalling is accomplished by generating a stall signal on the external bus, which may be generated during a cache coherency phase of the transaction to which the requested data relates.

Read line buffer and signaling protocol for processor

Apparatus for generating bus clock signals with a 1/N characteristic in

A livelock preventative measure is provided for agents in a multi-processor computing system. Livelock may occur when multiple agents each trade ownership of data in an attempt to modify it. When livelock occurs, a first agent posts a bus transaction for a data and, if a second agent posts a bus transaction for the same data, the first agent may stall the bus transaction of the second agent until the first agent has completed its operation on the data.

Transaction stall technique to prevent livelock in multiple-processor

Each of a plurality of device or agents connected to a computer system bus is provided with a mechanism for unilaterally and dynamically limiting the depth of a pipeline of the bus. Each agent includes a state machine which indicates whether the bus is in a throttled state, a stalled state or a free state. When in a free state, an agent having control of the bus may transmit any number of bus transactions and the depth of the pipeline may therefore increase. In the throttled state, the agent may transmit only a single bus transaction from the throttled state, the state machine always transitions either to the stalled state or to the free state. In the stalled state, no agents may transmit transactions onto the bus and the depth of the pipeline therefore cannot increase and instead may decrease with time as previously issued transactions are drained from the bus. Wired-OR logic is employed for allowing an agent to transmit a state transition signal to all other agents on the bus changing the state of the various state machines only a single state transition signal is required to completely control the state of the state machines. By employing wired-OR logic, any particular agent is capable of switching the state machines into a stalled state to prevent new bus transactions from being issued to the bus. In this manner, each agent is capable of unilaterally restricting or limiting the depth of the pipeline. Hardware or software is provided within each agent to control the state machine in a manner such that all state machines remain synchronized with each indicating the same state at substantially the same time.

Bus agent providing dynamic pipeline depth control

In a computer system, an apparatus for handling lock conditions wherein a first instruction executed by a first processor processes data that is common to a second processor while the second processor is locked from simultaneously executing a second instruction that also processes this same data. A lock bit is set when the first processor begins execution of the first instruction. Thereupon, the second processor is prevented from executing its instruction until the first processor has completed its processing of the shared data. Hence, the second processor queues its request in a buffer. The lock bit is cleared after the first processor has completed execution of its instruction. The first processor then checks the buffer for any outstanding requests. In response to the second processor's queued request, the first processor transmits a signal to the second processor indicating that the data is now not locked.

Apparatus and method for caching lock conditions in a multi-processor

Each of a plurality of device or agents connected to a computer system bus is provided with a mechanism for unilaterally and dynamically limiting the depth of a pipeline of the bus. Each agent includes a state machine which indicates whether the bus is in a throttled state, a stalled state or a free state. When in a free state, an agent having control of the bus may transmit any number of bus transactions and the depth of the pipeline may therefore increase. In the throttled state, the agent may transmit only a single bus transaction from the throttled state, the state machine always transitions either to the stalled state or to the free state. In the stalled state, no agents may transmit transactions onto the bus and the depth of the pipeline therefore cannot increase and instead may decrease with time as previously issued transactions are drained from the bus. Wired-OR logic is employed for allowing an agent to transmit a state transition signal to all other agents on the bus changing the state of the various state machines. Only a single state transition signal is required to completely control the state of the state machines. By employing wired-OR logic, any particular agent is capable of switching the state machines into a stalled state to prevent new bus transactions from being issued to the bus. In this manner, each agent is capable of unilaterally restricting or limiting the depth of the pipeline. Hardware or software is provided within each agent to control the state machine in a manner such that all state machines remain synchronized with each indicating the same state at substantially the same time.

Bus system providing dynamic control of pipeline depth for a multi-agent

Requests to memory issued by an agent on a bus are satisfied while maintaining cache consistency. The requesting agent may issue a request to another agent, or the memory unit, by placing the request on the bus. Each agent on the bus snoops the bus to determine whether the issued request can be satisfied by accessing its cache. An agent which can satisfy the request using its cache, i.e., the snooping agent, issues a signal to the requesting agent indicating so. The snooping agent places the cache line which corresponds to the request onto the bus, which is retrieved by the requesting agent. In the event of a read request, the memory unit also retrieves the cache line data from the bus and stores the cache line in main memory. In the event of a write request, the requesting agent transfers write data over the bus along with the request. This write data is retrieved by both the memory unit, which temporarily stores the data, and the snooping agent. Subsequently, the snooping agent transfers the entire cache line over the bus. The memory unit retrieves this cache line, merges it with the write data previously stored, and writes the merged cache line to memory.

Method and apparatus for supporting read, write, and invalidation

An initialization mechanism for symmetric arbitration agents ensures that multiple agents on a bus are each initialized with a different arbitration counter value. The arbitration counter of each bus agent is used to keep track of which agent was the last or current owner of the bus and which agent will be the next owner of the bus. All bus agents agree on which agent will be the priority agent at system reset and thus be allowed first ownership of the bus. Each agent's arbitration counter is initialized according to each agent's own agent identification. The arbitration pins of the bus agents are interconnected such that each agent determines for itself a unique agent identification based on which pin of its arbitration pins is active at system reset and the maximum number of bus agents allowed on the bus. After determining its agent identification, each bus agent initializes its arbitration counter such that every agent agrees which agent is the priority agent. Each agent performs this initialization based on its agent identification, the identity of the priority agent, and the maximum number of agents allowed on the bus.

Initialization mechanism for symmetric arbitration agents

A computer system providing a universal architecture includes a processor card connected to a system bus of a host computer system. The processor card is adapted for insertion into a slot of the computer system and houses a processor and a bus bridge conversion device. The processor operates according to a signaling protocol which is different than the signaling protocol of the computer system bus. The bus conversion device converts the signaling protocol of the system bus to the signaling protocol of the processor, and vice-versa. The bus conversion device includes logic for bus arbitration conversion, bus lock conversion, and cache coherency control. Logic is also included that converts incoming and outgoing requests so that the card may properly transact with other agents coupled to the bus.

Growing community of inventors

Beaverton, OR, United States of America

Matthew A Fisch