Abstract: A system may comprise a first group of switches, each switch including a first group of inputs and outputs, and a first group of controllers, each controller being independent from one another and corresponding to a switch of the first group of switches, to selectively control the switch to connect the switch's inputs with outputs. The first group of switches and controllers may be installed in a chassis. The system may comprise a second group of switches, each switch including a second group of inputs and outputs, and a second group of controllers, each controller corresponding to a switch of the second group of switches, to selectively control the switch to connect the switch's inputs with outputs. The second group of controllers may control and connect, via a group of control links, to the first group of controllers.

Abstract: A method includes receiving a plurality of streams of data from a plurality of data sources. During a first time interval of receiving the streams of data, the method further includes dividing each of the plurality of streams into a first time-aligned data segment to produce a set of first time-aligned data segments. The method further includes generating a first data matrix from data blocks of the set of first time-aligned data segments. The method further includes encoding the first data matrix using an encoding matrix to produce a first coded matrix. The method further includes slicing the first coded matrix into a first set of encoded data slices based on the first orientation. The method further includes outputting a first set of encoded data slices of the first coded matrix.

Abstract: A method for generating a high-precision packet train includes configuring an initial packet generation flow of duration T in a network node and sending a packet to a loopback port to initiate the initial packet generation flow in the network node, where the loopback port loops packets back to the network node or recirculates packets within the network node, and where the loopback port is configured for traffic shaping that establishes a pre-determined inter-packet gap for packets output by the loopback port. The method further includes configuring a main packet generation flow having a duration t1 that commences on expiration of the duration T. Looped back packets in the network node are sent to the loopback port for the entirety of durations T and t1, while one copy of each looped back packet in the network node is sent to a network port during the duration t1.

Abstract: Data is sent from a memory buffer device to a host device over a link. An error in the data is determined. A read response cancellation signal is sent to the host device to indicate the error to the host device, where the read response cancellation signal is to be sent subsequent to the data being sent from the memory buffer device to the host device.

Abstract: Configurable user interface systems for a patient support structure are disclosed. As described a control interface comprises the capability to allow limited impact on processes deemed important when other applications and programs are run. The configurable user interface systems described herein allow for customized display of information and display options available to a user in various environments.

Abstract: A memory controller comprises a command interface to transmit a memory command to a plurality of memory devices associated with the memory controller. The memory controller also comprises an acknowledgement interface to receive an acknowledgment status packet from the plurality of memory devices over a shared acknowledgement link coupled between the memory controller and the plurality of memory devices, the acknowledgement status packet indicating whether the command was received by the plurality of memory devices. In addition, the memory controller comprises a memory controller core to decode the acknowledgment status packet to identify a portion of the acknowledgement status packet corresponding to each of the plurality of memory devices.

Abstract: In a virtualized desktop system an interfacing module is coupled to peripheral ports of a target device. The interfacing module is connected to a network. A digital user station is connected to the network. The digital user station is configured to be coupled to peripherals. The interfacing module and digital user station use respective hardware engines to communicate via said network.

Abstract: Disclosed herein are a shared memory controller and a method of controlling a shared memory. An embodiment method of controlling a shared memory includes concurrently scanning-in a plurality of read/write commands for respective transactions. Each of the plurality of read/write commands includes respective addresses and respective priorities. Additionally, each of the respective transactions is divisible into at least one beat and at least one of the respective transactions is divisible into multiple beats. The method also includes dividing the plurality of read/write commands into respective beat-level read/write commands and concurrently arbitrating the respective beat-level read/write commands according to the respective addresses and the respective priorities. Concurrently arbitrating yields respective sequences of beat-level read/write commands corresponding to the respective addresses.

Abstract: The invention sets forth an L1 cache architecture that includes a crossbar unit configured to transmit data associated with both read data requests and write data requests. Data associated with read data requests is retrieved from a cache memory and transmitted to the client subsystems. Similarly, data associated with write data requests is transmitted from the client subsystems to the cache memory. To allow for the transmission of both read and write data on the crossbar unit, an arbiter is configured to schedule the crossbar unit transmissions as well and arbitrate between data requests received from the client subsystems.

Abstract: A memory is provided that comprises a bank of non-volatile memory cells configured into a plurality of banklets. Each banklet in the plurality of banklets can be enabled separately and independently of the other banklets in the bank of non-volatile memory cells. The memory further comprises peripheral banklet circuitry, coupled to the bank of a non-volatile memory array, that is configured to enable selected subsets of bit lines within a selected banklet within the plurality of banklets. Moreover, the memory comprises banklet select circuitry, coupled to the peripheral banklet circuitry, that is configured to select data associated with a selected banklet for reading out from the banklet or writing to the banklet.

Abstract: Bus clock frequency scaling for a bus interconnect and related devices, systems, and methods are disclosed. In one embodiment, the bus interconnect comprises an interconnect network configurable to connect a master port(s) to a slave port(s). A bus interconnect clock signal clocks the interconnect network. The controller is configured to receive bandwidth information related to traffic communicated over the master port(s) and the slave port(s). The controller is further configured to scale (e.g., increase or decrease) the frequency of the bus interconnect clock signal if the bandwidth of the master port(s) and/or the slave port(s) meets respective bandwidth condition(s), and/or if the latency of the master port(s) meets a respective latency condition(s) for the master port(s). The master port(s) and/or slave port(s) can also be reconfigured in response to a change in frequency of the bus interconnect clock signal to optimize performance and conserve power.

Abstract: The present disclosure provides a memory interconnection architecture for a processor, such as a vector processor, that performs parallel operations. An example processor may include a compute array that includes processing elements; a memory that includes memory banks; and a memory interconnect network architecture that interconnects the compute array to the memory. In an example, the memory interconnect network architecture includes a switch-based interconnect network and a non-switch based interconnect network. The processor is configured to synchronously load a first data operand to each of the processing elements via the switch-based interconnect network and a second data operand to each of the processing elements via the non-switch-based interconnect network.

Abstract: Systems and methods presented herein provide for the management of link rates for connecting targets devices (e.g., storage devices) to initiators (e.g., host systems). In one embodiment, an expander includes a plurality of PHYs including a PHY having a first link rate and a PHY having a second link rate that is different than the first link rate. The expander also includes a link manager communicatively coupled to the PHYs and operable to process a connection request from an initiator for the first link rate, extract a timer from the connection request, and determine whether the first link rate is available. The link manager is also operable to start the timer when the link manager determines that the first link rate is unavailable and issue a response to the initiator to inform the initiator that the timer has started and that connection at the first link rate is delayed.

Abstract: The invention pertains to a system and method for a set of middleware components for supporting the execution of computational applications on high-performance computing platform. A specific embodiment of this invention was used to deploy a financial risk application on Blue Gene/L parallel supercomputer. The invention is relevant to any application where the input and output data are stored in external sources, such as SQL databases, where the automatic pre-staging and post-staging of the data between the external data sources and the computational platform is desirable. This middleware provides a number of core features to support these applications including for example, an automated data extraction and staging gateway, a standardized high-level job specification schema, a well-defined web services (SOAP) API for interoperability with other applications, and a secure HTML/JSP web-based interface suitable for non-expert and non-privileged users.

Abstract: A configurable bus includes a plurality of bus segments. The configurable bus also includes two or more pluralities of input/output (I/O) ports. Each bus segment is coupled to at least one of the pluralities of I/O ports. Also coupled to the bus segments is a cross-couple unit that is configurable to selectively couple any of the bus segments together.

Abstract: An apparatus and method is provided for coupling additional memory to a plurality of processors. The method may include determining the memory requirements of the plurality of processors in a system, comparing the memory requirements of the plurality of processors to an available memory assigned to each of the plurality of processors, and selecting a processor from the plurality of processors that requires additional memory capacity. The apparatus may include a plurality of processors, where the plurality of processors is coupled to a logic element. In addition, the apparatus may include an additional memory coupled to the logic element, where the logic element is adapted to select a processor from the plurality of processors to couple with the additional memory.

Abstract: An apparatus and method is provided for coupling additional memory to a plurality of processors. The method may include determining the memory requirements of the plurality of processors in a system, comparing the memory requirements of the plurality of processors to an available memory assigned to each of the plurality of processors, and selecting a processor from the plurality of processors that requires additional memory capacity. The apparatus may include a plurality of processors, where the plurality of processors is coupled to a logic element. In addition, the apparatus may include an additional memory coupled to the logic element, where the logic element is adapted to select a processor from the plurality of processors to couple with the additional memory.

Abstract: A programmable analog filter includes a crossbar array with a number of junction elements and a filter circuit being implemented within the crossbar array. At least a portion of the junction elements form reprogrammable components within the filter circuit. A method for using a programmable analog filter is also provided.

Abstract: Techniques are disclosed to implement a scheduling scheme for a crossbar scheduler that provides distributed request-grant-accept arbitration between input group arbiters and output group arbiters in a distributed switch. Input and output ports are grouped and assigned a respective arbiter. The input group arbiters communicate requests indicating a count of respective ports having data packets to be transmitted via one of the output ports. The output group arbiter attempts to accommodate the requests for each member of an input group before proceeding to a next input group.

Abstract: Methods, apparatus, and computer platforms and architectures employing many-to-many and many-to-one peripheral switches. The methods and apparatus may be implemented on computer platforms having multiple nodes, such as those employing a Non-uniform Memory Access (NUMA) architecture, wherein each node comprises a plurality of components including a processor having at least one level of memory cache and being operatively coupled to system memory and operatively coupled to a many-to-many peripheral switch that includes a plurality of downstream ports to which NICs and/or peripheral expansion slots are operatively coupled, or a many-to-one switch that enables a peripheral device to be shared by multiple nodes. During operation, packets are received at the NICs and DMA memory writes are initiated using memory write transactions identifying a destination memory address.

Abstract: Exemplary embodiments of the present invention disclose a method and system for executing data permute and data shift instructions. In a step, an exemplary embodiment encodes a control index value using the recoding logic into a 1-hot-of-n control for at least one of a plurality of datum positions in the one or more target registers. In another step, an exemplary embodiment conditions the 1-hot-of-n control by a gate-free logic configured for at least one of the plurality of datum positions in the one or more target registers for each of the data permute instructions and the at least one data shift instruction. In another step, an exemplary embodiment selects the 1-hot-of-n control or the conditioned 1-hot-of-n control based on a current instruction mode. In another step, an exemplary embodiment transforms the selected 1-hot-of-n control into a format applicable for the crossbar switch.

Abstract: A data and signal interface for controlling the transfer of data and signals between a memory array and macro function such as that of a digital signal processor (DSP) core. In one embodiment, the interface comprises a plurality of memory ports which interface with X/Y memory banks, a plurality of function ports, each with a function controller, which interface with DSP functions, a crossbar connecting the memory and function ports, and an arbitration unit for arbitrating memory access by the function ports. The memory interface advantageously allows multiple simultaneous accesses of memory banks via a plurality of macro functions, each access under the control of a parent processor instruction. A standardized protocol used for memory read/write operations is also disclosed.

Abstract: Exemplary embodiments of the present invention disclose a method and system for executing data permute and data shift instructions. In a step, an exemplary embodiment encodes a control index value using the recoding logic into a 1-hot-of-n control for at least one of a plurality of datum positions in the one or more target registers. In another step, an exemplary embodiment conditions the 1-hot-of-n control by a gate-free logic configured for at least one of the plurality of datum positions in the one or more target registers for each of the data permute instructions and the at least one data shift instruction. In another step, an exemplary embodiment selects the 1-hot-of-n control or the conditioned 1-hot-of-n control based on a current instruction mode. In another step, an exemplary embodiment transforms the selected 1-hot-of-n control into a format applicable for the crossbar switch.

Abstract: A system on a chip (SOC) includes a master module, a first swapping module, and a switch module. The master module is configured to generate a transaction request, the transaction request including an address field including an address, the address corresponding to a first slave module associated with the transaction request, and a plurality of interface select bits corresponding to a desired one of a plurality of ports of the first slave module. The first swapping module is configured to swap, in the transaction request, the plurality of interface select bits with selected bits of the address in the address field. The switch module is configured to route the transaction request to the desired one of the plurality of ports based on the address.

Abstract: A system on chip (SoC) includes a first master, a slave, a bus switch transmitting a first command of the master and a first response of the slave, and a first priority controller connected between the first master and the bus switch The first priority controller measures at least one of first bandwidth and first latency based on the first command and the first response and adjusts the priority of the first command according to at least one of the measurement results.

Abstract: A portable handheld device includes an image sensor for capturing an image; an orientation sensor for determining a rotation of the image sensor; and a system-on-chip processor having integrated on a common wafer a CPU for processing a script language, a multi-core processor for processing an image captured by the image sensor, and a common synchronization register. The multi-core processor includes multiple processing units connected in parallel by a crossbar switch. Each processing unit stores one or more synchronization bits for identifying which of the other processing units are functioning as a single process therewith. The common synchronization register contains therein synchronization bits from each of the processing units.

Abstract: A communications control system is disclosed that includes a serial communications interface and a parallel communications interface for coupling a plurality of input/output modules with a control module. The serial communications interface is configured for connecting the plurality of input/output modules to the control module in parallel to transmit information between the plurality of input/output modules and the control module, and the parallel communications interface is configured for separately connecting the plurality of input/output modules to the control module to transmit information between the plurality of input/output modules and the control module, and to transmit information between individual ones of the plurality of input/output modules. The serial communications interface may comprise a multidrop bus, and the parallel communications interface may comprise a cross switch.

Abstract: An island-based network flow processor (IB-NFP) integrated circuit includes rectangular islands disposed in rows. In one example, the configurable mesh data bus is configurable to form a command/push/pull data bus over which multiple transactions can occur simultaneously on different parts of the integrated circuit. The rectangular islands of one row are oriented in staggered relation with respect to the rectangular islands of the next row. The left and right edges of islands in a row align with left and right edges of islands two rows down in the row structure. The data bus involves multiple meshes. In each mesh, the island has a centrally located crossbar switch and six radiating half links, and half links down to functional circuitry of the island. The staggered orientation of the islands, and the structure of the half links, allows half links of adjacent islands to align with one another.

Abstract: A star coupler has the ability to distinguish signals arriving via connections according to the time slot in which they arrive and to forward these signals to at least one other connection on the basis of the connection via which the signals arrive and on the basis of the time slot. An assignment in which the star coupler once treats the bus system as a single bus system and virtually divides the bus system into two subsystems in another time slot is possible in particular.

Abstract: A bus connecting ports of a crossbar switch in a ring form is provided, and the configuration information of registers in ports is transferred between ports via the bus and updated, and thus a wiring length of the bus connecting the registers is reduced.

Abstract: A system and method embodying some aspects for communicating between nodes in a network-on-chip are provided. The system comprises a microprocessing chip and a plurality of connection paths. The microprocessing chip comprises sixteen processing nodes disposed on the chip. The plurality of connection paths are configured such that each is at most three hops away front any other node. Each node also has connection paths to at most three other nodes.

Abstract: A portable handheld device includes an image sensor for capturing an image; an orientation sensor for determining a rotation of the image sensor; and a system-on-chip processor having integrated on a common wafer a CPU for processing a script language, a multi-core processor for processing an image captured by the image sensor, and a common synchronization register. The multi-core processor includes multiple processing units connected in parallel by a crossbar switch. Each processing unit stores one or more synchronization bits for identifying which of the other processing units are functioning as a single process therewith. The common synchronization register contains therein synchronization bits from each of the processing units.

Abstract: A memory interleaving device includes a slave interface, a master interface, and a crossbar switch. The slave interface is connected with a master intellectual property through an on-chip network. The master interface is connected with a slave intellectual property. The crossbar switch connects the slave interface with the master interface. The memory interleaving device transmits requests from the master intellectual property to the slave intellectual property, receives data or responses respectively corresponding to the requests from the slave intellectual property, and transmits the data or responses to the master intellectual property in an order in which the requests are received.

Abstract: Interconnect circuitry 2 has a plurality of data source circuits 8 connected to respective input paths 4 and a plurality of data destination circuits 10 connected to respective output paths 6. Connection cells 12 provide selective connections between input paths 4 and output paths 6. Arbitration circuitry 26 provides adaptive priority arbitration between overlapping requests received at different input paths. Priority bits 16 within a matrix of priority bit 46 for each output path 10 are used to represent the priority relationships between different input paths which compete for access to that output path 10. Update operations are applied on a per row or per column basis within the matrix to implement update schemes such as least recently granted, most recently granted, round robin, reversal, swap, selective least recently granted, selective most recently granted etc.

Abstract: Systems and methods to perform a register access are described. A particular method includes receiving a data frame at a bridge element of a plurality of bridge elements in communication with a plurality of server computers. The data frame may include a register access request and may be forwarded from a controlling bridge in communication with the plurality of bridge elements. A register may be accessed and execution of the register access request may be initiated in response to receiving the data frame.

Abstract: There is provided a hardware accelerator system and method. The system and method relate to a low power scalable stream compute accelerator for general matrix multiply (GEMM). There is provided a systolic compute accelerator architecture for matrix operations. Further, the system may include an application specific engine.

Abstract: Various aspects of dynamic power reduction in a bus communication architecture are described herein as embodied in an XBAR architecture that provides flexible gating of multiple paths and repeater circuitry to allow any of a number of selected clients to communicate with any of the other interconnected clients while reducing dynamic power consumption by disabling unused repeater circuitry in the bus communication architecture.

Abstract: A microcontroller for a peripheral hub includes a plurality of host bus interface microdrivers and a corresponding plurality of host transports. A first manager client, associated with a supported peripheral device, processes messages from a first host. A host manager module routes asynchronous communications, including but not limited to HID input reports, from a client to a host via one of a plurality of supported transports via a targeted transport indicated in the communication. The host manager modules routes synchronous communications from a host to a client via a targeted transport selected from a plurality of transports.

Abstract: A data and signal interface for controlling the transfer of data and signals between a memory array and macro function such as that of a digital signal processor (DSP) core. In one embodiment, the interface comprises a plurality of memory ports which interface with X/Y memory banks, a plurality of function ports, each with a function controller, which interface with DSP functions, a crossbar connecting the memory and function ports, and an arbitration unit for arbitrating memory access by the function ports. The memory interface advantageously allows multiple simultaneous accesses of memory banks via a plurality of macro functions, each access under the control of a parent processor instruction. A standardized protocol used for memory read/write operations is also disclosed.

Abstract: According to an aspect of an embodiment, a server system includes a service processor, a plurality of system boards and a plurality of crossbar boards connecting the system boards. The service processor includes a first notifier that notifies each of the crossbar boards of a crossbar board subjected to maintenance. The crossbar boards each include a first transmitter that, when notified by the service processor that the crossbar board subjected to maintenance is another crossbar board, generates a suspension packet for suspending packet transmission to the another crossbar board and transmits the suspension packet to each of the system boards. The system boards each include a suspender that, when receiving the suspension packet from the crossbar board, suspends packet transmission to the crossbar board subjected to maintenance.

Abstract: A method, electronic device apparatus and a cable apparatus for reducing crosstalk in a signal transmitted to an electronic device through the cable apparatus are disclosed. The cable apparatus has a plurality of signal lines. The device and method may determine a relevant communication scheme, activate the relevant communication scheme by electrically coupling at least one of the plurality of signal lines of the cable apparatus correlating to the activated relevant communication scheme. At least one of the plurality of signal lines of the cable apparatus not correlating to the activated relevant communication scheme is electrically grounded.

Abstract: Methods and devices for manipulating HDMI-CEC messages transmitted over a network including at least two HDMI-CEC display devices with their associated at least two HDMI-CEC cluster trees that at least partially overlap, and enabling each of the HDMI-CEC display devices to communicate using HDMI-CEC with its associated HDMI-CEC cluster tree according to its current HDMI-CEC network view.

Abstract: Embodiments include a system and method for an interrupt controller that propagates interrupts to a subsystem in a system-on-a-chip (SOC). Interrupts are provided to an interrupt controller that controls access of interrupts to a particular subsystem in the SOC that includes multiple subsystems. Each subsystem in the SOC generates multiple interrupts to other subsystems in the SOC. The interrupt controller processes multiple interrupts and generates an interrupt output. The interrupt output is then transmitted to a particular subsystem.

Abstract: A controller designed for use with a flash memory storage module, including a crossbar switch designed to connect a plurality of internal processors with various internal resources, including a plurality of internal memories. The memories contain work lists for the processors. In one embodiment, the processors communicate by using the crossbar switch to place tasks on the work lists of other processors.

Abstract: A mechanism is described for facilitating dynamic cancellation of signal crosstalk in input/output differential channels according to one embodiment. A method of embodiments may include detecting crosstalk between a first differential signal channel pair (“differential pair”) and a second differential pair of a plurality of differential pairs at a computing system, and switching polarity relating to the first transmission links of the first differential pair to cancel out the crosstalk with the second differential pair.

Abstract: A crossbar switch device for a processor block ASIC core and a method for a flush-posted-write(s)-before-read mode thereof are described. Operation for the flush-posted-write(s)-before-read mode is set in a first processor block interface coupled to programmable logic fabric. At least one write command is sent from a transaction initiating device instantiated using the programmable logic fabric to the first processor block interface. The at least one write command is posted in the first processor block interface. At least one write command received is stored in a command queue of the crossbar switch device. A read command initiated by a microprocessor is sent to the crossbar switch device. The at least one write command has an address overlap with the read command with respect to a destination target. The read command is temporarily blocked in the crossbar switch device until a command phase of the at least one write command is completed.

Abstract: Techniques for encoding data are described herein. An example of a device in accordance with the present techniques includes a signaling module coupled to a plurality of digital inputs. The signaling module is to encode data received at the plurality of digital inputs to generate encoded data. Based on the encoded data, the signaling module can drive line voltages on a plurality of signal lines of a bus. Each one of the plurality of line voltages corresponds to a weighted sum of the data received at the plurality of digital inputs.

Abstract: Techniques for decoding encoded data are described herein. An example of a device in accordance with the present techniques includes a signaling module with a receiver, quantizer, and arithmetic circuit. The receiver receives a plurality of encoded line voltages or currents on a plurality of signal lines. The quantizer determines signal levels of each of the plurality of signal lines at a unit interval. The arithmetic circuit provides a plurality of digital output bits of the decoder based on the signal levels. Each one of the digital output bits is a mathematical combination of all of the signal levels.

Abstract: A peripheral component interconnect express (PCI-E) compatible chassis comprises a plurality of peripheral slots each configured to receive a peripheral module, a system slot configured to receive a first upstream host to control at least one of the peripheral modules and a reconfigurable switch fabric configured to allow at least one of the peripheral modules to receive a second upstream host to control other peripheral modules independent of the first upstream host.

Abstract: A memory controller connected with a storage medium via a plurality of channels is provided which includes a signal processing block including a plurality of signal processing engines; and a decoding scheduler configured to control a data path such that at least one activated signal processing engine of the plurality of signal processing engines is connected with the plurality of channels, respectively.