Abstract: System and method for aggressive credit waiting in a high performance computing environment. In accordance with an embodiment, systems and methods can provide for an indexed matrix of credit wait policies between ports within a single switch. In addition, systems and methods can provide for an array of credit wait polices at an egress port from a switch, the array being indexed by virtual lane.

Abstract: Technologies for latency based service level agreement (SLA) management in remote direct memory access (RDMA) networks include multiple compute devices in communication via a network switch. A compute device determines a service level objective (SLO) indicative of a guaranteed maximum latency for a percentage of RDMA requests of an RDMA session. The compute device receives latency data indicative of latency of an RDMA request from a host device. The compute device determines a priority associated with the RDMA request as a function of the SLO and the latency data. The compute device schedules the RDMA request based on the priority. The network switch may allocate queue resources to the RDMA request based on the priority, reclaim the queue resources after the RDMA request is scheduled, and then return the queue resources to a free pool. Other embodiments are described and claimed.

Abstract: A joint assembly includes a first member having splines formed therein. A second member includes splines formed thereon and is coupled to the first member. The splines of the first member engage the splines of the second member. An access window is formed on the first member. A ring retains the first member to the second member. A portion of the ring is accessible through the access window, where the ring can be manipulated to release the first member from the second member.

Abstract: A network endpoint receiver controls packet flow from a transmitter. Packets are received via a network in packet traffic according to a push mode, where the transmitter controls pacing of transmitting the packets. Characteristics related to the packet traffic are monitored at the receiver. The monitored characteristics are compared to reception performance parameters, and based on the comparison, a decision is made to switch from the push mode to a pull mode for controlling the packet flow. The receiver transmits a pull mode request packet to the transmitter, where the pull mode request packet indicates a pacing of subsequent packets transmitted by the transmitter to the receiver in accordance with the pull mode. Pacing of further transmitted packets may be controlled by subsequent pull mode request packets sent over time to the transmitter by the receiver. Similarly, the receiver may control additional transmitters to transmit at equal or different rates.

Abstract: A speech processing system configured to convey linked content to a user in a voice user interface (VUI) environment is described. The system may create output audio data that includes an audible indicator (e.g., a beep) that indicates to a user linked content. An audible indicator may be located at the beginning and/or end of linked content in the output audio data. The system may also output non-linked content in a first voice while outputting linked content in a second voice. The system may further overlay audio atop the linked portion of the output audio data, with the overlaid audio indicating the linked content to the user. A user may invoke linked content in output audio by speaking the linked content, or a portion thereof, back to the system. The system may then output the linked, additional content to the user.

Abstract: Examples herein relate to allocation of an intermediate queue to a flow or traffic class (or other allocation) of packets prior to transmission to a network. Various types of intermediate queues are available for selection. An intermediate queue can be shallow and have an associated throughput that attempts to meet or exceed latency guarantees for a packet flow or traffic class. Another intermediate queue is larger in size and expandable and can be used for packets that are sensitive to egress port incast such as latency sensitive packets. Yet another intermediate queue is expandable but provides no guarantee on maximum end-to-end latency and can be used for packets where dropping is to be avoided. Intermediate queues can be deallocated after a flow or traffic class ends and related memory space can be used for another intermediate queue.

Abstract: System and method for supporting scalable bitmap based P_Key table in a high performance computing environment. A method can provide, at least one subnet comprising one or more switches, a plurality of host channel adapters, and a plurality of end nodes. The method can associate the plurality of end nodes with at least one of a plurality of partitions, wherein each of the plurality of partitions are associated with a P_Key value. The method can associate each of the one or more switches with a bitmap based P_Key table of a plurality of bitmap based P_Key tables. The method can associate each of the host channel adapters with a bitmap based P_Key table of the plurality of bitmap based P_Key tables.

Abstract: Systems and methods are provided for obtaining data to be secured based on a secret sharing technique, the data being associated with a file identifier and a split specification that includes at least a number of splits n and a minimum number of splits m required for reconstructing the data, and a Repeatable Random Sequence Generator (RRSG) RRSG scheme. An RRSG state can be initialized based at least in part on a given data transformation key to provide repeatable sequence of random bytes. For every m bytes of data: a polynomial whose coefficients are determined based at least in part on m bytes of the data and a portion of the repeatable sequence of random bytes can be determined; the polynomial can be evaluated at n unique values determined by a portion of repeatable sequence of random bytes to generate n bytes. Each byte can be stored into one of the n split stores.

Abstract: A barcoded end facet printed photonic chip includes: an optically transparent direct laser writing substrate including a transverse waveguide writing surface to receive a direct write laser light for off-axis direct write laser printing and a facet surface to receive the direct write laser light for on-axis direct write laser printing of a barcode-guided direct laser written optical coupling on the facet surface; a waveguide disposed in the optically transparent direct laser writing substrate and in optical communication with the facet surface; and an optically visible bulk impregnated barcode disposed in the optically transparent direct laser writing substrate arranged proximate to the waveguide and in optical communication with the facet surface.

Abstract: System and method for supporting scalable bitmap based P_Key table in a high performance computing environment. A method can provide, at least one subnet comprising one or more switches, a plurality of host channel adapters, and a plurality of end nodes. The method can associate the plurality of end nodes with at least one of a plurality of partitions, wherein each of the plurality of partitions are associated with a P_Key value. The method can associate each of the one or more switches with a bitmap based P_Key table of a plurality of bitmap based P_Key tables. The method can associate each of the host channel adapters with a bitmap based P_Key table of the plurality of bitmap based P_Key tables.

Abstract: System and method for using multiple global identification subnet prefix values in a network switch environment in a high performance computing environment. A packet is received from a network fabric by a first Host Channel Adapter (HCA). The packet has a header portion including a destination subnet prefix identifying a destination subnet of the network fabric. The network HCA is allowed to receive the first packet from a port of the network HCA by selectively determining a logical state of a flag and, selectively in accordance with a predetermined logical state of the flag, ignoring the destination subnet prefix identifying the destination subnet of the network fabric.

Abstract: System and method for supporting subnet number aliasing in a high performance computing environment. In accordance with an embodiment, a fabric member can be assigned, by a global fabric manager, an alias fabric local subnet number in order to keep a fabric running after a fabric reconfiguration. The alias fabric local subnet number can be assigned for a period of time, the period of time being static, configurable, or indefinite.

Abstract: An optical parametric oscillator for producing idler coherent light and signal coherent light from pump coherent light by balanced parametric dispersion includes: substrate cladding; a microring resonator disposed on the substrate cladding and including: a broadly transparent Kerr nonlinear medium including a annulus with a radius R, a height H, and a width W that provides a balanced parametric dispersion; and that: receives pump coherent light from a waveguide; and produces idler coherent light and signal coherent light from the pump coherent light, the idler coherent light and signal coherent light produced according to the balanced parametric dispersion of the microring resonator; and the waveguide disposed on the substrate cladding in optical communication with the microring resonator and comprising a broadly transparent medium such as silicon nitride and that: receives pump coherent light; and communicates the pump coherent light to the microring resonator for production of the idler coherent light and t

Abstract: System and method for using multiple global identification subnet prefix values in a network switch environment in a high performance computing environment. A packet is received from a network fabric by a first Host Channel Adapter (HCA). The packet has a header portion including a destination subnet prefix identifying a destination subnet of the network fabric. The network HCA is allowed to receive the first packet from a port of the network HCA by selectively determining a logical state of a flag and, selectively in accordance with a predetermined logical state of the flag, ignoring the destination subnet prefix identifying the destination subnet of the network fabric.

Abstract: System and method for supporting virtual machine migration in a high performance computing environment. In accordance with an embodiment, when a virtual machine migrates from a first subnet to a second subnet, a gateway port at the first subnet can, upon receiving packets addressed to the migrated virtual machine, consult a memory lookup table to discover the virtual machine's new addresses. The gateway port can update the packet accordingly. The memory lookup table can be addressed based on a GUID of the virtual machine.

Abstract: System and method for monitoring logical network traffic flows using a ternary content addressable memory (TCAM). An exemplary embodiment can provide a network port that is associated with a TCAM. The TCAM can be configured with a plurality of entries, wherein each TCAM entry contains a value. Further, each TCAM entry can be associated with at least one network counter. A predefined set of values can be retrieved from at least one header field of a data packet processed by the network port. Each value in the predefined set of values can be aggregated into a search value, and the search value can be compared to the value contained in each TCAM entry. When a match is found between the search value and the value contained in a TCAM entry, each network counter associated with the matching TCAM entry can be incremented.

Abstract: System and method for supporting shared multicast local identifiers (MLIDs) a high performance computing environment. In accordance with an embodiment, a shared MLID range can be configured such that each subnet within a fabric can utilize an MLID within a shared MLID range without the need to utilize a TCAM, or other memory, lookup of a MGID to MLID mapping.

Abstract: Examples described herein relate to a Transport Layer Security (TLS) offload engine to: based on detection of encrypted data unassociated with a previously detected data header: search for one or more data headers; identify at least two candidate data headers for validation; and based on receipt of an indication that the at least two candidate data headers are valid, perform decryption of received data in one or more packets. In some examples, the TLS offload engine is to: based on receipt of an indication that one or more of the at least two candidate data headers is not a valid header, search for two or more other candidate data headers.

Abstract: A propeller shaft assembly comprises a first rotary component having a first splined portion and a first engaging surface arranged transverse to a longitudinal axis of the first rotary component and spaced from the first splined portion and a second rotary component having a second splined portion configured to engage the first splined portion. The second splined portion defines a second engaging surface arranged transverse to the longitudinal axis of the first rotary component. A shear component is disposed between the first engaging surface of the first rotary component and the second engaging surface of the second rotary component. The shear component forms a crash feature of the propeller shaft assembly configured to shear at an edge of the second engaging surface when the first shear component is compressed between the first engaging surface and the second engaging surface.

Abstract: Technologies for managing burst bandwidth requirements are disclosed. In the illustrative embodiment, a software-defined network (SDN) controller monitors storage devices in a data center. If a storage device fails, the SDN controller manages the bandwidth used to replicate the data that was stored on the failed storage device. The SDN controller may allocate an initial amount of bandwidth based on one or more parameters of the storage device, and the SDN controller may increase the bandwidth in a series of discrete steps. In another embodiment, the SDN controller may predict a bandwidth burst based on sequential writes at a storage sled from several compute devices, and allocate bandwidth accordingly in a tiered manner.