Arm Limited

Antony John Harris

Bruce James Mathewson

Christopher William Laycock

Richard Roy Grisenthwaite

Alistair Crone Bruce

Jamshed Jalal

Stuart David Biles

Andrew Christopher Rose

Ian Rudolf Bratt

Tushar P Ringe

Sean James Salisbury

Anitha Kona

Arthur Brian Laughton

Ian Victor Devereux

Ashok Kumar Tummala

Peter Guy Middleton

Daniel Adam Sara

Håkan Lars-Göran Persson

David John Gwilt

Dipesh Ishwerbhai Patel

Christopher Edwin Wrigley

Simon Crossley

Jeffrey Carl Defilippi

The present disclosure advantageously provides a system cache and a method for storing coherent data and non-coherent data in a system cache. A transaction is received from a source in a system, the transaction including at least a memory address, the source having a location in a coherent domain or a non-coherent domain of the system, the coherent domain including shareable data and the non-coherent domain including non-shareable data. Whether the memory address is stored in a cache line is determined, and, when the memory address is not determined to be stored in a cache line, a cache line is allocated to the transaction including setting a state bit of the allocated cache line based on the source location to indicate whether shareable or non-shareable data is stored in the allocated cache line, and the transaction is processed.

Cache for storing coherent and non-coherent data

An apparatus and method are provided for handling protocol conversion. The apparatus has interconnect circuitry for routing messages between components coupled to the interconnect circuitry in a manner that conforms to a first communication protocol. Protocol conversion circuitry is coupled between the interconnect circuitry and an external communication path, for converting messages between the first communication protocol and a second communication protocol that has a layered architecture comprising multiple layers. The protocol conversion circuitry has a gateway component forming one of the components coupled to the interconnect circuitry, and a controller coupled with the gateway component and used to control connection with the external communication path. For a selected layer of the multiple layers, the protocol conversion circuitry provides, within the gateway component, upper selected layer circuitry to implement a first portion of functionality of the selected layer, where the first portion comprises at least protocol dependent functionality of the selected layer. It also provides, within the controller, lower selected layer circuitry to implement a remaining portion of the functionality of the selected layer, the remaining portion comprising only protocol independent functionality of the selected layer.

Technique for handling protocol conversion

Interconnect circuitry and a method of operating the interconnect circuitry are provided, where the interconnect circuitry is suitable to couple at least two master devices to a memory, each comprising a local cache. Any access to the memory mediated by the interconnect circuitry is policed by a memory protection controller situated between the interconnect circuitry and the memory. The interconnect circuitry modifies a coherency type associated with a memory transaction received from one of the master devices to a type which ensures that when a modified version of a copy of a transaction target specified by the issuing master device is stored in a local cache of another master device an access to the transaction target in the memory must take place and therefore must be policed by the memory protection controller.

Enforcing data protection in an interconnect

A memory interface apparatusis provided with first interface circuitry, second interface circuitryand transaction control circuitry. The first interface circuitry receives a first write request from a transaction masterand issues a further transaction request associated with the memory address of the first write request via the second interface circuitry to a memory system. When an indication of the completion of the further transaction has been received at the second interface circuitry, then a second write request may be issued from the second interface circuitry to the memory system to write the target data associated with the first write request. After a write response signal in respect of the second write request is received at the second interface circuitry, then an acknowledge signal RACK indicating completion of the further transaction and that the write response signal has been received may be issued from the second interface circuitry. Between issue of the further transaction and issue of the acknowledge signal snoop requests to the memory addresses concerned that arise elsewhere within the memory system may be managed and blocked.

Memory interface control

Interconnect circuitry configured to provide routes for interconnecting several initiator devices and at least one recipient device including a memory. At least one of the initiator devices has a cache for storing a local copy of a subset of data items stored in the memory. The interconnect circuitry includes: a plurality of input ports and at least one output port; a plurality of paths for transmitting the transaction requests between the inputs and the at least one output; coherency control circuitry for maintaining an order in which at least some of the transaction requests to a same data storage location proceed through the interconnect circuitry. The interconnect circuitry is configured not to control the writeback transaction requests with the coherency control circuitry, such that the writeback transaction requests proceed independently of transaction requests routed through the coherency control circuitry.

Coherency control with writeback ordering

An apparatus and method are provided for performing verification tests for a design of a data processing system. The apparatus comprises a system under verification representing at least part of the design of the data processing system, and a transactor for connecting to an interface of the system under verification, and for generating signals for input to the system under verification via the interface during performance of the verification tests. Profile storage stores a profile providing a statistical representation of desired traffic flow at the interface, the statistical representation providing statistical information for a plurality of traffic attributes and also identifying at least one dependency between such traffic attributes. The transactor then references the profile in order to determine the signals to be generated, such that the signals generated take account of the specified dependencies identified in the profile. Such a mechanism enables the transactor to more realistically replicate the traffic flow that will be observed in the real system. Another aspect to the present invention provides a mechanism for generating such profiles.

Use of statistical representations of traffic flow in a data processing system

A data processing apparatus for forming a portion of a coherent cache system comprises at least one master device for performing data processing operations, and a cache coupled to the at least one master device and arranged to store data values for access by that at least one master device when performing the data processing operations. Cache coherency circuitry is responsive to a coherency request from another portion of the coherent cache system to cause a coherency action to be taken in respect of at least one data value stored in the cache. Responsive to an indication that the coherency action has resulted in invalidation of that at least one data value in the cache, refetch control circuitry is used to initiate a refetch of that at least one data value into the cache. Such a mechanism causes the refetch of data into the cache to be triggered by the coherency action performed in response to a coherency request from another portion of the coherent cache system, rather than relying on any actions taken by the at least one master device, thereby providing a very flexible and efficient mechanism for reducing cache latency in a coherent cache system.

Apparatus and method for handling data in a cache

Interconnect logic is provided for coupling master logic units and slave logic units within a data processing apparatus to enable transactions to be performed. Each transaction comprises an address transfer from a master logic unit to a slave logic unit and one or more data transfers between that master logic unit and that slave logic unit. The interconnect logic comprises a plurality of connection paths for providing at least one address channel for carrying address transfers and at least one data channel for carrying data transfers, and control logic is used to control the use of the at least one address channel and the at least one data channel in order to enable the transactions to be performed. The control logic comprises address arbiter logic which, for an associated address channel, arbitrates between multiple address transfers seeking to use that associated address channel, and data arbiter logic which, for an associated data channel, arbitrates between multiple data transfers seeking to use that associated data channel. The data arbiter is operable independently of the address arbiter such that the data transfers of multiple transactions can occur out of order with respect to the corresponding address transfers of those multiple transactions. This enables efficient use to be made of the interconnect logic resources.

Interconnect logic for a data processing apparatus

An on-chip integrated circuit interconnectuses a serialization technique to divide a transaction to be transmitted into a sequence of transmission packets which are serially transmitted over a narrower connection. The order in which bits of the transaction are allocated to transmission packets is selected such that higher priority bits required by a receiving slave device in order that it can commence processing the transaction are sent first. This reduces the latency of the system.

Bit ordering for packetised serial data transmission on an integrated circuit

The present invention provides a data processing apparatus and method for managing snoop operations. The data processing apparatus has a plurality of processing units for performing data processing operations requiring access to data in shared memory, with at least two of the processing units having a cache associated therewith for storing a subset of the data for access by that processing unit. A snoop-based cache coherency protocol is employed to ensure data accessed by each processing unit is up-to-date, and when an access request is issued the cache coherency protocol is referenced in order to determine whether a snoop process is required. Snoop control storage is provided which defines a plurality of snoop schemes, each snoop scheme defining a series of snoop phases to be performed to implement the snoop process, and each snoop phase requiring a snoop operation to be performed on either a single cache or multiple caches. When a snoop process is required, a snoop unit is used to reference the snoop control storage in order to identify, having regard to one or more properties of the access request, the snoop scheme to be employed to perform the snoop process. Such an approach provides a great deal of flexibility with regards to how snoop processes are implemented, in particular allowing different snoop schemes to be used dependent on the properties of the access request in question.

Data processing apparatus and method for managing snoop operations

An integrated circuitincludes a transaction masterconnected via interconnect circuitryto a transaction slaveThe transaction slavegenerates a transfer-complete signal (R Last or B) to indicate completion of a data transfer (either a read or a write). When this transfer-complete signal has been received by the transaction masterthen the transaction mastergenerates a complete-acknowledgement signal RACK, WACK, which is passed back to the transaction slave so as to acknowledge receipt of the transfer-complete signal.

Control of master/slave communication within an integrated circuit

A data processing apparatus and method of handling write transactions in such an apparatus is provided. The apparatus has a plurality of devices, and bus circuitry providing connection paths between the plurality of devices. At least one of the devices has a bus master interface operable to generate write transactions for output via the bus circuitry, whilst at least one of the devices has a bus slave interface operable to receive the write transactions from the bus circuitry. A write transaction includes transferring a write address from a bus master interface to a bus slave interface and separately transferring write data from the bus master interface to the bus slave interface. In accordance with embodiments of the present invention, the bus master interface is allowed to generate a write transaction such that the write data is received at the bus slave interface before the associated write address. This leads to a significant decrease in the complexity of the apparatus.

Handling of write transactions in a data processing apparatus

An apparatus for arbitration within a data processing apparatus between a plurality of transfers to be routed over a corresponding plurality of paths provided by an interconnect circuit. The plurality of paths include a shared connection, the data processing apparatus having a plurality of initiator logic elements for initiating transfers and a plurality of recipient logic elements for receiving transfers, for each transfer the corresponding path coupling the initiator logic element responsible for initiating that transfer with the recipient logic element destined to receive that transfer. The apparatus provides arbitration logic with an indication as to whether the ready signal from a storage element has been asserted, and employs the arbitration logic to select, in dependence on predetermined criteria including at least that indication, one of the plurality of transfers for routing via the shared connection.

Performing arbitration in a data processing apparatus

A bus mastersends write transactions to a bus slavewhich include separate write addresses AW and write data WD. Write transaction identifiers AWID, WID are associated with these write addresses and write data. The bus slave can accept multiple write addresses such that there can be copending write transactions to the same bus slave. The bus slave uses the write transaction identifiers to correlate interleaved write data for the co-pending write transactions with their write addresses.

Write transaction interleaving

Bus logic couples plural master logic units with plural slave logic units to enable data transfers. Each master unit performs an address transfer which, when received by a specified slave unit, causes a data transfer between that master unit and said specified slave unit. Each slave unit must complete a data transfer prior to performing any further data transfers. A slave unit performs data transfers in an order which differs from that in which associated address transfers were received by that slave unit. In response to an adress transfer, the bus logic couples a master unit with a slave unit to enable a data transfer. The bus logic determines whether propagation of an address transfer may cause a deadlock situation where data transfers can not take place between affected master and slave units and, if so, to prevent propagating that address transfer.

Growing community of inventors

Sheffield, United Kingdom

Antony John Harris