Arm Limited

Oracle International Corporation

Jared Smolens

Manish K Shah

Jens Olson

John Wakefield Brothers

Gideon N Levinsky

John D Pape

Aaron DeBattista

Eric Kunze

Daren Croxford

Robert T Golla

Dominic Hugo Symes

Paul Joseph Jordan

Mark Luttrell

Ian Rudolf Bratt

Sharjeel Saeed

Zoran Radovic

Elliot Maurice Simon Rosemarine

Lingchuan Meng

Chi-wen Cheng

Aspects of the present disclosure relate to apparatus comprising execution circuitry comprising at least one execution unit to execute program instructions, and control circuitry. The control circuitry receives a stream of processing instructions, and issues each received instruction to one of said at least one execution unit. Responsive to determining that a first type of context switch is to be performed from an initial context to a new context, issuing continues until a pre-emption point in the stream of processing instructions is reached. Responsive to reaching the pre-emption point, state information is stored, and the new context is switched to. Responsive to determining that a context switch is to be performed to return from the new context to the initial context, the processing status is restored from the state information, and the stream of processing instructions is continued.

Methods and apparatus for context switching

A processor comprising a first storage managed as a circular buffer to store a plurality of data structures. Each data structure comprises: an identifier, a size indicator and first data associated with instructions for execution of a task. The processor is configured for searching for a data structure in the first storage. A data structure subsequent to the tail data structure can be located using a storage address in the first storage of a tail data structure and the size indicator of all data structures preceding the second data structure among the plurality of data structures. When a data structure is found, the task may be executed based at least in part on the first data of the found data structure.

Data storage

A processor arranged to compress neural network activation data comprising an input module for obtaining neural network activation data. The processor also comprises a block creation module arranged to split the neural network activation data into a plurality of blocks; and a metadata generation module for generating metadata associated with at least one of the plurality of blocks. Based on the metadata generated a selection module selects a compression scheme for each of the plurality of blocks, and a compression module for applying the selected compression scheme to the corresponding block to produce compressed neural network activation data. An output module is also provided for outputting the compressed neural network activation data.

Compression of neural network activation data

Systems, apparatuses and methods suitable for optimizing synchronization mechanisms for multi-core processors are provided. The synchronizing mechanisms may be optimized by receiving a command stream which comprises a plurality of commands including one or more wait commands, wherein each wait command has an associated state and one or more associated conditions; sequentially processing each command in the command stream until a wait command is reached; checking the state associated with the wait command to be processed, wherein if said state is a blocking state, further processing of commands in the command stream is paused until each of said wait command's associated conditions are met, and wherein if said state is a non-blocking state, the next command in the command stream is retrieved and processed.

Synchronization mechanisms for a multi-core processor using wait commands having either a blocking or a non-blocking state

Herein described is a method of operating an accumulation process in a data processing apparatus. The accumulation process comprises a plurality of accumulations which output a respective plurality of accumulated values, each based on a stored value and a computed value generated by a data processing operation. The method comprises storing a first accumulated value, the first accumulated value being one of said plurality of accumulated values, into a first storage device comprising a plurality of single-bit storage elements; determining that a predetermined trigger has been satisfied with respect to the accumulation process; and in response to the determining, storing at least a portion of a second accumulated value, the second accumulated value being one of said plurality of accumulated values, into a second storage device.

Accumulating data values and storing in first and second storage devices

A system for generating predictions for a hardware table walk to find a map of a given virtual address to a corresponding physical address is disclosed. The system includes a plurality of memories, which each includes respective plurality of entries, each of which includes a prediction of a particular one of a plurality of buffers which includes a portion of a virtual to physical address translation map. A first circuit may generate a plurality of hash values to retrieve a plurality of predictions from the plurality of memories, where each has value depends on a respective address and information associated with a respective thread. A second circuit may select a particular prediction of the retrieved predictions to use based on a history of previous predictions.

Adaptive tablewalk translation storage buffer predictor

A method and apparatus for performing branch prediction is disclosed. A branch predictor includes a history buffer configured to store a branch history table indicative of a history of a plurality of previously fetched branch instructions. The branch predictor also includes a branch target cache (BTC) configured to store branch target addresses for fetch addresses that have been identified as including branch instructions but have not yet been predicted. A hash circuit is configured to form a hash of a fetch address, history information received from the history buffer, and hit information received from the BTC, wherein the fetch address includes a branch instruction. A branch prediction unit (BPU) configured to generate a branch prediction for the branch instruction included in the fetch address based on the hash formed from the fetch address, history information, and BTC hit information.

Method and apparatus for augmentation and disambiguation of branch history in pipelined branch predictors

A system for generating predictions for a hardware table walk to find a map of a given virtual address to a corresponding physical address is disclosed. The system includes a plurality memories, which each includes respective plurality of entries, each of which includes a prediction of a particular one of a plurality of buffers which includes a portion of a virtual to physical address translation map. A first circuit may generate a plurality of hash values to retrieve a plurality of predictions from the plurality of memories, where each has value depends on a respective address and information associated with a respective thread. A second circuit may select a particular prediction of the retrieved predictions to use based on a history of previous predictions.

Techniques for executing versioned memory access instructions. In one embodiment, a processor is configured to execute versioned store instructions of a first thread within a first mode of operation. In this embodiment, in the first mode of operation, the processor is configured to retire a versioned store instruction only after a version comparison has been performed for the versioned store instruction. In this embodiment the processor is configured to suppress retirement of instructions in the first thread that are younger than an oldest versioned store instruction until the oldest versioned store instruction has retired. In some embodiments, the processor is configured to execute versioned store instructions of a given thread within a second mode of operation, in which the processor is configured to retire outstanding versioned store instructions before a version comparison has been performed.

Growing community of inventors

Santa Clara, CA, United States of America

Jared Smolens