Abstract: A method of operating a processing unit includes storing a first copy of a first interrupt control value in a cache device of the processing unit, receiving from an interrupt controller a first interrupt message transmitted via an interconnect fabric, where the first interrupt message includes a second copy of the first interrupt control value, and if the first copy matches the second copy, servicing an interrupt specified in the first interrupt message.

Abstract: A system and method of implementing a wait state for a plurality of threads executing on a computer processor core of the processor. The processor is configured to execute instruction streams by the plurality of threads, wherein the plurality of threads includes a first thread and a set of remaining threads and determine that the first thread has entered a first wait state loop. The processor is also configured to determine that any of the set of remaining threads has not entered a corresponding wait state loop and remain by the first thread in the first wait state loop until each of the set of remaining threads has entered the corresponding wait state loop.

Abstract: Access control is provided for peer-to-peer communication between a source peripheral device and a destination peripheral device without going through a host device. The access control mechanism can allow or block a request for a transaction to go out via a port of the source peripheral device to the destination peripheral device by comparing an attribute associated with the transaction with a filter attribute stored in memory. Embodiments of the disclosed technologies can allow programming of different filter attributes for different tenants in a multi-tenant environment.

Abstract: A network-on-chip (NoC) system includes a default communication path between a master device and a slave device, and a backup communication path between the master device and the slave device. The default communication path is configured to work in a normal operation state of the chip. The backup communication path is configured to replace the default communication path when a fault arises in the default communication path.

Abstract: Computing apparatus includes a central processing unit (CPU), which is configured to run concurrently multiple virtual machines, including at least first and second virtual machines. A peripheral component bus is connected to communicate with the CPU. Multiple peripheral devices are connected to communicate via the bus with the CPU and with others of the peripheral devices, including at least first and second peripheral devices that are each respectively partitioned into at least first and second functional entities, which are respectively assigned to serve the at least first and second virtual machines. Access control logic is configured to forward peer-to-peer communications initiated by the functional entities between the peripheral devices over the bus while inhibiting access in the peer-to-peer communications between the functional entities that are assigned to different ones of the virtual machines.

Abstract: Embodiments of the present invention disclose a data processing apparatus. Output ends of an input switching module in the apparatus are respectively connected to input ends of buffer units included in a buffer module; a control end of a write arbiter is connected to a control end of the input switching module. Input ends of an output switching module are respectively connected to output ends of the buffer units; Output ends of the output switching module are respectively connected to input ends of a rearranger; a control end of a read arbiter is connected to a control end of the output switching module; and output ends of the rearranger are respectively connected to output ends of the data processing apparatus.

Abstract: An apparatus includes multiple data sources and arbitration circuitry. The data sources are configured to send to a common destination data items and respective arbitration requests, such that the data items are sent to the destination regardless of receiving any indication that the data items were served to the destination in response to the respective arbitration requests. The arbitration circuitry is configured to receive and buffer the data items, to perform arbitration on the buffered data items responsively to the arbitration requests, and to serve the buffered data items to the destination in accordance with the arbitration.

Abstract: In a method of power control for a system-on-chip, output of at least one of a first wakeup request signal and a second wakeup request signal is controlled such that a time interval between the output of the first wakeup request signal and the output of the second wakeup request signal is greater than or equal to a time interval threshold. The first wakeup request signal and the second wakeup request signal are one of concurrent and consecutive wakeup request signals.

Abstract: An arbitration circuit includes a use frequency setting block that sets a setting value for limiting a bus use frequency for each of a plurality of masters. A use request management section holds the bus use request from each of the plurality of masters and selects a use request that has not been granted from among the held use requests. A use frequency limitation block limits the use request selected by the use request management section such that the bus use frequency of each of the plurality of masters will not exceed its setting value. A use request grant block grants a use request of any one of the plurality of masters from among use requests not limited by the use frequency limitation block received from the plurality of masters.

Abstract: In one embodiment, a latency value is determined for an input/output IO request in a host computer of a plurality of host computers based on an amount of time the IO request spent in the host computer's issue queue. The issue queue of the host computer is used to transmit IO requests to a storage system shared by the plurality of host computers. The method determines a host specific value assigned to the host computer based in proportion on a number of shares assigned to the host in a quality of service policy for IO requests. The size for the host computer's issue queue is determined based on the latency value and the host specific value to control a number of IO requests that are added to the host computer's issue queue where other hosts in the plurality of hosts independently determine respective sizes for respective issue queues.

Abstract: A content delivery system comprises at least one content server that servers a number of client requests. The content server uses a Threshold-Based Normalized Rate Earliest Delivery First (TB-NREDF) scheduler. The TB-NREDF scheduler imposes a threshold value, or limit, on the number of rescheduling requests.

Abstract: The computer system of the present invention has a plurality of SAS target devices, an SAS initiator device, and a service delivery subsystem that is connected to each SAS target device by means of a physical link that is physical wiring and connected to the SAS initiator device by means of a wide link constituted by a plurality of physical links. The SAS initiator device controls how many physical links in the wide link are allocated to a particular SAS target device, whereby access from the SAS initiator device to the SAS target device is made via a physical link that is allocated to the SAS target device and is not made via a physical link that is not allocated to the SAS target device.

Abstract: In a nuclear process control system, a priority logic module (PLM) is provided. The priority logic module comprises a plurality of input ports, each input port associated with one of a plurality of priorities, a plurality of output ports, and a test mode select port associated with a test mode select signal. The test mode select signal selects one of a normal mode or test mode, each mode being associated with matching signals received by the input ports to signals sent by the output ports. The priority logic module further comprises a configurable priority logic circuit, wherein the priority logic circuit maps one of the input ports to one of the output ports.

Abstract: Provided is an arbitration circuit included in a host controller that can be connected to a plurality of external devices via a plurality of pipe control circuits. The arbitration circuit includes an available state information storage unit that stores available state information. The available state information indicates an available state of the plurality of pipe control circuits and is updated by the pipe control circuit by a unit of data transfer of a predetermined communication size. The arbitration circuit further includes an arbitration unit that refers to the available state information storage unit, selects the arbitrary pipe control circuit from the available pipe control circuit, and allocates the selected pipe control circuit to the external device, while updating the available state information storage unit.

Abstract: The computer system of the present invention has a plurality of SAS target devices, an SAS initiator device, and a service delivery subsystem that is connected to each SAS target device by means of a physical link that is physical wiring and connected to the SAS initiator device by means of a wide link constituted by a plurality of physical links. The SAS initiator device controls how many physical links in the wide link are allocated to a particular SAS target device, whereby access from the SAS initiator device to the SAS target device is made via a physical link that is allocated to the SAS target device and is not made via a physical link that is not allocated to the SAS target device.

Abstract: When selecting one command within a processor from a plurality of command queues vested with order of priority, the order of priority assigned to the plurality of command queues is dynamically changed so as to select a command, on a priority basis, from a command queue vested with a higher priority from among the plurality of command queues in accordance with the post-change order of priority.

Abstract: A method and system for controlling transmission and execution of commands in an integrated circuit (IC) device provide transmission of commands and acknowledgements in an order of their priorities. Priority levels of the commands and acknowledgements are defined based on pre-assigned levels of precedence of the respective master and slave devices. In one application, the invention is used to increase performance of IC devices employing an Advanced eXtensible Interface (AXI).

Abstract: Quality-of-Service (QoS) is an important system-level requirement in the design and implementation of on-chip networks. QoS requirements can be implemented in an on-chip-interconnect by providing for at least two signals indicating priority at a transaction-level interface where one signal transfers information in-band with the transaction and the other signal transfers information out-of-band with the transaction. The signals can be processed by the on-chip-interconnect to deliver the required QoS. In addition, the disclosed embodiments can be extended to a Network-on-Chip (NoC).

Abstract: A priority determining method and apparatus can reduce a total waiting time of DMA request blocks by granting priority to each of Direct Memory Access (DMA) request blocks transmitting a DMA request signal, based on Data Transfer Amounts (DTAs) of the DMA request blocks and Arrival Times (ATs) of the DMA request signals, counting the number of priority changes of each of DMA request blocks whose priority is changed in the priority granting process, and if a DMA request signal is received from a new DMA request block, determining priorities of the DMA request blocks based on the counted the number of priority changes.

Abstract: A method and system for bus arbitration to be used in a system having a plurality of data handling units (110a, . . . , 110d) and a shared bus (140) with a plurality of data-lines. The invention provides a method and an system to carry out the method, having steps of; receiving data transfer requests from the data handling units; selecting a set of data transfer requests the allowance of which serves a maximum number of data handling units and utilizes a maximum number of data-lines, and; allowing the data handling units that issued said selected set of data transfer requests to access said bus in a single bus cycle.

Abstract: The computer system of the present invention has a plurality of SAS target devices, an SAS initiator device, and a service delivery subsystem that is connected to each SAS target device by means of a physical link that is physical wiring and connected to the SAS initiator device by means of a wide link constituted by a plurality of physical links. The SAS initiator device controls how many physical links in the wide link are allocated to a particular SAS target device, whereby access from the SAS initiator device to the SAS target device is made via a physical link that is allocated to the SAS target device and is not made via a physical link that is not allocated to the SAS target device.

Abstract: A method and system for bus arbitration to be used in a system having a plurality of data handling units (110a, . . . , 110d) and a shared bus (140) with a plurality of data-lines. The invention provides a method and an system to carry out the method, having steps of; receiving data transfer requests from the data handling units; selecting a set of data transfer requests the allowance of which serves a maximum number of data handling units and utilizes a maximum number of data-lines, and; allowing the data handling units that issued said selected set of data transfer requests to access said bus in a single bus cycle.

Abstract: A bus of a SoC (system on chip) includes a system arbiter for controlling not only a command arbiter but also a read information arbiter, a write data control circuit, a write complete notice arbiter and the like. A sequential table containing a series of system operations including activation processing and application processing and an operation clock information circuit or the like that becomes effective when a SoC bus region is divided by an operation clock frequency are utilized in assignment of priority of buses of the system arbiter. Thus, the information transfer efficiency of the whole system bus and the information transfer efficiency of every transfer originator can be improved.

Abstract: A system includes a master device and a plurality of slave devices. The master device initiates a bus transaction having an arbitration data field for processing by a subset of the slave devices. Each slave device of the subset arbitrates a corresponding data value for the arbitration data field via the multiple-access bus such that an extreme data value of the data values of the slave devices of the subset is transmitted via the multiple-access bus for the arbitration data field. The slave device can arbitrate its data value by providing the data value for serial transmission via a data line of the multiple-access bus and monitoring the data line. In response to determining that a bit value of the data value being provided does not match the state of the data line, the slave device terminates provision of the data value, thereby ceasing arbitration of its data value.

Abstract: A bus arbitration method for arbitrating a bus in a computer capable of executing a plurality of tasks by a plurality of devices connected to the bus is provided and includes: acquiring a task information at a timing, the information containing a priority of each of the tasks and a usage rate of each of the devices for executing each of the tasks; producing an information of a bus use condition of each of the devices on the basis of the priority and the usage rate so that that the bus is preferentially assigned to a device necessary to execute a task having high priority; and arbitrating the bus between the devices according to the information of the bus use condition.

Abstract: A method and apparatus are disclosed for performing dynamic arbitration of memory accesses by a CPU and at least one bus master interface module based on, at least in part, monitoring a CPU throttle control signal and monitoring CPU power and performance states, and making decisions based on the monitored parameters. Bus master memory access break events and memory read and write accesses are also monitored as part of the arbitration process in accordance with certain embodiments of the present invention. An arbitration (ARB) module performs the dynamic arbitration. A CPU throttle control module generates the CPU throttle control signal, indicating when the CPU is idle, and also monitors and outputs the CPU power and performance states. A memory controller (MC) module controls accesses to the memory subsystem based on, at least in part, the dynamic arbitration performed by the dynamic arbitration module.

Abstract: Method and system for arbitrating between plural arbitration requests is provided. The system includes a plurality of first stage arbiters that receive plural arbitration requests and a signal that indicates a previously granted request, wherein the first stage arbiters assert a high priority request signal if a high priority request is pending and a low priority request signal is asserted, if a low priority request is pending; a second stage arbiter that arbitrates between high priority requests, when high priority requests are pending; wherein if a high priority request is not pending, then a low priority request is granted; and a data handler module that operates in parallel with the second stage arbiter to immediately move data associated with a request that is granted at any given time.

Abstract: A method for new nodes to join a cluster in a serial sequence includes (a) a new node transmitting a first type of request to join the cluster and (b) the new node determining if it has to back off the first type of request. The new node has to back off if (1) it has received a second type of request to join the cluster from another new node, (2) it has received the first type of request with a higher sequence number from another new node, (3) it has received the first type of request with a lower node number from another new node, or (4) a member node of the cluster is in a busy state. The new node transmits the first type of request, receives the first type of request, and receives the second type of request through primary links to the new nodes and member nodes of the cluster.

Abstract: A method for arbitration grants access to an ultra high priority device if the ultra high priority device requests access. This access is limited to a selectable number of accesses. Thereafter the ultra high priority device is masked from requesting access for a selectable interval of time during which access may be granted to other devices. The number of assess and the interval of masking are preferably controlled by memory mapped data registers loaded into dedicated counters.

Abstract: A programmable logic device, in accordance with an embodiment of the present invention, may comprise a bus and a plurality of programmable masters configurable to interface the bus. A first portion of a memory may include configuration data operable to configure masters of the plurality, while a second portion of the memory may include access patterns to control when the different masters of the plurality may access the bus. An injection rate controller may control when a given master is to send data on the bus based on the access pattern associated with the master. A master controller may be operable to write the access patterns for the masters to the second portion of the configuration memory.

Abstract: A method for arbitration among a plurality of requesting devices for a shared resource in which one device is an ultra high priority device grants access to one requesting device at a time. The ultra high priority device is granted access if it requests access interrupting access by another device. The ultra high priority device is limited to a selectable number of accesses and thereafter is masked for a selectable interval. This interval permits access may by other devices. Each of the other devices is also limited to a selectable number of accesses followed by re-arbitration. The other devices can have a normal priority or a time out priority if a request hasn't been granted in a selectable amount of time.

Abstract: Provided are an arbiter capable of improving memory access efficiency in a multi-bank memory, a memory access arbitration system including the arbiter, and an arbitration method thereof, where the arbiter detects requests that are not included in a busy bank, and allows the requests corresponding to a bank receiving the largest number of pending requests priorities; and write request information generated by masters is stored in a predetermined buffer to be output as additional master request information, and provides the corresponding master with an opportunity to generate new request information.

Abstract: The information processing device comprises first and second master circuits and an arbiter for arbitrating access rights to a bus to which the master circuits are connected. The arbiter has storage units retaining information representing priorities of the access rights, and an arbitration control logical unit for arbitrating the access rights of the master circuits based on the information. When the priority of the first master circuit is higher than the priority of the second master circuit and there is no access request from the first master circuit but there is an access request from the second master circuit, the arbitration control logical unit permits access of the second master circuit, and the storage units lower the priority of the second master circuit without changing the priority of the first master circuit.

Abstract: In a method of controlling transmitting and receiving buffers of a network controller and a network controller operating under such a method, at least one request for access to a system bus from the transmitting buffer and the receiving buffer is received, and the occupancy level of data in the receiving buffer and the vacancy level of data in the transmitting buffer are determined. Access to the system bus is granted based on the determination result. Buffers in the transmitting and receiving paths are treated as a single virtual transmitting buffer and a single virtual receiving buffer, respectively. Bus priority is determined by the data occupancy level in each virtual buffer and any change in the occupancy level. Therefore, it is possible to prevent or reduce underflow of the transmitting buffer and overflow of the receiving buffer, thereby impartially arbitrating which of the buffers can access the memory.

Abstract: The present invention is to provide a bus arbitration apparatus and a bus arbitration method not reducing data transfer capability as a whole and preventing a loss of transferred data. It performs the arbitration with priority in response to properties of bus masters. It sequentially arbitrates a first hierarchy bus master of which requests are urgent, a second hierarchy bus master that requests data processing in real time, and a third hierarchy bus master that is neither a first hierarchy bus master nor a second hierarchy bus master sequentially.

Abstract: Systems and methods for controlling access by a set of agents to a resource, where the agents have corresponding priorities associated with them, and where a monitor associated with the resource controls accesses by the agents to the resource based on the priorities. One embodiment is implemented in a computer system having multiple processors that are connected to a processor bus. The processor bus includes a shaping monitor configured to control access by the processors to the bus. The shaping monitor attempts to distribute the accesses from each of the processors throughout a base period according to priorities assigned to the processors. The shaping monitor allocates slots to the processors in accordance with their relative priorities. Priorities are initially assigned according to the respective bandwidth needs of the processors, but may be modified based upon comparisons of actual to expected accesses to the bus.

Abstract: In a bus control device including an external interface, internal units, a memory interface, and an internal bus, the memory interface monitors the usage pattern of the internal bus, and in a case where the internal unit is not using the internal bus, a priority processing interval for allowing only the external interface to use the internal bus is set, thereby prohibiting the internal units from using the internal bus during the priority processing interval.

Abstract: A method of communicating between an initial device and a target device connected by a plurality of intermediate segments in a distributed arbitration system is provided. The method includes establishing an arbitration timer for a communication request by the initial device. Furthermore, use of each of the intermediate segments is arbitrated based on the arbitration timer.

Abstract: A method and apparatus are disclosed for performing dynamic arbitration of memory accesses by a CPU and at least one bus master interface module based on, at least in part, monitoring a CPU throttle control signal and monitoring CPU power and performance states, and making decisions based on the monitored parameters. Bus master memory access break events and memory read and write accesses are also monitored as part of the arbitration process in accordance with certain embodiments of the present invention. An arbitration (ARB) module performs the dynamic arbitration. A CPU throttle control module generates the CPU throttle control signal, indicating when the CPU is idle, and also monitors and outputs the CPU power and performance states. A memory controller (MC) module controls accesses to the memory subsystem based on, at least in part, the dynamic arbitration performed by the dynamic arbitration module.

Abstract: A method for new nodes to join a cluster in a serial sequence includes (a) a new node transmitting a first type of request to join the cluster and (b) the new node determining if it has to back off the first type of request. The new node has to back off if (1) it has received a second type of request to join the cluster from another new node, (2) it has received the first type of request with a higher sequence number from another new node, (3) it has received the first type of request with a lower node number from another new node, or (4) a member node of the cluster is in a busy state. The new node transmits the first type of request, receives the first type of request, and receives the second type of request through primary links to the new nodes and member nodes of the cluster.

Abstract: A method for use with a computer system includes permitting a first bus agent to access a bus during predetermined windows of time and preventing a second bus agent from accessing the bus outside of the windows. The first bus agent has a higher priority than the second bus agent. The method includes monitoring the use of the bus by the first bus agent during the window and the regulation durations of the windows are selectively regulated based on the use.

Abstract: Systems and methods are described for a load/store micropacket handling system. A method includes interconnecting a compute node with a shared memory node; translating a processor instruction into an interconnect command; transforming the interconnect command into a direct memory access interconnect command; transmitting the direct memory access interconnect command via a link medium; and performing an operation defined by the direct memory access interconnect command. An apparatus includes a computer network, including: a compute node, having: a compute node interconnect interface unit; and a compute node interconnect adapter; a link medium, coupled to the compute node; and a shared memory node, coupled to the link medium, having: a shared memory node interconnect interface unit; and a shared memory node interconnect adapter.

Abstract: An information handling system is provided which includes a dynamic interrupt router for balancing interrupt assignments among a plurality of devices requesting interrupt assignments. The system balances interrupt assignments among both fixed devices mounted on the processor board and interrupt assignments to devices situated in expansion slots. When the system is populated with a large number of devices relative to the number of available interrupts, improved interrupt sharing is desirably achieved by causing a device which generates a large number of interrupt requests to share a common interrupt with a device which generates a lower number of interrupts.

Abstract: A functional system comprises a set of functions (F) requiring access to a collective resource (RSRC). Such a system can be, for example, a data processing system comprising a plurality of processors requiring access to a collective memory. For reasons of cost it is desirable to guarantee a certain minimum access for one or more functions while a certain degree of flexibility as regards the access is maintained. For this purpose, the system comprises an interface (INT) adapted to implement an access scheme (AS) characterized by a plurality of states (S) passed through in a predetermined manner. A state (S) forms a possibility of access of a given length and defines an order of priority in accordance with which a function (F) can access the collective resource (RSRC).

Abstract: A method and system for ordering equitable access to a limited resource (such as a spinlock) by a plurality of contenders (such as processors) where each of the contenders contends for access more than one time. The method classifies one or more contenders that have failed to gain access to the limited resource after at least a predetermined number of attempts as abused contenders. The abused contenders attempt among themselves to gain access to the limited resource. The method repeats the above until all of the abused contenders have gained access to the limited resource.

Abstract: A signal communication device for use within a computer includes a set of optical fibers configured to form an optical computer bus between a set of computer sub-system elements of a computer. A set of input optical connector cards are connected to the set of optical fibers. Each of the input optical connector cards includes a transmitting dynamic bandwidth allocator responsive to an optical bus clock signal operating at a multiple of a computer system clock signal such that a set of bus time slots are available for each computer system clock signal cycle. The transmitting dynamic bandwidth allocator allows a light signal to be applied to the optical computer bus during a dynamically assigned bus time slot. In this way, the optical computer bus bandwidth can be dynamically allocated to different computer sub-system elements during a single computer system clock signal cycle.

Abstract: In a method for administration of priorities of routes in a telecommunications network, for converting priority values of various routes from an actual condition into a target condition, a request for defining its priority value is implemented for each route defined in the target condition that has one of the priority modes “EQUAL” or “INSERT” as a parameter. The requests are executed in the sequence of decreasing priority, and the priority mode “insert” is employed for the respectively first request for fixing on a given priority value. The priority mode “EQUAL” is selected for every further request for fixing on the same priority value.

Abstract: A processing system comprises: a shared system resource; a plurality of control devices, each assignable with a task having a predetermined maximum time to complete, the control devices time sharing the system resource in the process of performing their assigned tasks in accordance with a predetermined sequence; and an arbiter circuit for regulating access of said control devices to the system resource. Each control device includes a throttle circuit coupled to the arbiter circuit and individually programmable to control in cooperation with the arbiter circuit utilization of the system resource by the corresponding control device so that each control device may perform its task within the predetermined maximum completion time thereof.

Abstract: Circuits and associated methods for operation thereof for gathering real-time statistical information regarding operation of the arbiter circuit in a particular system application. The real-time statistical information so gathered is useful for off-line analysis by a system designer for determining optimal configuration and parameter values associated with operation of a particular arbiter in a specific system application. In a first exemplary preferred embodiment, a timer circuit associated with the arbiter measures a predetermined period of time during which statistical data is to be gathered. Counter circuits associated with the arbiter count the number of occurrences of events of interest to the designer during the time period measured by the timer circuit. Each counter circuit preferably senses and counts a particular event of interest to the designer.

Abstract: A system for controlling and/or regulating operational sequences in a motor vehicle having several equal-access control units for controlling and/or regulating certain functions in the motor vehicle. Control units each have a volatile memory, and a nonvolatile memory in which a loading routine is included. They are connected to one another via a time-controlled communications system.