Compaq Computer Corporation, Inc.

Digital Equipment Corporation

Stephen R VanDoren

Madhumitra Sharma

Simon C Steely, Jr

Denis J Foley

Maurice B Steinman

Kourosh Gharachorloo

David Martin Fenwick

Paul M Goodwin

Craig Durand Keefer

David W Davis

Hari Krishnan Nagpal

The invention pertains to serializing local and remote references to a portion of a shared memory to optimize sequencing of requests in a switch-based, multi-processor system in which the local and remote references can occur concurrently. Usually, local accesses are typically much faster than remote accesses. Thus, in the interest of performance, both local and remote accesses are permitted to occur concurrently in the multiprocessing system. However, in one instance a local access can cause deadlock problems for a remote access. In addition, problems associated with coherency of the shared memory can also arise. Thus, in order to prevent deadlock problems and to maintain coherency of a shared memory, if a local reference to an address of memory has been forwarded to a switch, in this instance a hierarchical switch, then all subsequent references to that address of memory are forwarded to the hierarchical switch. The hierarchical switch has ordering properties that maintain the received order of inputs.

Shadow commands to optimize sequencing of requests in a switch-based multi-processor system

An architecture and coherency protocol for use in a large SMP computer system includes a hierarchical switch structure which allows for a number of multi-processor nodes to be coupled to the switch to operate at an optimum performance. Within each multi-processor node, a simultaneous buffering system is provided that allows all of the processors of the multi-processor node to operate at peak performance. A memory is shared among the nodes, with a portion of the memory resident at each of the multi-processor nodes. Each of the multi-processor nodes includes a number of elements for maintaining memory coherency, including a victim cache, a directory and a transaction tracking table. The victim cache allows for selective updates of victim data destined for memory stored at a remote multi-processing node, thereby improving the overall performance of memory. Memory performance is additionally improved by including, at each memory, a delayed write buffer which is used in conjunction with the directory to identify victims that are to be written to memory. An arb bus coupled to the output of the directory of each node provides a central ordering point for all messages that are transferred through the SMP. The messages comprise a number of transactions, and each transaction is assigned to a number of different virtual channels, depending upon the processing stage of the message. The use of virtual channels thus helps to maintain data coherency by providing a straightforward method for maintaining system order. Using the virtual channels and the directory structure, cache coherency problems that would previously result in deadlock may be avoided.

High-performance non-blocking switch with multiple channel ordering constraints

Low occupancy protocol for managing concurrent transactions with

Order supporting mechanisms for use in a switch-based multi-processor

Method and apparatus for delaying victim writes in a switch-based

Method and apparatus for disambiguating change-to-dirty commands in a

Multi-processor computer system having a data switch with simultaneous

Employing multiple channels for deadlock avoidance in a cache coherency

A command queueing apparatus for directing address and command information amongst the various interfaces, or consumers, on a multi-CPU node in a computer system. The apparatus includes a core queue containing core queue entries, each core queue entry corresponding to a pending system bus operation. Each core queue entry includes one or more consumer information fields specific to each consumer. Also included is a plurality of virtual queues, each virtual queue corresponding to a consumer, each virtual queue having a virtual queue entry. A virtual queue entry for a consumer is a subset of the fields of a core queue entry, the subset of fields including the consumer information fields for the consumer corresponding to the virtual queue.

Turbotable: apparatus for directing address and commands between

A method and apparatus in a computer system for updating Duplicate Tag cache status information. The invention operates in a computer system having one or more processor modules coupled to a system bus operating in accordance with a SNOOPING bus protocol. Processor commands and addresses for modification of an entry of the processor's Duplicate Tag status information is provided by the processor to its address interface to the system bus. System bus command and address information is received and stored in a interface pipeline of the address interface. A determination is made as to whether the system bus commands and addresses in the interface pipeline are valid. If there are no valid system bus commands and addresses in the interface pipeline, the Duplicate Tag status information is updated without determining if the processor commands and addresses conflict with the system bus commands and addresses.

Method and apparatus for updating a duplicate tag status in a snoop bus

Growing community of inventors

Northborough, MA, United States of America

Stephen R VanDoren