Abstract: Techniques for a firewall to determine access to a portion of memory are provided. In one aspect, an access request to access a portion of memory within a pool of shared memory may be received at a firewall. The firewall may determine whether the access request to access the portion of memory is allowed. The access request may be allowed to proceed based on the determination. The operation of the firewall may not utilize address translation.

Abstract: Glass-as-a-Platform (GaaP) assemblies are provided. Embodiments of the GaaP assembly comprise a first glass plate and a second glass plate, each disposed under one or more switch ASICs and one or more opto-electronic devices co-packaged on the same substrate. Each glass plate includes a plurality of waveguides. The co-packaged substrate is disposed on top of one or more of the first glass plate and second glass plate, the first glass plate configured to couple to one or more opto-electronic devices and the second glass plate configured to couple to one or more other opto-electronic devices. A faceplate interface end of each glass plate is configured to connect to one or more optical cable connectors. The glass plates are configured to route optical signals to and from one or more opto-electronic devices and one or more optical cable connectors through the one or more waveguides and openings in the co-packaged substrate.

Abstract: Methods and systems for providing vendor agnostic captive portal authentication in a network that includes a plurality of network access devices are provided. For instance, one method includes receiving a redirect request for a communication between a first user-terminal and a first network access device, the redirect request including at least one of a vendor-specific item of information of the first network access device and an Internet Protocol (IP) address of the first network access device. The method further includes comparing the at least one of the vendor-specific item of information of the first network access device and the IP address of the first network access device against each of a plurality of entries of a network access device database, and providing the first user-terminal access to a captive portal page in response to an appropriate match.

Abstract: Examples include an optical device for redirecting optical signals. The optical device includes a plurality of input ports, a plurality of optical blocks such that at least one optical block of the plurality of optical blocks aligned to each input port of the plurality of input ports, and a plurality of output ports. The plurality of input ports may direct a plurality of optical signals of selective wavelengths to a first direction. Each of the optical blocks may be movable to a plurality of positions to selectively redirect the respective optical signal of the plurality of signals from the first direction to a second direction to one or more output ports of the plurality of output ports that may receive the one or more optical signals redirected to the second direction.

Abstract: A technique includes holding a bus interface of a removable device that is inserted into a connector of a computer system in a state to prevent the device from communicating with a communication link. The communication link is coupled to the connector and is associated with operating system access to the device. The method includes a baseboard management controller communicating with the device using a channel other than the communication link while the bus interface of the device is held in the state; the baseboard management controller performing a security operation corresponding to the device based on the communication with the device using the channel; and the baseboard management controller releasing the bus interface of the device from the state to allow the device to communicate with the communication link in response to the baseboard management controller completing the security operation.

Abstract: A self-learning rate access prioritizer for high-priority applications in a wireless network is provided herein. The self-learning rate access prioritizer includes a method of assigning an application rate limiter for each high-priority network software application. The method further includes employing an assigned application rate limiter to determine the present bandwidth for a first high-priority network software application. Next, the method includes re-provisioning bandwidth to the first high-priority network software application in response to a ratio of a first bandwidth of the first high-priority network software application and a provisioned bandwidth for the first high-priority network software application. Furthermore, the method includes re-provisioning bandwidth from the first high-priority network software application in response to the ratio being less than a low utilization ratio assigned to the first high-priority network software application.

Abstract: Systems are provided for implementing a hybrid resistor-memristor crossbar array, which allows for flexible conductance to be used in implementing the weight matrix of a neural network. The hybrid resistor-memristor crossbar array may include resistor crossbars, each resistor having a static conductance value. The hybrid resistor-memristor crossbar array may also have a memristor coupled to an output line associated with the resistor crossbar array, wherein the memristor has a variable conductance value, and further wherein the static conductance values and the variable conductance value are set to calculate a matrix-vector multiplication associated with a weight matrix of a neural network. An expected range of coefficients for a weight matrix of a neural network can be given by the Discrete Transform Cosine (DCT). Accordingly, the static conductance values of the resistors in the resistors crossbar array are set to values equal to known coefficients of the DCT.

Abstract: A faceplate optical sub-assembly is provided for accommodating a plurality of optical receptacles mounted in a faceplate of a computing device. The faceplate optical sub-assembly accommodates one or more optical receptacle housings having optically-connected front and rear optical bays. A collar having a single aperture surrounds the one or more optical bays, and a shell structure comprised of a pair of interlocking sub-shells engages on the rear of the collar. A gasket is disposed between the collar and the shell structure. The collar, gasket, and shell structure provide electromagnetic interference (EMI) shielding for optical connections made between optical fibers inserted in the front and rear optical bays, and rigidly engage the plurality of optical receptacle housings. The single aperture of the collar and the multi-part shell structure allows for insertion of a fiber jumper assembly into the rear bays of the faceplate optical sub-assembly prior to insertion into a faceplate of a computing device.

Abstract: Systems and methods for an optical ternary content addressable memory (TCAM) are provided. The optical TCAM implements a time-division multiplexing (TDM) based encoding scheme to encode each bit position of a search word in the time domain. Each bit position is associated with at least two time slots. The encoded optical signal comprising the search word is routed through one or more modulators configured to represent a respective TCAM stored word. If a mismatch between at least one bit position of the search word and at least one TCAM stored word occurs, a photodetector or photodetector array will detect light.

Abstract: Examples herein relate to optoelectronic systems or modules. In particular, implementations herein relate to an optoelectronic module or system that includes a substrate having opposing first and second sides and an optoelectronic component having opposing first and second sides flip chip assembled to the substrate. The optoelectronic component is configured to emit at least one optical signal to the substrate, receive at least one optical signal from the substrate, or both. The optoelectronic system further includes an underfill exclusion structure configured to prevent underfill material dispensed between the optoelectronic component and the substrate from flowing into an optical area or path of the at least one optical signal transmitted between the optoelectronic component and the substrate. The underfill exclusion structure is spaced apart from at least one of the optoelectronic component or the substrate.

Abstract: Processes and apparatuses described herein provide for an efficient cyclical fiber-optic connection between a source component and multiple destination components in a computing environment. A comb laser generates a laser signal that includes laser light of a first frequency that is red-shifted from a carrier frequency. The comb laser concurrently transmits the laser signal to four ring resonators via an optical waveguide. Three of the ring resonators are initially configured for optical resonance at a second frequency that is blue-shifted from the carrier frequency, while one of the ring resonators is initially configured for optical resonance at the first frequency. The laser signal is modulated to communicate data to a first target location associated with the ring resonator that is initially configured for optical resonance at the first frequency.

Abstract: A method for evaluating an electronic design under test may be performed in an environment that includes a functional verification test bench having at least one verification component coupled to the electronic design under test. The method includes provisioning the functional verification test bench to provide protocol-agnostic performance data for activity of the electronic design under test during functional verification testing of the electronic design under test. The method further includes capturing at least a part of the protocol-agnostic performance data from the at least one verification component, and calculating, from the protocol-agnostic performance data, a performance measurement for the electronic design under test.

Abstract: Example implementations relate to a method and system for pumping fluid with a pump assembly to cool waste-heat producing system of an apparatus. The pump assembly includes a first housing, a rotor assembly, a stator assembly, a second housing, an outlet connection port coupled to the second housing, and a guide vane insert. The first housing includes a first bore and first inlet guide vanes (IGVs) coupled to inlet of the first bore. The rotor assembly including an impeller, is disposed in the first bore. The stator assembly including a coil, is mounted around a portion of the first housing. The second housing has a second bore fluidically coupled to the first bore, and first outlet guide vanes (OGVs) coupled at an entrance of the second bore. The guide vane insert including second OGVs, is disposed within the outlet connection port and fluidically coupled to outlet of the second bore.

Abstract: One embodiment can provide a sampler for a decision feedback equalizer (DFE). The sampler can include a comparator comprising a resolver and a plurality of amplifiers coupled to the resolver. The plurality of amplifiers are to receive an input signal and one or more feedback signals, and the plurality of amplifiers are coupled to each other in parallel, thereby facilitating a summation of the input signal and the one or more feedback signals. The comparator is to generate an output based on the summation of the input signals and the one or more feedback signals. The sampler can further include an inverter to invert the output of the comparator. The inverted output of the inverter is sent to a tap-1 amplifier to generate a tap-1 feedback signal to be sent to the comparator at a next unit interval (UI).

Abstract: In embodiments described herein, a chatbot is provided for engaging in a chatbot session with one or more computing devices. The chatbot session can be for providing technical support to or for a system or device. Data is collected from networking devices such as access points and, in turn, processed to obtain context data. The context data that is relevant to a chatbot session is provided to the chatbot and, in turn, the chatbot customizes its communications based on the context data.

Abstract: A component group table in a receiving node of a computer network stores access permission information for enabling the receiving node to validate an access request issued by a requesting node. An incoming access request at a receiving node includes a subnet ID/component ID (“SID/CID”) tuple. The receiving node selectively computes a component group table address for the requesting node according to an address mapping function determined by the value of at least one predetermined bit within the SID/CID tuple of the incoming access request. Using at least one bit in the SID/CID tuple enables the establishment of at least two address mapping regions in the component group table, such as separate regions for storage nodes and compute nodes in the network.

Abstract: Enhanced spatial reuse of radio spectrum in WLAN operation is described. An example of a storage medium includes instructions for connecting with multiple client devices at an access point in a basic service set (BSS) for transmission over a channel in a network environment; estimating a communication quality value for each of the client devices based at least in part on received signal strength values at the access point and at the client device; prioritizing spatial reuse operation based on the estimated communication quality values for the client devices; establishing a clear channel assessment (CCA) threshold for a spatial reuse operation in a transmission to a first client device, the first client device being selected based on an estimated communication quality value; and dynamically adjusting the CCA threshold based at least in part on success or failure of data transmission between the access point and the first client device.

Abstract: Examples herein relate to developing an orchestration plan. Examples disclose the development of a representation of a set of services wherein each service relates to other services via different types of relationships. The examples apply a set of dependency rules for each type of relationship at each service within the set of services such that the application of the set of dependency rules creates inter-service dependencies between state transitions of the set of services. Based on the creation of the inter-service dependencies, the orchestration plan is developed which includes a sequenced order of the state transitions for the set of services.

Abstract: Examples herein relate to an apparatus. In some examples, an apparatus may include a circuit to direct a power signal to at least one electrical component. The circuit may include a protection device to regulate power to the electrical component, detection circuitry to detect when the protection device has failed, and an alert handling logic to receive a signal from the detection circuitry that the protection device has failed.

Abstract: Systems and methods are provided for addressing die are inefficiencies associated with the use of redundant ternary content-addressable memory (TCAM) for facilitating error detection and correction. Only a portion of redundant TCAMs (or portions of the same TCAM) are reserved for modified coherency directory cache entries, while remaining portions are available for unmodified coherency directory cache entries. The amount of space reserved for redundant, modified coherency directory cache entries can be programmable and adaptable.