Abstract: Embodiments are directed to protection of communications between a trusted execution environment and a hardware accelerator utilizing enhanced end-to-end encryption and inter-context security. An embodiment of an apparatus includes one or more processors having one or more trusted execution environments (TEEs) including a first TEE to include a first trusted application; an interface with a hardware accelerator, the hardware accelerator including trusted embedded software or firmware; and a computer memory to store an untrusted kernel mode driver for the hardware accelerator, the one or more processors to establish an encrypted tunnel between the first trusted application in the first TEE and the trusted software or firmware, generate a call for a first command from the first trusted application, generate an integrity tag for the first command, and transfer command parameters for the first command and the integrity tag to the kernel mode driver to generate the first command.

Abstract: Moisture hermetic guard ring structures for semiconductor devices, related systems, and methods of fabrication are disclosed. Such devices systems, and methods include a guard ring structure laterally surrounding semiconductor devices of a device layer and metal interconnects of an interconnect layer, the guard ring structure extending through the interconnect layer, the device layer, and a bonding layer adjacent one of the interconnect layer or the device layer the bonding layer, and contacting a support substrate coupled to the bonding layer. Such devices systems, and methods may further include via structures having the same material system as the guard ring structure and also extending through the interconnect, the device, and bonding layers and contacting a support substrate.

Abstract: This disclosure describes systems, methods, and devices related to coexistence network integration. A device may transmit a beacon frame or a probe response frame containing a security element that is not a robust security network element (RSNE) element to indicate opportunistic wireless encryption (OWE) support. The device may identify a first association request frame received from a first station device (STA) comprising an RSNE element with OWE Authentication Key Management (AKM) indicating a compatibility of the first STA with OWE. The device may identify a second association request frame from a second station device (STA) indicating no compatibility with OWE. The device may generate one or more encryption keys for securing data transmission with OWE-compatible STAs. The device may transmit encrypted and unencrypted versions of groupcast data frames to the first STA and the second STA.

Abstract: Magnetoelectric magnetic tunnel junction (MEMTJ) logic devices comprise a magnetoelectric switching capacitor coupled to a pair of magnetic tunnel junctions (MTJs) by a conductive layer. The logic state of the MEMTJ is represented by the magnetization orientation of the ferromagnetic layer of the magnetoelectric capacitor, which can be switched through the application of an appropriate input voltage to the MEMTJ. The magnetization orientation of the magnetoelectric capacitor ferromagnetic layer is read out by the MTJs. The conductive layer is positioned between the capacitor and the MTJs. The MTJ ferromagnetic free layers are exchange coupled to the ferromagnetic layer of the magnetoelectric capacitor. The potential of an MTJ free layer is based on a supply voltage applied to the reference layer of the MTJ. The MTJ reference layers have a magnetization orientation that is parallel or antiparallel to the magnetization orientations of the ferromagnetic layer of the magnetoelectric capacitor.

Abstract: An integrated circuit structure includes a device layer including a first set of devices and a second set of devices. An interconnect layer is above the device layer, where the interconnect layer includes one or more conductive interconnect features within dielectric material. In an example, a first ring structure including conductive material extends within the interconnect layer, and a second ring structure including conductive material extends within the interconnect layer. In an example, the second ring structure is non-overlapping with the first ring structure. In an example, the first ring structure is above the first set of devices of the device layer, and the second ring structure is above the second set of devices of the device layer.

Abstract: Apparatus and method for non-local means filtering using a media processing block of a graphics processor. For example, one embodiment of a processor comprises: ray tracing circuitry to execute a first set of one or more commands to traverse rays through a bounding volume hierarchy (BVH) to identify BVH nodes and/or primitives intersected by the ray; shader execution circuitry to execute one or more shaders responsive to a second set of one or more commands to render a sequence of image frames based on the BVH nodes and/or primitives intersected by the ray; and a media processor comprising motion estimation circuitry to execute a third set of one or more commands to perform non-local means filtering to remove noise from the sequence of image frames based on a mean pixel value collected across the sequence of image frames.

Abstract: An apparatus for clock manager redundancy comprises a clock circuitry to manage a clock for a device; a first processing circuitry coupled to the clock circuitry to execute instructions to perform operations for a clock manager, the clock manager to receive messages with time information for a network and generate clock manager control information to adjust the clock to a network time for the network; a hardened execution environment coupled to the clock circuitry and the first processing circuitry, the hardened execution environment to comprise: a detector to monitor the clock manager and generate an alert when the detector identifies abnormal behavior of the clock manager; and a second processing circuitry to execute instructions to perform operations for a redundant clock manager, the redundant clock manager to take over operations for the clock manager in response to the alert from the detector. Other embodiments are described and claimed.

Abstract: Described herein is a technique to implement an efficient floating-point n-input sum of squares operation using faithful rounding to 1 unit in the place (ULP) instead of IEEE rounding. The resulting circuitry is useful to accelerate graphics algorithms that don't require fully IEEE compliant hardware. Multipliers that are 1ulp can be significantly smaller, faster and more power efficient than IEEE rounded multipliers.

Abstract: An apparatus comprising a memory device, a system on chip (SoC), including a central processing unit (CPU) to execute a virtual machine to retrieve data from the memory device and transmit the data to a remote input/output (I/O) device coupled to a remote computing platform as memory transaction data; and a port to transmit the memory transaction data as transaction layer packets (TLPs) and a network interface card (NIC) to receive the TLPs, including an interface to receive the TLPs and packet conversion hardware to convert the TLPs to network protocol packets and transmit the network protocol packets to the remote I/O memory device.

Abstract: Technologies for dividing work across one or more accelerator devices include a compute device. The compute device is to determine a configuration of each of multiple accelerator devices of the compute device, receive a job to be accelerated from a requester device remote from the compute device, and divide the job into multiple tasks for a parallelization of the multiple tasks among the one or more accelerator devices, as a function of a job analysis of the job and the configuration of each accelerator device. The compute engine is further to schedule the tasks to the one or more accelerator devices based on the job analysis and execute the tasks on the one or more accelerator devices for the parallelization of the multiple tasks to obtain an output of the job.

Abstract: Deep learning models, such as diffusion models, can synthesize images from noise. Diffusion models implement a complex denoising process involving many denoising operations. It can be a challenge to understand the mechanics of diffusion models. To better understand how and when structure is formed, saliency maps and concept formation intensity can be extracted from the sampling network of a diffusion model. Using the input map and the output map of a given denoising operation in a sampling network, a noise gradient map representative of the predicted noise of a given denoising operation can be determined. The noise gradient maps from the denoising operations at different indices can be combined to generate a saliency map. A concept formation intensity value can be determined from a noise gradient map. Concept formation intensity values from the denoising operations at different indices can be plotted.

Abstract: Embodiments described herein provide a technique to facilitate the synchronization of workgroups executed on multiple graphics cores of a graphics core cluster. One embodiment provides a graphics core including a cache memory and a graphics core coupled with the cache memory. The graphics core includes execution resources to execute an instruction via a plurality of hardware threads and barrier circuitry to synchronize execution of the plurality of hardware threads, wherein the barrier circuitry is configured to provide a plurality of re-usable named barriers.

Abstract: Described herein is a graphics processor comprising a system interconnect and a graphics processor cluster coupled with the system interconnect. The graphics processor cluster includes circuitry configurable to generate per-frame neural representations of a multi-view video via incremental training and transferal of weights.

Abstract: The disclosure relates to tuning configuration parameters for graphics pipeline for better user experience. A device for graphics processing, comprising: hardware engines; a graphics pipeline at least partly implemented by the hardware engines; and a tuner, coupled to the hardware engines and the graphics pipeline, the tuner to: collect statuses of the device during runtime for a previous frame; determine configuration parameters based on the collected statuses, the configuration parameters associated with three-dimensional 3D rendering, pre-processing and video encoding of the graphics pipeline; and tune the graphics pipeline with the determined configuration parameters for processing a next frame.

Abstract: This disclosure describes systems, methods, and devices related to WLAN sensing sounding. A device may identify a sensing null data packet (NDP) request frame received from a second device, the sensing NDP request frame associated with performing a wireless local area network channel sounding procedure; identify transmit parameters included in a transmit control field of the sensing NDP request frame; generate an NDP frame using the transmit parameters; and send, in response to the sensing NDP request frame, the NDP frame to the second device.

Abstract: This disclosure describes systems, methods, and devices related to traffic indications for multi-link devices (MLDs). A device may generate a first traffic indication map (TIM) with a first bitmap including a first indication that traffic is to be sent by a first access point (AP) device of the MLD to a first non-AP device of a second MLD using a first communication link The device may generate a second TIM with a second bitmap including a second indication that no traffic is to be sent by a second AP device of the MLD to a second non-AP device of the second MLD using a second communication link The device may send, using the first communication link, the beacon, the beacon including the first TIM and the second TIM. The device may send, using the first communication link, a data frame to the first non-AP device of the second MLD.

Abstract: Microelectronic assemblies, and related devices and methods, are disclosed herein. For example, in some embodiments, a microelectronic assembly may include a package substrate having a first surface and an opposing second surface, and a die secured to the package substrate, wherein the die has a first surface and an opposing second surface, the die has first conductive contacts at the first surface and second conductive contacts at the second surface, and the first conductive contacts are coupled to conductive pathways in the package substrate by first non-solder interconnects.

Abstract: Described herein is a technique for automatic program code optimization for high-level synthesis. One embodiment provides a method comprising receiving input including first program code in a high-level language; translating the first program code into an intermediate language; constructing an equality graph (e-graph) from the intermediate language; interleaving control-flow, data path, and gate-level transformations to explore equivalent hardware designs represented by the e-graph; selecting a hardware design based on a cost function; extracting a representation of a selected hardware design in the intermediate language; generating second program code in the high-level language; and performing high-level synthesis using the second program code.

Abstract: Described herein are integrated circuit devices that include semiconductor devices near the center of the device, rather than towards the top or bottom of the device. In this arrangement, heat can become trapped inside the device. Metal fill, such as copper, is formed within a portion of the device, e.g., over the semiconductor devices and any front side interconnect structures, to transfer heat away from the semiconductor devices and towards a heat spreader.

Abstract: The disclosure is directed to apparatus and methods for detection of out of position (OOP) components in a carrier tape forming machine. An apparatus includes cross track sensors coupled to the bus interface circuitry, the cross track sensors configured to detect OOP components prior to overlaying the components on the carrier tape with cover tape, optical sensors to detect the OOP components on the carrier tape after overlaying with cover tape and prior to sealing and to detect reflections from OOP components seated on the carrier tape, an amplifier coupled to the optical sensors to amplify signals generated by the optical sensors and set a range for determining whether the components are OOP, and relays to receive indications of detected OOP components, and a controller coupled to the relays to stop the carrier tape forming machine as a function of signals received by the relays.

Abstract: Thermal heat spreaders and/or an IC die with solderable thermal structures may be assembled together with a solder array thermal interconnects. A thermal heat spreader may include a non-metallic material and one or more metallized surfaces suitable for bonding to a solder alloy employed as thermal interface material between the heat spreader and an IC die. An IC die may include a metallized back-side surface similarly suitable for bonding to a thermal interconnect comprising a solder alloy. Metallization on the IC die and/or heat spreader may comprise a plurality of solderable structures. A multi-chip package may include multiple IC die having different die thickness that are accommodated by a z-height thickness variation in the thermal interconnects and/or the solderable structures of the IC die or heat spreader.

Abstract: Adjusting workload execution based on workload similarity. A processor may determine a similarity of a first workload to a second workload. The processor may adjust execution of the first workload based on execution parameters of the second workload and the similarity of the first workload to the second workload.

Abstract: Embodiments described herein provide a technique to facilitate the broadcast or multicast of asynchronous loads to shared local memory of a plurality of graphics cores within a graphics core cluster. One embodiment provides a graphics processor including a cache memory a graphics core cluster coupled with the cache memory. The graphics core cluster includes a plurality of graphics cores. The plurality of graphics cores includes a graphics core configured to receive a designation as a producer graphics core for a multicast load, read data from the cache memory; and transmit the data read from the cache memory to a consumer graphics core of the plurality of graphics cores.

Abstract: A first computing system includes a data store with a sensitive dataset. The first computing system uses a feature extraction tool to perform a statistical analysis of the dataset to generate feature description data to describe a set of features within the dataset. A second computing system is coupled to the first computing system and does not have access to the dataset. The second computing system uses a data synthesizer to receive the feature description data and generate a synthetic dataset that models the dataset and includes the set of features. The second computing system trains a machine learning model with the synthetic data set and provides the trained machine learning model to the first computing system for use with data from the data store as an input.

Abstract: An embodiment of an integrated circuit may comprise an array of hardware counters, and circuitry communicatively coupled to the array of hardware counters, the circuitry to count accesses to one or more selected pages of a memory with the array of hardware counters. Other embodiments are disclosed and claimed.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for sparse tensor storage for neural network accelerators. An example apparatus includes sparsity map generating circuitry to generate a sparsity map corresponding to a tensor, the sparsity map to indicate whether a data point of the tensor is zero, static storage controlling circuitry to divide the tensor into one or more storage elements, and a compressor to perform a first compression of the one or more storage elements to generate one or more compressed storage elements, the first compression to remove zero points of the one or more storage elements based on the sparsity map and perform a second compression of the one or more compressed storage elements, the second compression to store the one or more compressed storage elements contiguously in memory.

Abstract: An apparatus comprising translator circuitry to receive a plurality of physical addresses of memory data, determine an offset associated with each of the physical page addresses and apply a tweak seed to each offset to generate a plurality of tweaks.

Abstract: Embodiments detailed herein relate to matrix operations. In particular, support for matrix (tile) addition, subtraction, and multiplication is described. For example, circuitry to support instructions for element-by-element matrix (tile) addition, subtraction, and multiplication are detailed. In some embodiments, for matrix (tile) addition, decode circuitry is to decode an instruction having fields for an opcode, a first source matrix operand identifier, a second source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry is to execute the decoded instruction to, for each data element position of the identified first source matrix operand: add a first data value at that data element position to a second data value at a corresponding data element position of the identified second source matrix operand, and store a result of the addition into a corresponding data element position of the identified destination matrix operand.

Abstract: This disclosure describes systems, methods, and devices related to aligned channel access. A device may perform a first backoff countdown on a first link associated with a first station device (STA) of the device, wherein the device is a multi-link device (MLD). The device may detect a second backoff countdown associated with a second STA of the MLD after the first backoff countdown reaches zero. The device may determine to hold the first backoff countdown at zero based on the value of the second backoff countdown. The device may transmit in synchronization on the first link and on the second link from the first STA and the second STA respectively based on holding the first backoff countdown at zero.

Abstract: Embodiments described herein provide a technique to enable access to entries in a surface state or sampler state using 64-bit virtual addresses. One embodiment provides a graphics core that includes memory access circuitry configured to facilitate access to the memory by functional units of the graphics core. The memory access circuitry is configured to receive a message to access an entry in a surface state or a sampler state associated with a parallel processing operation. The message specifies a base address for a surface state entry or sampler state entry. The circuitry can add the base address and the offset to determine a 64-bit virtual address for the entry in the surface state entry or the sampler state and submit a memory access request to the memory to access the entry of the surface state or sampler state.

Abstract: Described herein is a generalized optimal reduction scheme for reducing an array modulo a constant. The constant modulo operation calculates a result for array of bits xi, width n modulo an odd positive integer constant d, (e.g., x[n:0] mod d). Circuitry to perform such operation can be configured to compress the array of bits xi, width n into an array of bits yi width m. The techniques described herein enable the design of optimal circuitry via iterative exploration of all potential reduction strategies that are available given the input constraints.

Abstract: The techniques described in the detailed description above enable the manufacturing of circuits with increased performance and efficiency when performing division by a constant number. One embodiment provides circuitry including an input circuit to receive an input value including a plurality of bits, a logarithmic tree coupled with the input circuit, the logarithmic tree configured to compute an array of values based on a plurality of multi-bit groups of the plurality of bits of the input value, each value in the array of values includes a modulus of a corresponding multi-bit group with respect to the constant, a binary array adder to compute a quotient of the division operation based on the array of values, the input value, and the constant, and an output circuit to output the quotient.

Abstract: This disclosure describes systems, methods, and devices related to bond strength measurement. A device may comprise a first portion of a plate connected to a movement mechanism, a second portion of the plate comprising a sticky probe and a third portion of the plate comprising a mirror with a reflective side pointing outwards. The device may further comprise an optical fiber sensor assembly comprising an optical fiber bundle for sending light through a first optical fiber and receiving light reflected from the mirror through a second optical fiber.

Abstract: An initializer for circle distribution on a 2D surface using a polar coordinate system for image compression, video compression, motion detection, and posture detection. The initializer can also be used for sphere distribution in a 3D shape. The initializer uses a mixed deterministic and iterative/stochastic approach. Using the polar coordinate system for initialization enables coverage of the user space, and after parameters are initialized, the method transitions to a cartesian coordinate system. Methods for using the polar system in CPU units by applying an XNOR/AND architecture for neural network model compression are also described. The neural network includes a perceptron for supervised learning of binary classifiers. The unit responsible for multiplication in a MAC architecture can be replaced with a non-linear expressive function. Thus, a neural network having a non-linear expressive perceptron (quadtron) is described for solving circle distribution and other problems.

Abstract: The disclosure is directed to apparatus and methods for manufacturing including a collaborative robot, a camera operatively coupled to the collaborative robot, a memory coupled to the collaborative robot, and processing circuitry coupled to the memory, the processing circuitry configured to receive image data of at least one component intended for a printed circuit board (PCB), the image data collected by the camera operatively coupled to the collaborative robot, determine, based on the image data, a coordinate location for the component, and secure the component to the PCB using an end effector of the collaborative robot based on the received image data. In one embodiment, the collaborative robot is configured to operate alongside a human, the collaborative robot in combination with the camera configured to manufacture a computer system with the PCB.

Abstract: Described herein are integrated circuit devices that include semiconductor devices near the center of the device, rather than towards the top or bottom of the device, and integrated inductors formed over the semiconductor devices. Power delivery to the device is on the opposite side of the semiconductor devices. The integrated inductors may be used for power step-down to reduce device thickness and/or a number of power rails.

Abstract: This disclosure describes systems, methods, and devices related to adding or removing communication access points (APs) affiliated with an associated AP multi-link device (AP-MLD). A non-AP-MLD may identify a communication link between the non-AP-MLD and an AP-MLD, the communication link previously used by the non-AP-MLD; encode a request frame comprising a multi-link reconfiguration element indicative of a request to add or remove the communication link; cause the non-AP-MLD to transmit the request frame to the AP-MLD; and identify a response frame received from the AP-MLD, the response frame comprising the multi-link reconfiguration element and indicating whether the communication link was accepted or rejected to be added or removed.

Abstract: A device includes a device level having a metallization structure coupled to a semiconductor device and a transistor above the device level. The transistor has a body including a single crystal group III-V or group IV semiconductor material, a source structure on a first portion of the body and a drain structure on a second portion of the body, where the source structure is separate from the drain structure. The transistor further includes a gate structure including a first gate structure portion in a recess in the body and a second gate structure portion between the source structure and the drain structure. A source contact is coupled with the source structure and a drain contact is coupled with the drain structure. The source contact is in contact with the metallization structure in the device level.

Abstract: Embodiments provided a blend circuit configured to perform a power optimized blend using blend circuitry configured such that the dynamic power consumed during the blending of two input color values is reduced when the input colors are close in value. When blending two identical input color values, a portion of the blend circuit can be bypassed and clock and/or data gated.

Abstract: Disclosed herein are IC structures with one or more decoupling capacitors based on dummy TSVs provided in a support structure. An example decoupling capacitor includes first and second capacitor electrodes and a capacitor insulator between them. The first capacitor electrode is a liner of a first electrically conductive material on sidewalls and a bottom of an opening in the support structure, the opening in the support structure extending from the first side towards, but not reaching, the second side. The capacitor insulator is a liner of a dielectric material on sidewalls and a bottom of the opening in the support structure lined with the first electrically conductive material. The second capacitor electrode is a second electrically conductive material filling at least a portion of the opening in the support structure lined with the first electrically conductive material and with the dielectric material.

Abstract: Embodiments for orchestrating execution of workloads on a distributed computing infrastructure are disclosed herein. In one example, environment data is received for compute devices in a distributed computing infrastructure. The environment data is indicative of an operating environment of the respective compute devices and a physical environment of the respective locations of the compute devices. Future operating conditions of the compute devices are predicted based on the environment data, and workloads are orchestrated for execution on the distributed computing infrastructure based on the predicted future operating conditions.

Abstract: Technologies for cryptographic separation of MMIO operations with an accelerator device include a computing device having a processor and an accelerator. The processor establishes a trusted execution environment. The accelerator determines, based on a target memory address, a first memory address range associated with the memory-mapped I/O transaction, generates a second authentication tag using a first cryptographic key from a set of cryptographic keys, wherein the first key is uniquely associated with the first memory address range. An accelerator validator determines whether the first authentication tag matches the second authentication tag, and a memory mapper commits the memory-mapped I/O transaction in response to a determination that the first authentication tag matches the second authentication tag. Other embodiments are described and claimed.

Abstract: Systems and methods for tone mapping of high dynamic range (HDR) images for high-quality deep learning based processing are disclosed. In one embodiment, a graphics processor includes a media pipeline to generate media requests for processing images and an execution unit to receive media requests from the media pipeline. The execution unit is configured to compute an auto-exposure scale for an image to effectively tone map the image, to scale the image with the computed auto-exposure scale, and to apply a tone mapping operator including a log function to the image and scaling the log function to generate a tone mapped image.

Abstract: Technologies for performing sensor fusion include a compute device. The compute device includes circuitry configured to obtain detection data indicative of objects detected by each of multiple sensors of a host system. The detection data includes camera detection data indicative of a two or three dimensional image of detected objects and lidar detection data indicative of depths of detected objects. The circuitry is also configured to merge the detection data from the multiple sensors to define final bounding shapes for the objects.

Abstract: Technologies for a flexible three-dimensional power plane in a chassis are disclosed. In one embodiment, a flexible ribbon cable is laid along a circuit board tray. The flexible ribbon cable is secured to the tray using power bosses. The power bosses connect to one or more conductors on the ribbon cable. When the circuit board is mounted on the circuit board tray, the power bosses extend through holes in the circuit board and mate with power clips on the surface of the circuit board tray. The ribbon cable, power bosses, and power clips can distribute power to various locations on the circuit board, without requiring large traces that take up space on the circuit board.

Abstract: A graph neural network (GNN) model is used in a scheduling process for compiling a deep neural network (DNN). The DNN, and parameter options for scheduling the DNN, are represented as a graph, and the GNN predicts a set of parameters that is expected to have a low cost. Using the GNN-based model, a compiler can produce a schedule for compiling the DNN in a relatively short and predictable amount of time, even for DNNs with many layers and/or many parameter options. For example, the GNN-based model reduces the overhead of exploring every parameter combination and does not exclude combinations from consideration like prior heuristic-based approaches.

Abstract: Various embodiments are generally directed to virtualized systems. A first guest memory page may be identified based at least in part on a number of accesses to a page table entry for the first guest memory page in a page table by an application executing in a virtual machine (VM) on the processor, the first guest memory page corresponding to a first byte-addressable memory. The execution of the VM and the application on the processor may be paused. The first guest memory page may be migrated to a target memory page in a second byte-addressable memory, the target memory page comprising one of a target host memory page and a target guest memory page, the second byte-addressable memory having an access speed faster than an access speed of the first byte-addressable memory.

Abstract: Described herein is a technique and associated tool for automatic program code optimization for high-level synthesis. The tool can efficiently explore multiple representations of an input program using e-graph rewriting and determine an HLS-efficient representation of program code for input into high-level synthesis tools.

Abstract: Semiconductor packages and methods for forming semiconductor packages are disclosed. An example semiconductor package includes a substrate and a core. An insulator material is present over the core, and along a direction perpendicular to a first surface of the core, a portion of the insulator material is between the core and a first surface of the substrate. A via extends between the first surface of the core and a second surface of the core in the direction perpendicular to the first surface of the core. A bridge die is in a recess in the substrate. The bridge die is coupled with the via. An electronic component is coupled to an end of the via at a second surface of the substrate.

Abstract: Embodiments described herein enable a microelectronic assembly that includes: a first substrate comprising glass and at least one inductor, the first substrate having a first side and an opposing second side; a second substrate coupled to the first side of the first substrate; and a plurality of integrated circuit (IC) dies. A first subset of the plurality of IC dies is directly coupled to the second side of the first substrate, a second subset of the plurality of IC dies is directly coupled to the second substrate adjacent to the first substrate, and a third subset of the plurality of IC dies is embedded in the second substrate between the first substrate and the second subset of the plurality of IC dies.