Abstract: The application provides an apparatus and a method for procedural video assessment. The apparatus includes: interface circuitry; and processor circuitry coupled to the interface circuitry and configured to: perform an action segmentation process for a procedural video received via the interface circuitry to obtain a plurality of action features associated with the procedure video; transform the plurality of action features into a plurality of action-procedure features based on an action-procedure relationship learning module for discovering a relationship between the plurality of action features and a plurality of scoring oriented procedures associated with the procedure video; and perform a procedure classification process to infer the plurality of scoring oriented procedures from the plurality of action-procedure features.

Abstract: Multi-tile Memory Management for Detecting Cross Tile Access, Providing Multi-Tile Inference Scaling with multicasting of data via copy operation, and Providing Page Migration are disclosed herein. In one embodiment, a graphics processor for a multi-tile architecture includes a first graphics processing unit (GPU) having a memory and a memory controller, a second graphics processing unit (GPU) having a memory and a cross-GPU fabric to communicatively couple the first and second GPUs. The memory controller is configured to determine whether frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU in the multi-GPU configuration and to send a message to initiate a data transfer mechanism when frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU.

Abstract: Methods and apparatus to reduce delamination in hybrid cores are disclosed. An example hybrid core of an integrated circuit (IC) package comprises a frame, and a glass panel including a top surface, an edge adjacent the frame, and a tapered surface extending between the edge and the top surface.

Abstract: Techniques for transferring virtual machines and resource management in a virtualized computing environment are described. In one embodiment, for example, an apparatus may include at least one memory, at least one processor, and logic for transferring a virtual machine (VM), at least a portion of the logic comprised in hardware coupled to the at least one memory and the at least one processor, the logic to generate a plurality of virtualized capability registers for a virtual device (VDEV) by virtualizing a plurality of device-specific capability registers of a physical device to be virtualized by the VM, the plurality of virtualized capability registers comprising a plurality of device-specific capabilities of the physical device, determine a version of the physical device to support via a virtual machine monitor (VMM), and expose a subset of the virtualized capability registers associated with the version to the VM. Other embodiments are described and claimed.

Abstract: An apparatus comprising a network interface card (NIC), including packet processing circuitry to determine whether the NIC is to operate according to a first telemetry protection mode to prevent copying of packet data payloads for telemetry or a second telemetry protection mode to enable copying of packet payloads for telemetry.

Abstract: The disclosure relates to method and apparatus for fusing layers of different models. The method for fusing layers of different models comprises: searching layers from different models and determining whether to perform layer fusing; fusing instructions in the layers from different models into a fused instruction in response to determining to perform layer fusing; combining input data for the instructions in the layers from different models into a combined input data; allocating a continuous storage area in a memory for the combined input data; loading the combined input data for the fused instruction from the continuous storage area in the memory to perform the fused instruction; and storing output data obtained after performing the fused instruction into a continuous storage area in the memory.

Abstract: Using a fixed group of pictures (GOP) size in video encoding significantly hinders compression efficiency due to its inability to adapt to the dynamic nature of video content. While encoding leverages spatio-temporal redundancy within a GOP for compression, a predetermined size fails to capture the varying complexity of scenes. This leads to wasted bits in low-motion segments and insufficient reference frame variation for high-motion areas, resulting in visual artifacts and reduced compression efficiency. To address this limitation, a GOP size recommendation engine involving machine learning models can determine frame-level GOP size recommendations based on pre-encoder frame statistics. The frame-level GOP size recommendations are used to adapt the GOP size for encoding video frames.

Abstract: An integrated circuit package includes a substrate with an integrated circuit device mounting surface, and at least one optical fiber mount in the substrate. The optical fiber mount includes a support having at least one optical fiber mounting channel, and the optical fiber mounting channel is configured to mount at least one clad optical fiber.

Abstract: Apparatus and method for a full quantum system simulator. For example, one embodiment of a method comprises: initializing a quantum computing system simulator for simulating multiple layers of a quantum system including one or more non-quantum layers and one or more physical quantum device layers of the quantum system; simulating a first set of operations of the one or more non-quantum layers of the quantum system to generate first simulation results; simulating a second set of operations of the one or more quantum device layers of the quantum system to generate second simulation results; analyzing the first and second simulation results to provide at least one configuration recommendation for the quantum system.

Abstract: A shared networking pipeline is implemented by a network interface device and shared by a plurality of host devices. A pool of shared buffers of a network interface device correspond to one or more stages in the pipeline and are configured to allocate entries to the plurality of host devices based on the respective shares of the shared packet processing pipeline. Data is buffered associated with traffic of a first one of the plurality of host devices in a first subset of shared buffers, where the traffic is to proceed from a first stage to a second stage in the shared packet processing pipeline, and the data is associated with processing of the traffic by the second stage. Forward progress of the traffic is to be prevented from the first stage to the second stage when the first subset of entries are occupied.

Abstract: Embodiments of apparatuses, methods, and systems for unified address translation for virtualization of input/output devices are described. In an embodiment, an apparatus includes first circuitry to use at least an identifier of a device to locate a context entry and second circuitry to use at least a process address space identifier (PASID) to locate a PASID-entry. The context entry is to include at least one of a page-table pointer to a page-table translation structure and a PASID. The PASID-entry is to include at least one of a first-level page-table pointer to a first-level translation structure and a second-level page-table pointer to a second-level translation structure. The PASID is to be supplied by the device. At least one of the apparatus, the context entry, and the PASID entry is to include one or more control fields to indicate whether the first-level page-table pointer or the second-level page-table pointer is to be used.

Abstract: A method and system of host to guest (H2G) notification are disclosed. H2G is provided via an instruction. The instruction is a send user inter-processor interrupt instruction. An exemplary processor includes decoder circuitry to decode a single instruction and execute the decoded single instruction according to the at least the opcode to cause a host to guest notification from a virtual device running in a host machine on the first physical processor to a virtual device driver running on a virtual processor in a guest machine on a second physical processor.

Abstract: A flip-flop circuit includes first and second storage circuits. The flip-flop circuit is configurable to store first values of a data signal in the first storage circuit in response to rising edges of a clock signal and to store second values of the data signal in the second storage circuit in response to falling edges of the clock signal during a double edge triggered mode. The flip-flop circuit is configurable to store third values of the data signal in the first storage circuit and to output the third values from the first storage circuit in response to the clock signal during a single edge triggered mode.

Abstract: The disclosure relates to adaptive buffer management to support a dynamic tensor shape in a DNN. An apparatus for the DNN may include processor circuitry configured to: determine whether a tensor shape of an input tensor of an object in the DNN is dynamic and exists in a shape buffer pool; run the object by use of a compilation result for the object stored in the shape buffer pool when the tensor shape of the input tensor is dynamic and exists in the shape buffer pool; and invoke the compilation procedure to perform JIT compilation for the object so as to get the compilation result for the object when the tensor shape of the input tensor is dynamic and does not exist in the shape buffer pool.

Abstract: Disclosed herein are microelectronic assemblies including microelectronic components that are coupled together by direct bonding, as well as related structures and techniques. For example, in some embodiments, a microelectronic assembly may include a first microelectronic component, including an organic dielectric material; a second microelectronic component coupled to the first microelectronic component by a direct bonding region, wherein the direct bonding region includes metal contacts and a dielectric material between adjacent ones of the metal contacts, and wherein the dielectric material includes an inorganic dielectric material; and a third microelectronic component coupled to the first microelectronic component by wire bonding or solder.

Abstract: An optical interconnect component for use in transmitting light between a photonic integrated circuit and one or more optical fibres attached to an optical fibre connector ferrule is disclosed. The optical interconnect component comprises a step formed at an edge of the optical interconnect component, the step including a ledge and a facet, one or more optical beam management elements formed in a surface of the optical interconnect component, and a plurality of integrated optical waveguides. Each of two or more of the integrated optical waveguides extends from the facet so as to define a plurality of optical ports at the facet, and each of the one or more optical beam management elements is aligned with, but separated from, an end of a corresponding one of the plurality of integrated optical waveguides.

Abstract: This disclosure describes systems, methods, and devices related to performance measurements. A device may decode a service request received from a management service consumer for the 5G system (5GS), wherein the service request may be associated with a performance measurement collection service to be delivered by the service producer to the service consumer related to a network exposure function (NEF). The device may detect performance measurements data received from the NEF. The device may decode from the performance measurements data a measurement label associated with the performance measurements data based on the service request. The device may encode a service response based on the performance measurements data received from the NEF.

Abstract: Embodiments for a matrix transpose and multiply operation are disclosed. In an embodiment, a processor includes a decoder and execution circuitry. The decoder is to decode an instruction having a format including an opcode field to specify an opcode, a first destination operand field to specify a destination matrix location, a first source operand field to specify a first source matrix location, and a second source operand field to specify a second source matrix location. The execution circuitry is to, in response to the decoded instruction, transpose the first source matrix to generate a transposed first source matrix, perform a matrix multiplication using the transposed first source matrix and the second source matrix to generate a result, and store the result in a destination matrix location.

Abstract: Described herein is a network and renderer aware split rendering technique that enables a cloud gaming service to split execution of cloud gaming workloads between a graphics processor of a cloud gaming server and a graphics processor of a client of the cloud gaming service. The split rendering technique enables portions of a frame that most vulnerable to quality degradation at low bitrates to be rendered on the client, which results in an improvement of the quality of the final frame that is presented at the client device.

Abstract: Technologies for a unified debug and test architecture in chiplets is disclosed. In an illustrative embodiment, several chiplets are integrated on an integrated circuit package. The chiplets are connected by a package interconnect, such as a universal chiplet interconnect express (UCIe) interconnect. Each chiplet includes several debug nodes, which are connected by an on-chiplet network. One of the chiplets, referred to as a package debug endpoint, acts as a link endpoint for an off-package link, such as a peripheral component interconnect express (PCIe) link. In use, debug messages can be sent to the package debug endpoint over a PCIe link. The debug messages can be routed within the chiplets and between chiplets, allowing for the debug functionality at each debug node to be probed using a common protocol. In this manner, chiplets from different vendors can be integrated into the same package and tested using common software.

Abstract: An integrated circuit device comprising a varactor comprising a first conductive contact; a second conductive contact; and a thin film transistor (TFT) channel material coupled between the first conductive contact and the second conductive contact.

Abstract: An integrated circuit device comprising a resistor formed on a non-crystalline substrate, the resistor comprising a gate electrode; a gate dielectric in contact with the gate electrode; a source electrode and a drain electrode; and a thin film transistor TFT channel material coupled between the source electrode and the drain electrode.

Abstract: In one embodiment, an integrated circuit package includes an integrated heat spreader (IHS) that incorporates a Peltier element. The IHS may include one or more Peltier elements, which may be in a top portion of the IHS. The Peltier element(s) may be electrically connected to the package substrate through a trace on a sidewall of the IHS.

Abstract: An electronic device and associated methods are disclosed. In one example, the electronic device includes plurality of metal-insulator-metal capacitor units and a control circuit to dynamically select different amounts of the plurality of metal-insulator-metal capacitor units in correlation to a type of operation in a semiconductor die.

Abstract: Microelectronic integrated circuit package structures include a die having a dielectric die edge sidewall and a bulk silicon die edge sidewall, where the bulk silicon die edge sidewall is in substantial alignment with the dielectric die edge sidewall. The bulk silicon die edge sidewall has a plurality of scallop structures along a vertical distance of the bulk silicon die edge sidewall.

Abstract: This disclosure describes systems, methods, and devices related to non-trigger based (non-TB) sensing. A device may initiate sensing measurements by sending a sensing null data packet announcement (NDPA) frame to an access point (AP) responder. The device may send one or more first null data packet (NDP) packets to the AP responder. The device may identify one or more second NDP packets received from the AP responder.

Abstract: Techniques for region-aware memory bandwidth allocation control are described. In an embodiment, an apparatus includes a processing core and control circuitry. The processing core is to execute a plurality of threads. The control circuitry is to control use of memory bandwidth per memory region and per thread.

Abstract: Devices, transistor structures, systems, and techniques are described herein related to backside contacts for field effect transistors formed using a backside contact etch prior to cavity spacer formation. A transistor includes semiconductor structures such as nanoribbons extending between a source and a drain. A spacer material is between a gate and the source/drain as cavity spacer fill. The spacer material is also between a portion of a backside contact and a portion of the source/drain, to eliminate a short between the backside contact and the gate.

Abstract: Disclosed herein are optical transceivers with multi-laser modules, as well as related optoelectronic assemblies and methods. In some embodiments, an optical transceiver may include: a first laser and a second laser, an optical output path, wherein an output of the first laser is coupled to the optical output path; and switching circuitry to decouple the output of the first laser from the optical output path and to couple an output of the second laser to the optical output path.

Abstract: In a technique of hardware thread isolation, a processor comprises a first core including a first hardware thread register. The core is to select a first key identifier stored in the first hardware thread register in response to receiving a first memory access request associated with a first hardware thread of a process. Memory controller circuitry coupled to the first core is to obtain a first encryption key associated with the first key identifier. The first key identifier may be selected from the first hardware thread register based, at least in part, on a first portion of a pointer of the first memory access request. The first key identifier selected from the first hardware thread register is to be appended to a physical address translated from a linear address at least partially included in the pointer.

Abstract: This disclosure describes systems, methods, and devices for placing bits in an isochronous data stream from a first data port to a second data port. A device may inject, using a first port, based on a periodicity less than a defined frame rate of a data stream comprising multiple frames, a status or control bit in place of one or more low-order bits, reserved bits, or unused bits of a frame of the data stream, wherein the frame includes one or more data words; receive, using a second port synchronized to the periodicity, the data stream from the first port; extract, using the second port, based on the periodicity, the status or control bit; and extract, using the second port, a remainder of the frame.

Abstract: Technologies for memory on package with reduced package thickness are disclosed. In the illustrative embodiment, a die assembly includes a substrate with a processor die mounted on the top surface and a memory die mounted on the bottom surface. The die assembly is mounted on another substrate, such as a mainboard. A cavity is defined in the mainboard, and the memory die mounted on the bottom surface of the die assembly is positioned in the cavity. Positioning the memory die on the bottom surface of the die assembly can reduce the overall thickness of the die assembly and, therefore, can reduce the overall thickness of a device that incorporates the die assembly.

Abstract: This disclosure relates matrix operation acceleration for different matrix sparsity patterns. A matrix operation accelerator may be designed to perform matrix operations more efficiently for a first matrix sparsity pattern rather than for a second matrix sparsity pattern. A matrix with the second sparsity pattern may be converted to a matrix with the first sparsity pattern and provided to the matrix operation accelerator. By rearranging the rows and/or columns of the matrix, the sparsity pattern of the matrix may be converted to a sparsity pattern that is suitable for computation with the matrix operation accelerator.

Abstract: A low-leakage oxide dielectric material with high elastic modulus is deposited directly upon an oxidizable feature with a polycyclic PE-ALD process that limits the formation of an oxide on the feature. A precursor of one or more constituents, such as silicon, may be deposited upon a workpiece during a deposition phase, and the absorbed precursor(s) may be oxidized during a first oxidation phase under more conservative conditions until a first film thickness is achieved. Subsequently, absorbed precursor(s) may be oxidized during a second oxidation phase under more aggressive conditions to arrive at a total film thickness. Transistor contact metal, which may provide local interconnection between source or drain terminals of multiple transistors, may maintain high electrical conductivity after being electrically insulated with such a low-leakage film.

Abstract: A data scaling module for USB4 that embodies display driver (DD) and connection manager (CM) operations. Periodic and aperiodic transfer requests are monitored. The periodic BW activity on periodic peripherals, such as display panels (DPs) is monitored, and determinations as to reduced periodic activity on a DP are made. Responsive to receiving a high aperiodic bandwidth request, the original refresh rate for the DP is reduced. The newly freed USB4 BW is provided for the aperiodic task. At completion of the aperiodic task, the DD increases the refresh rate to its original value.

Abstract: Multi-die packages including both photonic and electric integrated circuit (IC) die interconnected to each other through a routing structure built-up on a glass substrate. A glass preform comprising an optical waveguide may also be attached to the routing structure. A plurality of electrical IC (EIC) die may be arrayed over the routing structure along with a plurality of photonic IC (PIC). Each PIC may be coupled to an optical waveguide within the glass preform. Conductive vias may extend through the glass substrate and be further coupled with a host substrate. The host substrate may comprise glass and an optical waveguide embedded within the glass. A vertical coupler may be attached to the host substrate to optically couple the host substrate to the optical waveguide within the glass preform of the multi-die package. Many of the multi-die packages may be arrayed over a routing structure on the host substrate.

Abstract: Embodiments described herein are generally directed to detecting security issues in a hardware design using IFT. In an example, dataflows are tracked within a hardware design represented in an HDL without instrumenting the HDL. Dataflow primitives are received specifying taint sources from which the dataflows are to be tracked. A baseline simulation trace log is obtained for a baseline RTL simulation of the hardware design by causing a simulator to perform the baseline RTL simulation during which none of the taint sources are altered. Injection simulation trace logs are obtained for injection RTL simulations by causing the simulator to perform an injection RTL simulation, for each taint source, during which the taint source is altered. The dataflows are then identified based on comparisons between the baseline and the injection simulation trace logs. A potential security issue is detected within the hardware design by applying a policy to the dataflows.

Abstract: This disclosure describes systems, methods, and devices related to shifting layouts of electronic circuit vias during optical proximity corrections (OPC). A method may include identifying a first metal line, of an electronic circuit, drawn at a first position; identifying a second metal line, of the electronic circuit, drawn at a second position; identifying a via drawn at a third position extending between the first metal line and the second metal line; determining a fourth position to which the first metal line is to move from the first position; determining a fifth position to which the second metal line is to move from the second position; determining, based on the fourth position, the fifth position, a sixth position to which the via is to move from third position; and generating a layout for generating a photomask for the via at the sixth position.

Abstract: An electronic device and associated methods are disclosed. In one example, the electronic device includes an electronic package substrate including a glass core layer and a regulator circuit. A first portion of the circuit components of the regulator circuit is embedded in the glass core layer and a second portion of the circuit components of the regulator circuit is formed on a surface of the glass core layer.

Abstract: One or more transistors may have gate structures with differing sidewall slopes. The gate structures may be over stacks of channel regions in nanosheets (or nanoribbons or nanowires), and the differing gate profiles may correspond to differing electrical characteristics. Transistors with metal gate structures may be tuned by strategically etching the gate structures, for example, using lower etch powers, higher etch temperatures, and/or longer etch durations, to achieve substantially vertical gate profiles.

Abstract: Systems, apparatuses and methods include technology that identifies a model update that originates from a plurality of IoT devices. The technology determines votes from the plurality of IoT devices, where the votes indicate whether the model update will be deployed. The technology deploys the model update to the plurality of IoT devices based on the votes.

Abstract: Technologies for device management in metaverse interactions are disclosed. In an illustrative embodiment, a compute device is connected to remote compute devices in a metaverse. The compute device may detect local devices, such as by seeing a device in images captured by a camera of the compute device. The local device may be, e.g., a cell phone or smartwatch. The local devices may be registered by the compute device and reproduced in the metaverse. The local user of the compute device may interface with the local devices in the metaverse. The local user may allow remote users to interface or control the local device as well.

Abstract: A system that includes at least one memory and circuitry coupled to the at least one memory, wherein the circuitry is to access media from the at least one memory, wherein the circuitry is to: select one or more settings to apply to encode the video based on a cost of signaling applicable settings.

Abstract: Microelectronic assemblies, related devices and methods, are disclosed herein. In some embodiments, a microelectronic assembly may include a photonic integrated circuit (PIC) having a first surface having a channel and a first magnetic material; a fiber connector including a second surface with a second magnetic material; and a fiber physically coupled to the second surface of the fiber connector by an adhesive material; wherein the first surface of the PIC is coupled to the second surface of the fiber connector by the first and second magnetic materials with the fiber positioned in the channel.

Abstract: An apparatus comprising a source or drain of a field effect transistor (FET), a first dielectric between a portion of the source or drain and a FET gate, the first dielectric comprising silicon nitride, and a second dielectric above at least a portion of the first dielectric, the second dielectric comprising silicon oxide doped with at least one of oxygen or carbon, the second dielectric having a dielectric constant lower than the first dielectric.

Abstract: An electronic substrate may be fabricated by forming a base substrate and forming an inductor extending through the base substrate, wherein the inductor includes a magnetic material layer and a barrier layer, such that the barrier layer prevents the magnetic material layer from leaching into plating solutions during the fabrication of the electronic substrate. In one embodiment, the barrier material may comprise titanium. In another embodiment, the barrier layer may comprise a polymeric material. In still another embodiment, the barrier layer may comprise a nitride material layer. The inductor may further include a plating seed layer on the barrier layer and a conductive fill material abutting the plating seed layer.

Abstract: Technologies for optical coupling to photonic integrated circuit (PIC) dies are disclosed. In one illustrative embodiment, a PIC die has one or more waveguides. A lens array is positioned adjacent the PIC die. Light from waveguides of the PIC die reflects off of a reflective surface of the lens array. The reflective surface directs the light from the PIC die towards lenses in the lens array. The lenses collimate the light, facilitating coupling of light to and from other components. The reflective surface on the lens array may be oriented at any suitable angle, resulting in a collimated beam of light that is oriented at any suitable angle.

Abstract: This disclosure describes systems, methods, and devices related to performance measurements. A device may decode a management service (MnS) service request received from an MnS consumer for the 5G system (5GS), wherein the service request is associated with a performance measurement collection service to be delivered by the service producer to the consumer related to a location management function (LMF). The device may detect performance measurements data received from the LMF. The device may decode from the performance measurements data a measurement label associated with the performance measurements data based on the MnS service. The device may encode a service response based on the performance measurements data received from the PCF.

Abstract: In one embodiment, an interconnect bridge circuitry includes a first set of bridge-to-die electrical connectors in a first region of the circuitry, a second set of bridge-to-die electrical connectors in a second region of the circuitry, and an interconnection between a bridge-to-die connector of the first set and a bridge-to-die connector of the second set. The interconnection is in a third region of the circuitry between the first region and the second region, and includes a first trace connected to the bridge-to-die electrical connector of the first set, a second trace connected to the bridge-to-die electrical connector of the second set, the second trace parallel with the first trace, and a third trace connected between the first trace and the second trace.

Abstract: Thermal dissipation and grounding of integrated circuit (IC) devices with backside power delivery networks are discussed. An IC device layer between frontside and backside interconnect sections, composed mostly of an insulating material, is coupled to a crystalline heat spreader or a metal thermal ground layer by an array of thermal pillars extending through the insulating material. The crystalline heat spreader layer may include one or more thermal sensors, such as thermal sensing diodes, also coupled to the IC device layer by one or more thermal pillars. The IC device layer and crystalline layers are coupled by a hybrid bond, which forms the thermal pillars through a continuous section of the insulating material.