Abstract: A network interface device comprises a streaming data processing path comprising a first data processing engine and hubs. A first scheduler associated with a first hub controls an output of data by the first hub to the first data processing engine and a second scheduler associated with a second hub controls an output of data by the second hub. The first hub is arranged upstream of the first data processing engine on the data processing path and is configured to receive data from a first upstream data path entity and from a first data processing entity implemented in programmable circuitry via a data ingress interface of the first hub. The first data processing engine is configured to receive data from the first hub, process the received data and output the processed data to the second hub arranged downstream of first data processing engine.

Abstract: The present application relates to a network-on-chip data processing method. The method is applied to a network-on-chip processing system, the network-on-chip processing system is used for executing machine learning calculation, and the network-on-chip processing system comprises a storage device and a calculation device. The method comprises: accessing the storage device in the network-on-chip processing system by means of a first calculation device in the network-on-chip processing system, and obtaining first operation data; performing an operation on the first operation data by means of the first calculation device to obtain a first operation result; and sending the first operation result to a second calculation device in the network-on-chip processing system. According to the method, operation overhead can be reduced and data read/write efficiency can be improved.

Abstract: A method and a control device for returning of command response information, and an electronic device are provided. The method includes: receiving response information for a command request, the response information carrying a status identification and a level identification of the command request; storing the response information in a corresponding level of a data queue in accordance with the level identification, where the data queue includes multiple levels, and each level of the data queue is used to store one or more pieces of response information; scanning all levels of the data queue, and determining, a level in which all parts of response information are collected, as a candidate level; determining a first piece of response information in accordance with a status identification of the response information stored in the candidate level; and outputting the first piece of response information.

Abstract: Disclosed embodiments relate to systems and methods for performing instructions to transform matrices into a row-interleaved format. In one example, a processor includes fetch and decode circuitry to fetch and decode an instruction having fields to specify an opcode and locations of source and destination matrices, wherein the opcode indicates that the processor is to transform the specified source matrix into the specified destination matrix having the row-interleaved format; and execution circuitry to respond to the decoded instruction by transforming the specified source matrix into the specified RowInt-formatted destination matrix by interleaving J elements of each J-element sub-column of the specified source matrix in either row-major or column-major order into a K-wide submatrix of the specified destination matrix, the K-wide submatrix having K columns and enough rows to hold the J elements.

Abstract: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.

Abstract: An instruction scheduling method and an instruction scheduling system for a reconfigurable array processor. The method includes: determining whether a fan-out of a vertex in a data flow graph (DFG) is less than an actual interconnection number of a processing unit in a reconfigurable array; establishing a corresponding relationship between the vertex and a correlation operator of the processing unit; introducing a register to a directed edge, acquiring a retiming value of each vertex; arranging instructions in such a manner that retiming values of the instruction vertexes are in ascending order, and acquiring transmission time and scheduling order of the instructions; folding the DFG, placing an instruction to an instruction vertex; inserting a register and acquiring a current DFG; and acquiring a common maximum subset of the current DFG and the reconfigurable array by a maximum clique algorithm, and distributing the instructions.

Abstract: A storage stores observation data (a set of pairs each consists of a parameter vector value representing a point in a D-dimensional space and an observation value of an objective function at the point). A processor determines a low-dimensional search space (R (2?R<D)-dimensional affine subspace passes through a point represented by a parameter vector value in the D-dimensional space), extracts data (a set of pairs corresponding to points at which similarity to a point included in the search space are more than a predetermined value. The points are among points in the D-dimensional space represented by parameter vector values included in the observation data), and proposes a parameter vector value representing a next point based on the extracted data.

Abstract: A representative reconfigurable processing circuit and a reconfigurable arithmetic circuit are disclosed, each of which may include input reordering queues; a multiplier shifter and combiner network coupled to the input reordering queues; an accumulator circuit; and a control logic circuit, along with a processor and various interconnection networks. A representative reconfigurable arithmetic circuit has a plurality of operating modes, such as floating point and integer arithmetic modes, logical manipulation modes, Boolean logic, shift, rotate, conditional operations, and format conversion, and is configurable for a wide variety of multiplication modes. Dedicated routing connecting multiplier adder trees allows multiple reconfigurable arithmetic circuits to be reconfigurably combined, in pair or quad configurations, for larger adders, complex multiplies and general sum of products use, for example.

Abstract: The embodiments of the disclosure relate to a computing device, a computing equipment, and a programmable scheduling method for data loading and execution, and relate to the field of computer. The computing device is coupled to a first computing core and a first memory. The computing device includes a scratchpad memory, a second computing core, a first hardware queue, a second hardware queue and a synchronization unit. The second computing core is configured for acceleration in a specific field. The first hardware queue receives a load request from the first computing core. The second hardware queue receives an execution request from the first computing core. The synchronization unit configured to make the triggering of the load request and the execution request to cooperate with each other. In this manner, flexibility, throughput, and overall performance can be enhanced.

Abstract: A memory controller and buffers on memory modules each operate in two modes, depending on the type of motherboard through which the controller and modules are connected. In a first mode, the controller transmits decoded chip-select signals independently to each module, and the motherboard data channel uses multi-drop connections to each module. In a second mode, the motherboard has point-to-point data channel and command address connections to each of the memory modules, and the controller transmits a fully encoded chip-select signal group to each module. The buffers operate modally to correctly select ranks or partial ranks of memory devices on one or more modules for each transaction, depending on the mode.

Abstract: On-chip software-based activity monitoring is implemented to configure hardware-based activity throttling. A software-based activity monitor implemented on an integrated circuit obtains data from on-chip components to determine throttling modifications for a processing engine of the integrated circuit. The throttling modifications are applied to throttling criteria that is used by a hardware-based activity monitor on the integrated circuit which is responsible for directly evaluating and throttling processing at the processing engine of the integrated circuit.

Abstract: Circuits and methods enabling common control of an agent device by two or more buses, particularly MIPI RFFE serial buses. In essence, the invention provides flagging signals designating completed register write operations to denote which of two registers are active, such that synchronization is accomplished in a clock-free manner. One embodiment includes at least two decoders, each including a common register and a bus (S/P) decoder coupled to a respective bus and to the common register. The S/P decoder asserts a write-complete signal when a write operation to a corresponding common register is completed. A multiplexer has at least two selectable input bus ports coupled to the common registers within the at least two decoders. A selection circuit selects an input bus port of the multiplexer in response to the assertion of a last write-complete signal from the S/P decoders.

Abstract: In a processing system, a conversion circuit coupled to a system bus generates a flow control unit (FLIT) and provides the FLIT to a link interface circuit for transmission over an external link. The external link may be a peripheral component interface (PCI) express (PCIe) link coupled to an external device comprising a cache or memory. The conversion circuit generates the FLIT, including write information based on the write instruction, metadata associated with at least one cache line, and cache line chunks, including bytes of a cache line. The cache line chunks may be chunks of one of the at least one cache line. Including the metadata in the FLIT avoids separately transmitting the at least one cache line and the metadata over the external link, which improves performance compared to generating separate transmissions. In some examples, the FLIT corresponds to a compute express link (CXL) protocol FLIT.

Abstract: A bridging module, a data transmission system, and a data transmission method are provided. The bridging module obtains a first read request, and allocates a first location storage space for first return data corresponding to the first read request. The bridging module combines a first master transaction identifier and an address of the first location storage space as a first slave transaction identifier of the first read request, and sends the first read request to a slave device. The bridging module obtains a second read request, and allocates a second location storage space for second return data corresponding to the second read request. The bridging module combines a second master transaction identifier and an address of the second location storage space as a second slave transaction identifier of the second read request, and sends the second read request to the slave device.

Abstract: Systems and methods for stalling a host processor. In some embodiments, the host processor may be caused to initiate one or more selected transactions, wherein the one or more selected transactions comprise a bus transaction. The host processor may be prevented from completing the one or more selected transactions, to thereby stall the host processor.

Abstract: Systems and methods are disclosed for macro-op fusion. Sequences of macro-ops that include a control-flow instruction are fused into single micro-ops for execution. The fused micro-ops may avoid the use of control-flow instructions, which may improve performance. A fusion predictor may be used to facilitate macro-op fusion.

Abstract: Embodiments described herein provide techniques to manage drivers in a user space in a data processing system. One embodiment provides a data processing system configured perform operations, comprising discovering a hardware device communicatively coupled to the communication bus, launching a user space driver daemon, establishing an inter-process communication (IPC) link between a first proxy interface for the user space driver daemon and a second proxy interface for a server process in a kernel space, receiving, at the first proxy interface, an access right to enable access to a memory buffer in the kernel space, and relaying an access request for the memory buffer from the user space driver daemon via a third-party proxy interface to enable the user space driver daemon to access the memory buffer, the access request based on the access right.

Abstract: A reconfigurable processor comprises an array of processing units and an instrumentation network. The array of processing units is configured to execute runtime events to execute an application. The instrumentation network is operatively coupled to the array of processing units. The instrumentation network comprises a control bus configured to form control signal routes in the instrumentation network. The instrumentation network further comprises a plurality of instrumentation counters having inputs and outputs connected to the control bus and to the processing units. Instrumentation counters in the plurality instrumentation units are configurable to consume control signals on the inputs and produce counts of the runtime events on the outputs.

Abstract: A processor for sparse matrix calculation includes an on-chip memory, a cache, a gather/scatter engine, and a core. The on-chip memory stores a first matrix or vector, and the cache stores a compressed sparse second matrix data structure. The compressed sparse second matrix data structure includes a value array including non-zero element values of the sparse second matrix, where each entry includes a given number of element values; and a column index array where each entry includes the given number of offsets matching the value array. The gather/scatter engine gathers element values of the first matrix or vector using the column index array of the sparse second matrix. In a hybrid horizontal/vertical implementation, the gather/scatter engine gathers sets of element values from sets of rows and from different sub-banks within the same rows based on the column index array of the sparse matrix.

Abstract: A method, computer program product, and computing system for defining a queue. The queue may be based on a linked list and may be a first-in, first-out (FIFO) queue that may be configured to be use used with multiple producers and a single consumer. The queue may include a plurality of queue elements. A tail element and a head element may be defined from the plurality of elements within the queue. The tail element may point to a last element of the plurality of elements and the head element may point to a first element of a plurality of elements. An element may be dequeued from the tail element, which may include determining if the tail element is in a null state. An element may be enqueued to the head element, which may include adding a new element to the queue.