Abstract: Microelectronic assemblies, related devices and methods, are disclosed herein. In some embodiments, a microelectronic assembly may include a first die, having a first surface and an opposing second surface, in a first layer; a redistribution layer (RDL) on the first layer, wherein the RDL includes conductive vias having a greater width towards a first surface of the RDL and a smaller width towards an opposing second surface of the RDL; wherein the first surface of the RDL is electrically coupled to the second surface of the first die by first solder interconnects having a first solder; and a second die in a second layer on the RDL, wherein the second die is electrically coupled to the RDL by second solder interconnects having a second solder, wherein the second solder is different than the first solder.

Abstract: This disclosure describes systems, methods, and devices related to NAV timeout. A device may transmit, during a transmission opportunity (TxOP), an initial control frame (ICF) trigger frame including user information fields identifying one or more target stations (STAs). The device may receive from the one or more target STAs, an initial control response (ICR) frame, wherein the ICR frame includes feedback information and padding. The device may calculate a network allocation vector (NAV) timeout period based on a transmission time of a maximum-sized ICR frame at a lowest transmission rate. The device may adjust NAV settings based on the NAV timeout period.

Abstract: Voice anonymization systems and methods are provided. Voice anonymization is done on the speaker's computing device and can prevent voice theft. The voice anonymization systems and methods are lightweight and run efficiently in real time on a computing device, allowing for speaker anonymity without diminishing system performance during a teleconference or VoIP meeting. The anonymization system outputs a transformed speaker voice. The anonymization system can also generate a voice embedding that can be used to reconstruct the original speaker voice. The voice embedding can be encrypted and transmitted to another device. Sometimes, the voice embedding is not transmitted and the listener receives the anonymized voice. Systems and methods are provided for the detection of voice transformations in received audio. Thus, a listener can be informed whether the speaker voice output from the listener's computing device is the original speaker's voice or a transformed version of the original speaker voice.

Abstract: Particular embodiments described herein provide for an electronic device that can be configured to include a chassis, where the chassis includes a first chassis portion and a second chassis portion, a flexible display supported by the chassis, and a hinge. The hinge includes a first chassis attachment housing coupled to the first chassis portion, a first chassis portion lift arm coupled to the first chassis attachment housing, a first hinge pivot coupled to the first chassis portion lift arm, a second chassis attachment housing coupled to the second chassis portion, a second chassis portion lift arm coupled to the second chassis attachment housing, and a second hinge pivot coupled to the second chassis portion lift arm.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to map workloads. An example apparatus includes a constraint definer to define performance characteristic targets of the neural network, an action determiner to apply a first resource configuration to candidate resources corresponding to the neural network, a reward determiner to calculate a results metric based on (a) resource performance metrics and (b) the performance characteristic targets, and a layer map generator to generate a resource mapping file, the mapping file including respective resource assignments for respective corresponding layers of the neural network, the resource assignments selected based on the results metric.

Abstract: Write filter hardware is provided with circuitry to receive a signal to switch the write filter from a disabled state to an enabled state for a given range of addresses in a shared memory. A write attempt by a host processor to the range of addresses is identified, where access to the shared memory is shared with an accelerator device. The write filter hardware causes the write attempt to be dropped when the hardware write filter is in the enabled state for the given range of addresses.

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed to estimate a pose of a head of a user of an electronic device. An example apparatus to estimate a head pose includes at least one processor circuit to be programmed by instructions to: identify a plurality of facial landmarks in a plurality of images; identify initial image data based on the plurality of facial landmarks; augment the initial image data with a transformation operation; and train a neural network based on the initial image data and the augmented image data to: infer three-dimensional model parameters; and infer a confidence metric.

Abstract: Package substrates with components included in cavities of glass cores are disclosed. An example apparatus includes: a glass core having a first through-hole and a second through-hole, the first through-hole spaced apart from and smaller than the second through-hole; and a conductive material within the first through-hole, the conductive material to extend a full length of the first through-hole. The example apparatus further includes a dielectric material within the second through-hole, the dielectric material between an electronic component within the second through-hole and a sidewall of the second through-hole.

Abstract: Self-aligned gate endcap (SAGE) architectures with gate-all-around devices, and methods of fabricating self-aligned gate endcap (SAGE) architectures with gate-all-around devices, are described. In an example, an integrated circuit structure includes a semiconductor fin above a substrate and having a length in a first direction. A nanowire is over the semiconductor fin. A gate structure is over the nanowire and the semiconductor fin, the gate structure having a first end opposite a second end in a second direction, orthogonal to the first direction. A pair of gate endcap isolation structures is included, where a first of the pair of gate endcap isolation structures is spaced equally from a first side of the semiconductor fin as a second of the pair of gate endcap isolation structures is spaced from a second side of the semiconductor fin.

Abstract: Embodiments are directed to providing integrity-protected command buffer execution. An embodiment of an apparatus includes a computer-readable memory comprising one or more command buffers and a processing device communicatively coupled to the computer-readable memory to read, from a command buffer of the computer-readable memory, a first command received from a host device, the first command executable by one or more processing elements on the processing device, the first command comprising an instruction and associated parameter data, compute a first authentication tag using a cryptographic key associated with the host device, the instruction and at least a portion of the parameter data, and authenticate the first command by comparing the first authentication tag with a second authentication tag computed by the host device and associated with the command.

Abstract: In one embodiment, a matrix processor comprises a memory to store a matrix operand and a strided read sequence, wherein: the matrix operand is stored out of order in the memory; and the strided read sequence comprises a sequence of read operations to read the matrix operand in a correct order from the memory. The matrix processor further comprises circuitry to: receive a first instruction to be executed by the matrix processor, wherein the first instruction is to instruct the matrix processor to perform a first operation on the matrix operand; read the matrix operand from the memory based on the strided read sequence; and execute the first instruction by performing the first operation on the matrix operand.

Abstract: Systems, apparatus, and methods for energy harvesting in data centers are disclosed. An example apparatus includes interface circuitry; machine-readable instructions; and at least one processor circuit to at least one of instantiate or execute the machine-readable instructions to estimate first power consumption values for electronic components of a first rack; estimate second power consumption values for electronic components of a second rack; determine a first selection score for the first rack based on the first power consumption values and a second selection score for the second rack based on the second power consumption values; select a first electronic component of the first rack or a second electronic component of the second rack to receive a workload based on the first selection score and the second selection score; and cause the selected one of the first electronic component or the second electronic component to perform the workload.

Abstract: Disclosed herein are via plug resistors for incorporation into electronic substrates, and related methods and devices. Exemplary via plug resistor structures include a resistive element within and on a surface of a via extending at least partially through an electronic substrate and first and second electrodes coupled to the resistive element.

Abstract: Key-value (KV) caching accelerates inference in large language models (LLMs) by allowing the attention operation to scale linearly rather than quadratically with the total sequence length. Due to large context lengths in modern LLMs, KV cache size can exceed the model size, which can negatively impact throughput. To address this issue, KVCrush, which stands for KEY-VALUE CACHE SIZE REDUCTION USING SIMILARITY IN HEAD-BEHAVIOR, is implemented. KVCrush involves using binary vectors to represent tokens, where the vector indicates which attention heads attend to the token and which attention heads disregard the token. The binary vectors are used in a hardware-efficient, low-overhead process to produce representatives for unimportant tokens to be pruned, without having to implement k-means clustering techniques.

Abstract: Package substrates with components included in cavities of glass cores are disclosed. An example apparatus includes: a glass layer having an opening between opposing first and second surfaces of the glass layer; an electronic component within the opening; a dielectric material within the opening between the electronic component and a sidewall of the opening; and a through-glass via including a conductive material that extends through the glass layer.

Abstract: Techniques related to adaptive quantization matrix selection using machine learning for video coding are discussed. Such techniques include applying a machine learning model to generate an estimated quantization parameter for a frame and selecting a set of quantization matrices for encode of the frame from a number of sets of quantization matrices based on the estimated quantization parameter.

Abstract: Disclosed herein are embodiments related to security in cloudlet environments. In some embodiments, for example, a computing device (e.g., a cloudlet) may include: a trusted execution environment; a Basic Input/Output System (BIOS) to request a Key Encryption Key (KEK) from the trusted execution environment; and a Self-Encrypting Storage (SES) associated with the KEK; wherein the trusted execution environment is to verify the BIOS and provide the KEK to the BIOS subsequent to verification of the BIOS, and the BIOS is to provide the KEK to the SES to unlock the SES for access by the trusted execution environment.

Abstract: Some embodiments include apparatuses and electrical models associated with the apparatus. One of the apparatuses includes an integrated circuit having a die; a package substrate; first conductive connections coupled between the die and a first side of the package substrate; second conductive connections located on a second side of the package substrate opposite from the first side. The second conductive connections are coupled to the first conductive connections through conductive paths in the package substrate. The first conductive connections and the conductive connections are associated with an S-parameter of an electrical model of the integrated circuit package. The electrical model further includes at least one of a current value associated with a power rail of the integrated circuit package, an impedance target associated with a location at the integrated circuit package, and a mapping associated with the first and second conductive connections.

Abstract: Methods, apparatus, systems and articles of manufacture to sample enabled views per atlas in immersive video are disclosed. An example apparatus includes an interface to obtain a bitstream corresponding to an immersive video; a bitstream analyzer to determine that metadata corresponding to an atlas of the bitstream identifies that at least part of a view of interest corresponds to the atlas, the metadata included in the bitstream; and a filter to generate a filtered bitstream by removing atlases that do not identify at least part of a view of interest from the bitstream, the interface to provide the filtered bitstream to a decoder.

Abstract: Disclosed herein are techniques to provide forward error correction for a high-speed interconnect symbol stream, such as, DisplayPort. The symbol stream may be split into FEC blocks and parity bits generated for each of the FEC blocks. The parity bits may be interleaved, encoded, and transmitted over an interconnect along with the symbol stream to provide forward error correction for the symbol stream.