Arm Limited

Intel Corporation

Mukesh Patel

Jamshed Jalal

Gurunath Ramagiri

Tushar P Ringe

Mark David Werkheiser

Sakshi Verma

Daniel Cutter

Rajesh Bhikhubhai Patel

Mark Norman Fullerton

Nigel C Paver

James David Dundas

Jose Niell

Stephen J Robinson

Ashok Kumar Tummala

Stephen J Strazdus

Murli Ganeshan

Wing K Yu

William T Maghielse

Jianwei Liu

Rupal Parikh

Devi Sravanthi Yalamarthy

Anthony Jebson

Deli Deng

Ritukar Khanna

Wenxuan Zhang

Iat Pui Chan

Kailesh B Bavaria

Lakshmi Joga Vishnu Vardhan Badukonda

A super home node of a first chip of a multi-chip data processing system manages coherence for both local and remote cache lines accessed by local caching agents and local cache lines accessed by caching agents of one or more second chips. Both local and remote cache lines are stored in a shared cache, and requests are stored in shared point-of-coherency queue. An entry in a snoop filter table of the super home node includes a presence vector that indicates the presence of a remote cache line at specific caching agents of the first chip or the presence of a local cache line at specific caching agents of the first chip and any caching agent of the second chip. All caching agents of the second chip are represented as a single caching agent in the presence vector.

Data processing network with super home node

Entries in a cluster-to-caching agent map table of a data processing network identify one or more caching agents in a caching agent cluster. A snoop filter cache stores coherency information that includes coherency status information and a presence vector, where a bit position in the presence vector is associated with a caching agent cluster in the cluster-to-caching agent map table. In response to a data request, a presence vector in the snoop filter cache is accessed to identify a caching agent cluster and the map table is accessed to identify target caching agents for snoop messages. In order to reduce message traffic, snoop message are sent only to the identified targets.

Configurable cache coherency controller

The present disclosure advantageously provides a method and system for allocating shared resources for an interconnect. A request is received at a home node from a request node over an interconnect, where the request represents a beginning of a transaction with a resource in communication with the home node, and the request has a traffic class defined by a user-configurable mapping based on one or more transaction attributes. The traffic class of the request is determined. A resource capability for the traffic class is determined based on user configurable traffic class-based resource capability data. Whether a home node transaction table has an available entry for the request is determined based on the resource capability for the traffic class.

Interconnect resource allocation

A method and apparatus are provided to enable snoop forwarding to occur together with memory protection. A data processing apparatus in, for instance, the form of a home node forwards a snoop forwarding request on behalf of a requester to a target, the snoop forwarding request being capable of indicating one or more access permissions of the target in relation to the data. A further data processing apparatus in the form of, for instance, a receiver node may receive the snoop forwarding request and based on its own permissions that are provided in the snoop forwarding request, together with the state of the data, either provide a response back to the requester or the home node. In a still further data processing apparatus in the form of, for instance, a Memory Protection Unit (MPU), a regular snoop forwarding request made to a target in relation to data can be forwarded to the target or demoted to a non-forwarding snoop request based on the permissions of the target in relation to the data at the MPU.

Snooping with access permissions

A system, apparatus and method for protecting coherent memory contents in a coherent data processing network by filtering data access requests and snoop response based on the Read/Write (R/W) access permissions. Requests are augmented with access permissions in memory protection units and the access permissions are used to control memory access by home nodes of the network.

System, method and apparatus for accessing shared memory

An apparatus and method are provided for managing snoop operations. The apparatus has an interface for receiving access requests from any of N master devices that have associated cache storage, each access request specifying a memory address within memory associated with the apparatus. Snoop filter storage is provided that has a plurality of snoop filter entries, where each snoop filter entry identifies a memory portion and snoop control information indicative of the master devices that have accessed that memory portion. When an access request received at the interface specifies a memory address that is within the memory portion associated with a snoop filter entry, snoop control circuitry uses the snoop control information in that snoop filter entry to determine which master devices to subject to a snoop operation. The snoop control circuitry maintains master indication data used to identify a first subset of the plurality of master devices whose accesses to the memory are to be precisely tracked within the snoop filter storage. The first subset comprises up to M master devices, where M is less than N. Each snoop filter entry has a precise tracking field and an imprecise tracking field. When multiple master devices have accessed the memory portion associated with a snoop filter entry, then the precise tracking field is used to precisely identify each master device of those multiple master devices that is within the first subset. When the multiple master devices includes at least one master device that is not in the first subset, then a generic indication is set in the imprecise tracking field.

Apparatus and method for managing snoop operations

An apparatus having a fabric interconnect that supports multiple topologies and method for using the same are disclosed. In one embodiment, the apparatus comprises mode memory to store information indicative of one of the plurality of modes; and a first fabric operable in a plurality of modes, where the fabric comprises logic coupled to the mode memory to control processing of read and write requests to memory received by the first fabric according to the mode identified by the information indicative.

Coherent fabric interconnect for use in multiple topologies

A method and apparatus for satisfying load operations by accessing data from a store buffer is described herein. The present invention further relates to satisfying load operations faster than prior art techniques in most cases. Finally, the present invention provides an improved technique for satisfying load operations that does not significantly impact processor performance.

Parallel search technique for store operations

A processor-based system may include a main processor and a coprocessor. The coprocessor handles instructions that include opcodes specifying a data processing operation to be performed by the coprocessor and a coprocessor identification field for identifying a target coprocessor for coprocessor instructions. Two bits indicate one of four data sizes including a byte (8 bits), a half word (16 bits), a word (32 bits), and a double word (64 bits). Two other bits indicate a saturation type.

Conditional execution of coprocessor instruction based on main processor arithmetic flags

Growing community of inventors

Round Rock, TX, United States of America

Mukesh Patel