Abstract: A data processing apparatus is specified, having multiple processor devices (4), multiple interface devices (5), to which external devices (E) are respectively connectable, and having connections (8, 10) between the interface devices (5) and the processor devices (4), via which data are transportable between the interface devices (5) and the processor devices (4). In the connections (8, 10), there is provision for at least one data management device (20) for handling data flows between the interface devices (5) and the processor devices (4). The data management device (20) is in the form of a hardware component.

Abstract: A system and method for monitoring processors operating in lockstep to detect mismatches in pending pipelined instructions being executed by the processors. A lockstep monitor implemented in hardware is provided to detect the mismatches in the pending pipelined instructions executing on the lockstep processors and to initiate an auto-recovery operation at the processors if a mismatch is detected.

Abstract: An electronic device according to various embodiments of the present invention can comprise: a housing; a first universal serial bus (USB) connector exposed through a portion of the housing, and including a first port; a plurality of second ports electrically connected with the first port; a third port for providing a plurality of logical wireless sessions; and a control circuit electrically connected with the plurality of second ports and the third port. The control circuit selects one of the second ports, and can provide a communication path between one of the logical wireless sessions and the selected second port in order to perform data communication. Additional various embodiments are possible.

Abstract: Embodiments disclosed herein provide a method, an electronic device, and a computer program product for processing a computing job. The method includes determining a first dependency relationship between a plurality of computing tasks included in a to-be-processed computing job. The method further includes determining, based on the first dependency relationship and demands of the plurality of computing tasks for computing resources, a group of computing tasks for combination from the plurality of computing tasks. The method further includes combining the group of computing tasks into a target computing task. The method further includes determining, based on the first dependency relationship, a second dependency relationship between the target computing task and computing tasks that are other than the group of computing tasks in the plurality of computing tasks.

Abstract: A merge unit configured to perform merge and permutation micro-operations by multiplexing data bytes of the inputs to simultaneously produce multiple data bytes of a merge and permutation result. Particularly, the merge unit includes a bank of MUXs arranged in parallel, each corresponding to one or more different data bytes in the merge result. When the merge unit is provided with a set of inputs, each MUX multiplexes the data bytes of the set of inputs (e.g., all the data bytes of the set of inputs) to selectively output a data byte to a particular location of the destination register storing the merge result. The selection by each MUX is individually controlled by a set of merge control words which identify a data byte location in an input and identify an input from the set of inputs.

Abstract: A system includes a memory system and a processor of a first processing system including a processor core, a direct memory access controller, and a communication interface. The processor core is configured to execute a plurality of instructions to configure the direct memory access controller to trigger a transmitter interrupt upon transmitting a first synchronization message through the communication interface to a second processing system, configure the direct memory access controller to trigger a receiver interrupt upon receiving a second synchronization message from the second processing system, determine a time difference between triggering of the transmitter interrupt and the receiver interrupt, and adjust a synchronization skew of a real-time scheduler based on the time difference to tune real-time synchronization between the first processing system and the second processing system.

Abstract: An apparatus and method are described for implementing memory management in a graphics processing system. For example, one embodiment of an apparatus comprises: a first plurality of graphics processing resources to execute graphics commands and process graphics data; a first memory management unit (MMU) to communicatively couple the first plurality of graphics processing resources to a system-level MMU to access a system memory; a second plurality of graphics processing resources to execute graphics commands and process graphics data; a second MMU to communicatively couple the second plurality of graphics processing resources to the first MMU; wherein the first MMU is configured as a master MMU having a direct connection to the system-level MMU and the second MMU comprises a slave MMU configured to send memory transactions to the first MMU, the first MMU either servicing a memory transaction or sending the memory transaction to the system-level MMU on behalf of the second MMU.

Abstract: A method includes receiving at a management component of an FPGA a persona change request and issuing a request by the management component to a reconfigurable PR slot of the FPGA to change a first persona of a first circuit device of the FPGA to a second persona of a second circuit device of the FPGA. The management component, the reconfigurable PR slot, and the first and second circuit devices are configured in the FPGA core. The method includes switching by the reconfigurable PR slot the first persona to the second persona. The method includes issuing a request by the management component, a host re-enumeration of the reconfigurable PR slot, triggering by the host a re-enumeration component a re-enumeration of the reconfigurable PR slot, and exposing by the reconfigurable PR slot the second persona such that the host is reconfigured to recognize the second circuit device.

Abstract: An embodiment circuit comprises a set of input terminals configured to receive input digital signals which carry input data, a set of output terminals configured to provide output digital signals which carry output data, and computing circuitry configured to produce the output data as a function of the input data. The computing circuitry comprises a set of multiplier circuits, a set of adder-subtractor circuits, a set of accumulator circuits, and a configurable interconnect network. The configurable interconnect network is configured to selectively couple the multiplier circuits, the adder-subtractor circuits, the accumulator circuits, the input terminals and the output terminals in at least two processing configurations. In a first configuration, the computing circuitry is configured to compute the output data according to a first set of functions, and, in a second configuration, the computing circuitry is configured to compute the output data according to a different set of functions.

Abstract: The disclosure includes systems and methods for bus control. A method comprises receiving a data exchange request, wherein the data exchange request includes a data exchange tag that identifies a data exchange, splitting the data exchange into a plurality of fractional data transactions, providing one or more bus commands to a system bus, receiving, at the bus controller, one or more acceptance notifications indicating that the one or more of the plurality have been accepted by the system bus, assigning transaction identifiers (TIDs) corresponding to the one or more of the plurality of fractional data transactions, receiving one or more completion notifications indicating that the one or more of the plurality have been completed, determining that each of the plurality of fractional data transactions associated with the data exchange tag have been completed, and notifying the processor that the requested data exchange has been completed.

Abstract: A semiconductor device and an operating method thereof are provided. An operating method of a semiconductor device, includes monitoring a plurality of request packets and a plurality of response packets that are being transmitted between a master device and a slave device; detecting a target request packet that matches desired identification (ID) information from among the plurality of request packets; counting the number of events of a transaction including the target request packet by using an event counter; counting the number of request packets whose corresponding response packets are yet to be detected, from among the plurality of request packets by using a Multiple Outstanding (MO) counter; determining whether an MO count value of the MO counter is valid; and if the MO count value is invalid, resetting the event counter.

Abstract: Aspects for vector operations in neural network are described herein. The aspects may include a vector caching unit configured to store a first vector and a second vector, wherein the first vector includes one or more first elements and the second vector includes one or more second elements. The aspects may further include one or more adders and a combiner. The one or more adders may be configured to respectively add each of the first elements to a corresponding one of the second elements to generate one or more addition results. The combiner may be configured to combine a combiner configured to combine the one or more addition results into an output vector.

Abstract: An apparatus to facilitate memory barriers is disclosed. The apparatus comprises an interconnect, a device memory, a plurality of processing resources, coupled to the device memory, to execute a plurality of execution threads as memory data producers and memory data consumers to a device memory and a system memory and fence hardware to generate fence operations to enforce data ordering on memory operations issued to the device memory and a system memory coupled via the interconnect.

Abstract: An integrated circuit includes a specific pin, an output circuit, a voltage detector, and a controller. The output circuit is coupled to the specific pin. The voltage detector obtains a detection voltage value from the specific pin. In response to an alert request, the controller provides a control signal to the output circuit based on the detection voltage value, so as to selectively control the output circuit to transmit the alert signal to the specific pin. When the control signal instructs the integrated circuit to operate in a blocking mode, the output circuit blocks the alert signal from being transmitted to the specific pin. When the control signal instructs the integrated circuit to operate in a transmission mode, the output circuit transmits the alert signal to the specific pin.

Abstract: A system includes a memory system and a processor of a first processing system including a processor core, a direct memory access controller, and a communication interface. The processor core is configured to execute a plurality of instructions to configure the direct memory access controller to trigger a transmitter interrupt upon transmitting a first synchronization message through the communication interface to a second processing system, configure the direct memory access controller to trigger a receiver interrupt upon receiving a second synchronization message from the second processing system, determine a time difference between triggering of the transmitter interrupt and the receiver interrupt, and adjust a synchronization skew of a real-time scheduler based on the time difference to tune real-time synchronization between the first processing system and the second processing system.

Abstract: A data processing system 2 supporting vector processing operations uses scaling vector length querying instructions. The scaling vector length querying instructions return a result which is dependent upon a number of elements in a vector for a variable vector element size specified by the instruction and multiplied by a scaling value specified by the instruction. The scaling vector length querying instructions may be in the form of count instructions, increment instructions or decrement instructions. The instructions may include a pattern constraint applying a constraint, such as modulo(M) or power of 2 to the partial result value representing the number of vector elements provided for the register element size specified for the instruction.

Abstract: An architecture for a Field Programmable Gate Array (FPGA) that better supports the designs of finite state machines (FSMs) generated by High-Level Synthesis (HLS) tools. The architecture is based on categorizing states of a FSM into branch free path states and independent states. A memory unit stores next state information for independent states and an accumulator unit computes next state information for branch free path states. A control unit selects the next state based on either the memory unit or the accumulator unit. An input sequence encoder encodes external inputs and current state values into encoded sequence signals that are input to the memory unit. Also disclosed is a state assignment algorithm that assigns state values to states of the FSM by first identifying branch free paths that terminate on the same state and then eliminating overlap between paths. States along the same branch free path are assigned sequential values.

Abstract: A computing device, comprising at least one peripheral computing component, electrically connected to each of a plurality of hardware processors; wherein at least one of the plurality of hardware processors is adapted to executing a code for: configuring the at least one peripheral computing component to access at least one first memory location in a first memory component electrically coupled with a first hardware processor of the plurality of hardware processors via a first electrical connection between the peripheral computing component and the first hardware processor; and configuring the at least one peripheral computing component to access at least one second memory location in a second memory component electrically coupled with a second hardware processor of the plurality of hardware processors via a second electrical connection between the peripheral computing component and the second hardware processor; and wherein the first hardware processor is not the second hardware processor.

Abstract: Methods, apparatuses, devices, and storage media for performing a processing task are provided. A portion of portions of the processing task can include a group of operations that are to be performed at a processing unit of processing units. The group of operations can include operations of a first type and operations of a second type. In the method, a first queue for performing the operations of the first type and a second queue for performing the operations of the second type can be built, respectively. Based on a definition of the processing task, a dependency relationship between a group of operations to be performed at the processing unit and a group of operations to be performed at other processing units in the plurality of processing units can be obtained. Operations in the first queue and operations in the second queue can be performed respectively based on the dependency relationship.

Abstract: An electronic device includes a requester and a link interface coupled between the requester and a link. The requester is configured to send a request packet to a completer on the link via the link interface. When sending the request packet to the completer, the requester sends, to the completer via the link interface, the request packet with a tag that is not unique with respect to tags in other request packets from the requester that will be in the internal elements of the completer before the request packet is in the internal elements of the completer, but that is unique with respect to tags in other request packets from the requester that will be in the internal elements of the completer while the request packet is in the internal elements of the completer.