Systems, apparatuses, and methods for implementing a discard engine in a graphics pipeline are disclosed. A system includes a graphics pipeline with a geometry engine launching shaders that generate attribute data for vertices of each primitive of a set of primitives. The attribute data is consumed by pixel shaders, with each pixel shader generating a deallocation message when the pixel shader no longer needs the attribute data. A discard engine gathers deallocations from multiple pixel shaders and determines when the attribute data is no longer needed. Once a block of attributes has been consumed by all potential pixel shader consumers, the discard engine deallocates the given block of attributes. The discard engine sends a discard command to the caches so that the attribute data can be invalidated and not written back to memory.

A system to support a machine learning (ML) operation comprises a core configured to receive and interpret commands into a set of instructions for the ML operation and a memory unit configured to maintain data for the ML operation. The system further comprises an inference engine having a plurality of processing tiles, each comprising an on-chip memory (OCM) configured to maintain data for local access by components in the processing tile and one or more processing units configured to perform tasks of the ML operation on the data in the OCM. The system also comprises an instruction streaming engine configured to distribute the instructions to the processing tiles to control their operations and to synchronize data communication between the core and the inference engine so that data transmitted between them correctly reaches the corresponding processing tiles while ensuring coherence of data shared and distributed among the core and the OCMs.

A system to support a machine learning (ML) operation comprises a core configured to receive and interpret commands into a set of instructions for the ML operation and a memory unit configured to maintain data for the ML operation. The system further comprises an inference engine having a plurality of processing tiles, each comprising an on-chip memory (OCM) configured to maintain data for local access by components in the processing tile and one or more processing units configured to perform tasks of the ML operation on the data in the OCM. The system also comprises an instruction streaming engine configured to distribute the instructions to the processing tiles to control their operations and to synchronize data communication between the core and the inference engine so that data transmitted between them correctly reaches the corresponding processing tiles while ensuring coherence of data shared and distributed among the core and the OCMs.

Methods, systems, and apparatus, including computer-readable media, are described for an integrated circuit that accelerates machine-learning computations. The circuit includes processor cores that each include: multiple channel controllers; an interface controller for coupling each channel controller to any memory channel of a system memory; and a fetch unit in each channel controller. Each fetch is configured to: receive channel data that encodes addressing information; obtain, based on the addressing information, data from any memory channel of the system memory using the interface controller; and write the obtained data to a vector memory of the processor core via the corresponding channel controller that includes the respective fetch unit.

Techniques are disclosed relating to data synchronization barrier operations. A system includes a first processor that may receive a data barrier operation request from a second processor include in the system. Based on receiving that data barrier operation request from the second processor, the first processor may ensure that outstanding load/store operations executed by the first processor that are directed to addresses outside of an exclusion region have been completed. The first processor may respond to the second processor that the data barrier operation request is complete at the first processor, even in the case that one or more load/store operations that are directed to addresses within the exclusion region are outstanding and not complete when the first processor responds that the data barrier operation request is complete.

A system to support a machine learning (ML) operation comprises a core configured to receive and interpret commands into a set of instructions for the ML operation and a memory unit configured to maintain data for the ML operation. The system further comprises an inference engine having a plurality of processing tiles, each comprising an on-chip memory (OCM) configured to maintain data for local access by components in the processing tile and one or more processing units configured to perform tasks of the ML operation on the data in the OCM. The system also comprises an instruction streaming engine configured to distribute the instructions to the processing tiles to control their operations and to synchronize data communication between the core and the inference engine so that data transmitted between them correctly reaches the corresponding processing tiles while ensuring coherence of data shared and distributed among the core and the OCMs.

Techniques are disclosed relating to data synchronization barrier operations. A system includes a first processor that may receive a data barrier operation request from a second processor include in the system. Based on receiving that data barrier operation request from the second processor, the first processor may ensure that outstanding load/store operations executed by the first processor that are directed to addresses outside of an exclusion region have been completed. The first processor may respond to the second processor that the data barrier operation request is complete at the first processor, even in the case that one or more load/store operations that are directed to addresses within the exclusion region are outstanding and not complete when the first processor responds that the data barrier operation request is complete.

A system to support a machine learning (ML) operation comprises an array-based inference engine comprising a plurality of processing tiles each comprising at least one or more of an on-chip memory (OCM) configured to maintain data for local access by components in the processing tile and one or more processing units configured to perform one or more computation tasks on the data in the OCM by executing a set of task instructions. The system also comprises a data streaming engine configured to stream data between a memory and the OCMs and an instruction streaming engine configured to distribute said set of task instructions to the corresponding processing tiles to control their operations and to synchronize said set of task instructions to be executed by each processing tile, respectively, to wait current certain task at each processing tile to finish before starting a new one.

A multi-core processor providing heterogeneous processor cores and a shared cache is presented.

A system to support a machine learning (ML) operation comprises an array-based inference engine comprising a plurality of processing tiles each comprising at least one or more of an on-chip memory (OCM) configured to maintain data for local access by components in the processing tile and one or more processing units configured to perform one or more computation tasks on the data in the OCM by executing a set of task instructions. The system also comprises a data streaming engine configured to stream data between a memory and the OCMs and an instruction streaming engine configured to distribute said set of task instructions to the corresponding processing tiles to control their operations and to synchronize said set of task instructions to be executed by each processing tile, respectively, to wait current certain task at each processing tile to finish before starting a new one.