Arm Limited

Antony John Penton

Simon John Craske

Andrew Christopher Rose

Ian Michael Caulfield

Peter Richard Greenhalgh

Allan John Skillman

Vladimir Vasekin

Max John Batley

Paul Stanley Hughes

Kauser Yakub Johar

Emre Özer

Balaji Venu

Xabier Iturbe

Alex James Waugh

Simon Andrew Ford

Chiloda Ashan Senerath Pathirane

Siddharth Gupta

Jatin Bhartia

Loïc Pierron

Richard Roy Grisenthwaite

Stuart David Biles

Cédric Denis Robert Airaud

Cyrille Nicolas Dray

Martinus Cornelis Wezelenburg

Chiloda Ashan Senarath Pathirane

Reiley Jeyapaul

Christopher Edwin Wrigley

Simon Axford

Robert Gwilym Dimond

Matthew Lee Winrow

Richard York

Mittu Xavier Kocherry

Vincent Rezard

Andrew James Antony Lees

Luc Olivier Palau

Sachin Gulyani

Zemian Hughes

Ken Yi Wong

An apparatus comprises associating circuitry to associate an indirect prefetch condition with a memory access request when hint information indicates that the data to be accessed in response to the memory access request is address indicating data which is to be used to generate a second address for a subsequent memory access request. A second address can be generated using the address indicating data, and a prefetch memory access request can be issued to seek to make data at the second address available in the associated cache.

Cache prefetching

An apparatus comprises a storage configured to store data items associated with error correction codes (ECCs); data retrieval circuitry responsive to a data retrieval request specifying a retrieval address to retrieve a retrieved data item and an associated ECC from a storage location corresponding to the retrieval address; and ECC decoding circuitry to generate a syndrome value by performing an ECC decoding operation on a decoding input value comprising data bits of the retrieved data item, code bits of the associated ECC, and address bits of the retrieval address, and to determine based on the syndrome value whether an error condition has occurred. Each bit of the syndrome value depends on a different combination of bits of the decoding input value. For each data bit of the decoding input value, an odd number of bits of the syndrome value depend on that data bit. For each address bit of the decoding input value, an even number of bits of the syndrome value depend on that address bit.

Error correction code

An apparatus is provided having a memory device and associated access control circuitry, and an additional memory device and associated additional access control circuitry. Redundant data generation circuitry generates, for a given block of data having an associated given memory address, an associated block of redundant data for use in an error detection process. The access control circuitry is arranged to store, at a location in the memory device determined from the given memory address, at least a portion of the given block of data and a first copy of the associated block of redundant data, and the additional access control circuitry is arranged to store, at a location in the additional memory device determined from the given memory address, any remaining portion of the given block of data not stored in the memory device and a second copy of the associated block of redundant data. Error detection circuitry performs the error detection process on the stored given block of data using one copy of the associated block of redundant data, and generates an output signal indicating a result of the error detection process. Comparison circuitry compares the first and second copies of the associated block of redundant data, and generates a comparison result signal to supplement the output signal from the error detection circuitry.

Apparatus and method for detecting errors in a memory device

An apparatushas a processing pipelinesupporting at least a first processing mode and a second processing mode with different energy consumption or performance characteristics. A storage structureis accessible in both the first and second processing modes. When the second processing mode is selected, control circuitrytriggers a subsetof the entries of the storage structure to be placed in a power saving state.

Processing pipeline with first and second processing modes having different performance or energy consumption characteristics

A processing systemincludes a processing pipelinewhich includes fetch circuitryfor fetching instructions to be executed from a memory. Buffer control circuitryis responsive to a programmable trigger, such as explicit hint instructions delimiting an instruction burst, or predetermined configuration data specifying parameters of a burst together with a synchronising instruction, to trigger the buffer control circuitry to stall a stallable portion of the processing pipeline (e.g. issue circuitry), to accumulate within one or more buffersfetched instructions starting from a predetermined starting instruction, and, when those instructions have been accumulated, to restart the stallable portion of the pipeline.

Programmable instruction buffering for accumulating a burst of instructions

An apparatus and method are described, the apparatus comprising processing circuitry to perform data processing operations, microarchitecture circuitry used by the processing circuitry during performance of the data processing operations, and an interface to receive interrupt requests. The processing circuitry is responsive to a received interrupt request to perform an interrupt service routine, and the apparatus comprises prediction circuitry to determine a predicted time of reception of a next interrupt of at least one given type. The apparatus also comprises microarchitecture control circuitry arranged to vary a configuration of the microarchitecture circuitry between a performance based configuration and a responsiveness based configuration in dependence on the predicted time, so as to seek to increase the responsiveness of the apparatus to interrupts as the predicted time is approached.

Improving the responsiveness of an apparatus to certain interrupts

Apparatus for processing data () includes issue circuitry () for issuing program instructions (processing operations) to execute either within real time execution circuitry () or non real time execution circuitry (). Registers within a register file () are marked as non real time dependent registers if they are allocated to store a data value which is to be written by an uncompleted program instruction issued to the non real time execution circuitry and not yet completed. Issue policy control circuitry () responds to a trigger event to enter a real time issue policy mode to control the issue circuitry () to issue candidate processing operations (such as program instruction, micro-operations, architecturally triggered processing operations etc.) to one of the non real time execution circuitry or the real time execution circuitry in dependence upon whether that candidate processing operation reads a register marked as a non real time dependent register.

Instruction issue according to in-order or out-of-order execution modes

A processing pipeline may have first and second execution circuits having different performance or energy consumption characteristics. Instruction supply circuitry may support different instruction supply schemes with different energy consumption or performance characteristics. This can allow a further trade-off between performance and energy efficiency. Architectural state storage can be shared between the execute units to reduce the overhead of switching between the units. In a parallel execution mode, groups of instructions can be executed on both execute units in parallel.

Apparatus and branch prediction circuitry having first and second branch prediction schemes, and method

A data processing apparatus has processing circuitry for executing first software at a first privilege level and second software at a second privilege level higher than the first privilege level. Attributes may be set by the first and second software to indicate whether execution of the data access instruction can be interrupted. For a predetermined type of data access instruction for which the second attribute set by the second software specifies that the instruction can be interrupted, the instruction may be set as interruptable even if the first attribute set by the first software specifies that the execution of the instruction cannot be interrupted.

Handling access attributes for data accesses

An apparatus has first processing circuitry and second processing circuity. The second processing circuitry has at least one hardware mechanism providing a greater level of fault protection or fault detection than is provided for the first processing circuitry. Coherency control circuitry controls access to data from at least part of a shared address space by the first and second processing circuitry according to an asymmetric coherency protocol in which a local-only update of data in a local cache of the first processing circuitry is restricted in comparison to a local-only update of data in a local cache of the second processing circuitry.

Asymmetric coherency protocol for first and second processing circuitry having different levels of fault protection or fault detection

The execution of time intensive instructions can lead to critical events being responded to late or not being responded to at all. An information processing apparatus comprises processing circuitry () for executing instructions comprising one or more time intensive instructions and exception generating circuitry () for generating at least one exception for the processing circuitry. The processing circuitry maintains a control value () for indicating whether or not the time intensive instructions can be executed. When a time intensive instruction is encountered, if the control value indicates that time intensive instructions cannot be executed then a first exception triggers the processing circuitry to suppress execution of the time intensive instruction. Alternatively, if the control value indicates that time intensive instructions can be executed, then the time intensive instruction is executed.

Selectively suppressing time intensive instructions based on a control value

A processing system includes a processing pipeline which includes fetch circuitry for fetching instructions to be executed from a memory. Buffer control circuitry is responsive to a programmable trigger, such as explicit hint instructions delimiting an instruction burst, or predetermined configuration data specifying parameters of a burst together with a synchronising instruction, to trigger the buffer control circuitry to stall a stallable portion of the processing pipeline (e.g. issue circuitry), to accumulate within one or more buffers fetched instructions starting from a predetermined starting instruction, and, when those instructions have been accumulated, to restart the stallable portion of the pipeline.

Programmable instruction buffering of a burst of instructions including a pending data write to a given memory address and a subsequent data read of said given memory address

Aspects of the present disclosure relate to an apparatus comprising processing circuitry to execute a plurality of code sequences, and configuration storage to store mode control data for the processing circuitry. When the processing circuitry is executing one of said plurality of code sequences, the mode control data is set so as to identify a high resilience mode of operation of the processing circuitry where usage of one or more components of the processing circuitry is modified so as to increase resilience of the processing circuitry to faults relative to a default mode of operation of the processing circuitry.

Apparatus and method for increasing resilience to faults

Apparatus for processing data is provided with fetch circuitry for fetching program instructions for execution from one or more active threads of instructions having respective program counter values. Pipeline circuitry has a first operating mode and a second operating mode. Mode switching circuitry switches the pipeline circuitry, between the first operating mode and the second operating mode in dependence upon a number of active threads of program instructions having program instructions available to be executed. The first operating mode has a lower average energy consumption per instruction executed than the second operating mode and the second operating mode has a higher average rate of instruction execution for a single thread than the first operating mode. The first operating mode may utilise a barrel processing pipeline to perform interleaved multiple thread processing. The second operating mode may utilise an out-of-order processing pipeline for performing out-of-order processing.

Mode switching in dependence upon a number of active threads

A data processing apparatus has prefetch circuitry for prefetching instructions from a data store into an instruction queue. Branch prediction circuitry is provided for predicting outcomes of branch instructions and the prefetch circuitry may prefetch instructions subsequent to the branch based on the predicted outcome. Instruction identifying circuitry identifies whether a given instruction prefetched from the data store is a predetermined type of program flow altering instruction and if so then controls the prefetch circuitry to halt prefetching of subsequent instructions into the instruction queue.

Growing community of inventors

Cambridge, United Kingdom

Antony John Penton