Arm Limited

Joseph Michael Pusdesris

Yasuo Ishii

Alexander Cole Shulyak

Klas Magnus Bruce

Michael Filippo

Jamshed Jalal

Miles Robert Dooley

Muhammad Umar Farooq

Chris Abernathy

Adrian Montero

Karthik Sundaram

Balaji Vijayan

Nicholas Andrew Plante

Paul Gilbert Meyer

Phanindra Kumar Mannava

David Joseph Hawkins

Dimitrios Kaseridis

Ho-Seop Kim

Jacob Martin Degasperis

Abhishek Raja

Houdhaifa Bouzguarrou

Alex James Waugh

James David Dundas

Gurunath Ramagiri

Michael Brian Schinzler

Andrew John Turner

Dam Sunwoo

Adam George

Krishnendra Nathella

Devin S Lafford

Jungsoo Kim

Vasu Kudaravalli

Eric Charles Quinnell

Rania Hussein Hassan Mameesh

Anoop Ramachandra Iyer

An apparatus comprises processing circuitry to perform data processing in response to instructions; prediction state storage circuitry to store prediction state information; prediction state training circuitry to train the prediction state information in response to events detected during processing of instructions by the processing circuitry; and prediction circuitry to predict, based on the prediction state information, a given speculative action to be performed in response to a given prediction trigger event; in which: the prediction circuitry varies, based on one or more current system resource conditions of the apparatus, at least one action selection criterion used to select which speculative action is to be performed.

Prediction circuitry configured to predict speculative action based on hit-to-train ratio or based on train counter and hit counter

In register renaming circuitry architectural registers specified in instructions are mapped to physical registers using a mapping table. Operations to be performed with respect to the physical registers are generated in dependence on the instructions and on the mapping table entries. When the mapping table has a mapping of a first instruction destination physical register for a first instruction destination architectural register specified in a first instruction, a second instruction specifying the first instruction destination architectural register as a second instruction source architectural register causes an adapted second operation to be generated corresponding to the second instruction using at least one first instruction source physical register as at least one second instruction source physical register. The adapted second operation incorporates a first operation corresponding to the first instruction.

Register rename stage fusing of instructions

Processing circuitry to execute load operations, each associated with an identifier. Prediction circuitry to receive a given load value associated with a given identifier, and to make, in dependence on the given load value, a prediction indicating a predicted load value for a subsequent load operation to be executed by the processing circuitry and an ID-delta value indicating a difference between the given identifier and an identifier of the subsequent load operation. The predicted load value being predicted in dependence on at least one occurrence of each of the given load value and the predicted load value during execution of a previously-executed sequence of load operations. The prediction circuitry is configured to determine the ID-delta value in dependence on a difference between identifiers associated with the at least one occurrence of each of the given load value and the predicted load value in the previously-executed sequence of load operations.

Predicting a load value for a subsequent load operation

Aspects of the present disclosure relate to an apparatus comprising processing circuitry, first cache circuitry and second cache circuitry, wherein the second cache circuitry has an access latency higher than an access latency of the first cache circuitry. The second cache circuitry is responsive to receiving a request for data stored within the second cache circuitry to identify said data as pseudo-invalid data and provide said data to the first cache circuitry. The second cache circuitry is responsive to receiving an eviction indication, indicating that the first cache circuitry is to evict said data, to, responsive to determining that said data has not been modified since said data was provided to the first cache circuitry, identify said pseudo-invalid data as valid data.

Methods and apparatus for transferring data within hierarchical cache circuitry

There is provided a data processing apparatus comprising history storage circuitry that stores sets of behaviours of helper instructions for a control flow instruction. Pointer storage circuitry stores pointers, each associated with one of the sets. The behaviours in the one of the sets are indexed according to one of the pointers associated with that one of the sets. Increment circuitry increments at least some of the pointers in response to an increment event and prediction circuitry determines a predicted behaviour of the control flow instruction using one of the sets of behaviours.

Control flow prediction using pointers

A data processing apparatus is provided. Rename circuitry performs a register rename stage of a pipeline by storing, in storage circuitry, mappings between registers. Each of the mappings is associated with an elimination field value. Operation elimination circuitry replaces an operation that indicates an action is to be performed on data from a source register and stored in a destination register, with a new mapping in the storage circuitry that references the destination register and has the elimination field value set. Operation circuitry responds to a subsequent operation that accesses the destination register when the elimination field value is set; by obtaining contents of the source register, performing the action on the contents to obtain a result, and returning the result.

Operation elimination

An apparatus comprises memory management circuitry to perform a translation table walk for a target address of a memory access request and to signal a fault in response to the translation table walk identifying a fault condition for the target address, prefetch circuitry to generate a prefetch request to request prefetching of information associated with a prefetch target address to a cache; and faulting address prediction circuitry to predict whether the memory management circuitry would identify the fault condition for the prefetch target address if the translation table walk was performed by the memory management circuitry for the prefetch target address. In response to a prediction that the fault condition would be identified for the prefetch target address, the prefetch circuitry suppresses the prefetch request and the memory management circuitry prevents the translation table walk being performed for the prefetch target address of the prefetch request.

Faulting address prediction for prefetch target address

Indirect prefetch circuitry initiates a producer prefetch requesting return of producer data having a producer address and at least one consumer prefetch to request prefetching of consumer data having a consumer address derived from the producer data. A producer prefetch filter table stores producer filter entries indicative of previous producer addresses of previous producer prefetches. Initiation of a requested producer prefetch for producer data having a requested producer address is suppressed when a lookup of the producer prefetch filter table determines that the requested producer address hits against a producer filter entry of the table. The lookup of the producer prefetch filter table for the requested producer address depends on a subset of bits of the requested producer address including at least one bit which distinguishes different chunks of data within a same cache line.

Producer prefetch filter

A predicated-loop-terminating branch instruction controls, based on whether a loop termination condition is satisfied, whether the processing circuitry should process a further iteration of a predicated loop body or process a following instruction. If at least one unnecessary iteration of the predicated loop body is processed following a mispredicted-non-termination branch misprediction when the loop termination condition is mispredicted as unsatisfied for a given iteration when it should have been satisfied, processing of the at least one unnecessary iteration of the predicated loop body is predicated to suppress an effect of the at least one unnecessary iteration. When the mispredicted-non-termination branch misprediction is detected for the given iteration of the predicated-loop-terminating branch instruction, in response to determining that a flush suppressing condition is satisfied, flushing of the at least one unnecessary iteration of the predicated loop body is suppressed as a response to the mispredicted-non-termination branch misprediction.

Responding to branch misprediction for predicated-loop-terminating branch instruction

A technique is provided for prefetching data items. An apparatus has a storage structure with a plurality of entries to store data items. The storage structure is responsive to access requests from processing circuitry to provide access to the data items. The apparatus has prefetch circuitry to prefetch data and correlation information storage to store correlation information for a plurality of data items. The correlation information identifies, for each of the plurality of data items, one or more correlated data items. The prefetch circuitry is configured to monitor the access requests from the processing circuitry. In response to detecting a hit in the correlation information storage for a particular access request that identifies a requested data item for which the correlation information storage stores correlation information, the prefetch circuitry is configured to prefetch the one or more correlated data items identified by the correlation information for the requested data item.

Prefetching

A request node is provided, that includes request circuitry for issuing outgoing memory access requests to a remote node. Status receiving circuitry receives statuses regarding remote memory access requests at the remote node and control circuitry controls at least one of a rate or an aggression at which the outgoing memory access requests are issued to the remote node in dependence on at least some of the statuses. The control circuitry is inhibited from controlling the rate or the aggression until multiple statuses are received.

Controlling access requests of request nodes

Data processing apparatuses and methods of processing data are disclosed. The operations comprise: storing copies of data items; and storing, in a producer pattern history table, a plurality of producer-consumer relationships, each defining an association between producer load indicator and a plurality of consumer load entries, each consumer load entry comprising a consumer load indicator and one or more usefulness metrics. Further steps comprise: initiating, in response to a data load from an address corresponding to the producer load indicator in the producer pattern history table and when at least one of the corresponding one or more usefulness meets a criterion, a producer prefetch of data to be prefetched for storing as a local copy; and issuing, when the data is returned, one or more consumer prefetches to return consumer data from a consumer address generated from the data returned by the producer prefetch and a consumer load indicator of a consumer load entry.

Data processing apparatus and method for generating prefetches

There is provided a data processing apparatus comprising table circuitry to store a table that indicates, for a program counter value of an instruction that performs a memory access operation at a memory address, one or more offsets of the memory address and an associated confidence for each of the one or more offsets. Prefetch circuitry prefetches data based on each of the offsets in dependence on the associated confidence. Each of the offsets of the memory address is dynamically determined.

Prefetching at dynamically determined offsets

A technique is provided for controlling eviction from a storage structure. An apparatus has a storage structure with a plurality of entries to store data. The apparatus also has eviction control circuitry configured to maintain eviction control information in accordance with an eviction policy, the eviction policy specifying how the eviction control information is to be updated in response to accesses to the entries of the storage structure. The eviction control circuitry is responsive to a victim selection event to employ the eviction policy to select, with reference to the eviction control information, one of the entries to be a victim entry whose data is to be discarded from the storage structure. The eviction control circuitry is further configured to maintain, for each of one or more groups of entries in the storage structure, an indication of a most-recent entry. The most-recent entry is an entry in that group that was most recently subjected to at least a given type of access. For each group, in response to an access to a given entry of that group other than the most-recent entry for that group, the eviction control circuitry is configured to update the eviction control information according to the eviction policy. However, in response to an access to the most-recent entry for that group, the eviction control circuitry is configured to prevent an update to at least the eviction control information associated with the most-recent entry.

Apparatus and method for controlling eviction from a storage structure

An apparatus and method are provided. The apparatus comprises storage circuitry to store a plurality of data elements. Processing circuitry executes a stream of instructions comprising access instructions that access some of the data elements at given locations. Training circuitry determines a pattern of the given locations based on the access instructions. Prefetch circuitry performs prefetches based on the pattern and filter circuitry filters the access instructions used by the training circuitry to determine the pattern by including discontinuous access instructions whose given location raises a discontinuity with the given location of a previous access instruction. In this way, it is possible to perform prefetching by calculating, rather than guessing, at a cumulative stride between the access instructions.

Growing community of inventors

Austin, TX, United States of America

Joseph Michael Pusdesris