Abstract: An apparatus to facilitate exception handling for debugging in a graphics environment is disclosed. The apparatus includes load store pipeline hardware circuitry to: in response to a page fault exception being enabled for a memory access request received from a thread of the plurality of threads, allocate a memory dependency token correlated to a scoreboard identifier (SBID) that is included with the memory access request; send, to memory fabric of the graphics processor, the memory access request comprising the memory dependency token; receive, from the memory fabric in response to the memory access request, a memory access response comprising the memory dependency token and indicating occurrence of a page fault error condition and fault details associated with the page fault error condition; and return the SBID associated with the memory access response and fault details of the page fault error condition to a debug register of the thread.

Abstract: Described herein are gate-all-around (GAA) transistors with extended drains, where the drain region extends through a well region below the GAA transistor. A high voltage can be applied to the drain, and the extended drain region provides a voltage drop. The transistor length (and, specifically length of the extended drain) can be varied based on the input voltage to the device, e.g., providing a longer drain for higher input voltages. The extended drain transistors can be implemented in devices that include CFETs, either by implementing the extended drain transistor across both CFET layers, or by providing a sub-fin pedestal with the well regions in the lower layer.

Abstract: This disclosure describes systems, methods, and devices related to using encrypted 802.11 association. A device may identify a beacon received from an access point (AP), the beacon including an indication of an authentication and key manager (AKM); transmit, to the AP, an 802.11 authentication request including an indication of parameters associated with the AKM; identify an 802.11 authentication response received from the AP based on the 802.11 authentication request, the 802.11 authentication response including a message integrity check (MIC) using a key confirmation key (KCK) and an indication that the parameters have been selected by the AP; transmit, to the AP, an 802.11 association request encrypted by a security key based on an authenticator address of the AP; and identify an 802.11 association response received from the AP based on the 802.11 association request, the 802.11 association response encrypted by the security key.

Abstract: Package substrates with components included in cavities of glass cores are disclosed. An example apparatus includes: a glass core having a first opening and a second opening spaced apart from the first opening, the second opening having a greater width than the first opening. The example apparatus further includes a conductive material adjacent a first wall of the first opening; and a dielectric material adjacent a second wall of the second opening.

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 is electrically coupled to the second surface of the first die by solder interconnects, and a second die in a second layer on the RDL, wherein the second die is electrically coupled to the RDL by non-solder interconnects.

Abstract: Memory management for wireless networks is described. A method, includes accessing an operational parameter for a network slice of a wireless network, determining a first memory region of a plurality of memory regions in the memory pool based on the operational parameter, and encoding configuration information to allocate the first memory region to the network slice. Other embodiments are described and claimed.

Abstract: Described herein are stacked photonic integrated circuit (PIC) assemblies that include multiple layers of waveguides. The waveguides are formed of substantially monocrystalline materials, which cannot be repeatedly deposited. Layers of monocrystalline material are fabricated and repeatedly transferred onto the PIC structure using a layer transfer process, which involves bonding a monocrystalline material using a non-monocrystalline bonding material. Layers of isolation materials are also deposited or layer transferred onto the PIC assembly.

Abstract: Methods and apparatus to improve user experience on computing devices are disclosed. An example computing device includes a microphone to capture audio corresponding to spoken words. The example computing device further includes a speech analyzer to: detect a keyword prompt from among the spoken words, the keyword prompt to precede a query statement of a user of the computing device; and identify topics associated with a subset of the spoken words, the subset of the spoken words captured by the microphone before the keyword prompt. The example computing device also includes a communications interface to, in response to detection of the keyword prompt, transmit information indicative of the query statement and ones of the identified topics to a remote server.

Abstract: Generally discussed herein are systems, methods, and apparatuses that include conductive pillars that are about co-planar. According to an example, a technique can include growing conductive pillars on respective exposed landing pads of a substrate, situating molding material around and on the grown conductive pillars, removing, simultaneously, a portion of the grown conductive pillars and the molding material to make the grown conductive pillars and the molding material about planar, and electrically coupling a die to the conductive pillars.

Abstract: A datacenter including a plurality of racks. The racks associated with a motorized and/or automated system to move the racks between first and second positions. In the first position, the racks are arranged in a side-by-side fashion in one or more rows. In the second position, a rack is moved so that a lateral side of the rack is accessible. In some embodiments, the racks include a motor and gear system for interacting with tracks. In some embodiments, each of the racks includes a plurality of chassis, each chassis including a plurality of input/output (I/O) connectors to receive a connector of a cable, the plurality of I/O connectors are arranged along a lateral side of the chassis so that they are accessible when the rack is in the second position. In use, the racks may be moved between the first and second positions while the chassis remain in normal operation.

Abstract: Methods and apparatus relating to techniques for avoiding cache lookup for cold cache. In an example, an apparatus comprises logic, at least partially comprising hardware logic, to collect user information for a user of a data processing device, generate a user profile for the user of the data processing device from the user information, and set a power profile a processor in the data processing device using the user profile. Other embodiments are also disclosed and claimed.

Abstract: In one embodiment, an apparatus includes: an integrity circuit to receive data and generate a protection code based at least in part on the data; a cryptographic circuit coupled to the integrity circuit to encrypt the data into encrypted data and encrypt the protection code into an encrypted protection code; a message authentication code (MAC) circuit coupled to the cryptographic circuit to compute a MAC comprising a tag using header information, the encrypted data, and the encrypted protection code; and an output circuit to send the header information, the encrypted data, and the tag to a receiver via a link. Other embodiments are described and claimed.

Abstract: Methods, apparatus, systems and articles of manufacture for loss-error-aware quantization of a low-bit neural network are disclosed. An example apparatus includes a network weight partitioner to partition unquantized network weights of a first network model into a first group to be quantized and a second group to be retrained. The example apparatus includes a loss calculator to process network weights to calculate a first loss. The example apparatus includes a weight quantizer to quantize the first group of network weights to generate low-bit second network weights. In the example apparatus, the loss calculator is to determine a difference between the first loss and a second loss. The example apparatus includes a weight updater to update the second group of network weights based on the difference. The example apparatus includes a network model deployer to deploy a low-bit network model including the low-bit second network weights.

Abstract: Techniques for scalable virtualization of an Input/Output (I/O) device are described. An electronic device composes a virtual device comprising one or more assignable interface (AI) instances of a plurality of AI instances of a hosting function exposed by the I/O device. The electronic device emulates device resources of the I/O device via the virtual device. The electronic device intercepts a request from the guest pertaining to the virtual device, and determines whether the request from the guest is a fast-path operation to be passed directly to one of the one or more AI instances of the I/O device or a slow-path operation that is to be at least partially serviced via software executed by the electronic device. For a slow-path operation, the electronic device services the request at least partially via the software executed by the electronic device.

Abstract: Predictive uncertainty of a generative machine learning model may be estimated. The generative machine learning model may be a large language model or large multi-modal model. A datum may be input into the generative machine learning model. The generative machine learning model may generate outputs from the datum. Latent embeddings for the outputs may be extracted from the generative machine learning model. A covariance matrix with respect to the latent embeddings may be computed. The covariance matrix may be a two-dimensional matrix, such as a square matrix. The predictive uncertainty of the generative machine learning model may be estimated using the covariance matrix. For instance, the matrix entropy of the covariance matrix may be determined. The matrix entropy may be an approximated dimension of a latent semantic manifold spanned by the outputs of the generative machine learning model and may indicate the predictive uncertainty of the generative machine learning model.

Abstract: Methods and apparatus relating to techniques for multi-tile memory management. In an example, a graphics processor includes an interposer, a first chiplet coupled with the interposer, the first chiplet including a graphics processing resource and an interconnect network coupled with the graphics processing resource, cache circuitry coupled with the graphics processing resource via the interconnect network, and a second chiplet coupled with the first chiplet via the interposer, the second chiplet including a memory-side cache and a memory controller coupled with the memory-side cache. The memory controller is configured to enable access to a high-bandwidth memory (HBM) device, the memory-side cache is configured to cache data associated with a memory access performed via the memory controller, and the cache circuitry is logically positioned between the graphics processing resource and a chiplet interface.

Abstract: The disclosed embodiments are generally directed to inline encryption of data at line speed at a chip interposed between two memory components. The inline encryption may be implemented at a System-on-Chip (“SOC” or “SOC”). The memory components may comprise Non-Volatile Memory express (NVMe) and a dynamic random access memory (DRAM). An exemplary device includes an SOC to communicate with a Non-Volatile Memory NVMe circuitry to provide direct memory access (DMA) to an external memory component. The SOC may include: a cryptographic controller circuitry; a cryptographic memory circuitry in communication with the cryptographic controller, the cryptographic memory circuitry configured to store instructions to encrypt or decrypt data transmitted through the SOC; and an encryption engine in communication with the crypto controller circuitry, the encryption engine configured to encrypt or decrypt data according to instructions stored at the crypto memory circuitry. Other embodiments are also disclosed and claimed.

Abstract: Technologies for trusted I/O include a computing device having a hardware cryptographic agent, a cryptographic engine, and an I/O controller. The hardware cryptographic agent intercepts a message from the I/O controller and identifies boundaries of the message. The message may include multiple DMA transactions, and the start of message is the start of the first DMA transaction. The cryptographic engine encrypts the message and stores the encrypted data in a memory buffer. The cryptographic engine may skip and not encrypt header data starting at the start of message or may read a value from the header to determine the skip length. In some embodiments, the cryptographic agent and the cryptographic engine may be an inline cryptographic engine. In some embodiments, the cryptographic agent may be a channel identifier filter, and the cryptographic engine may be processor-based. Other embodiments are described and claimed.

Abstract: A processing apparatus described herein includes a general-purpose parallel processing engine comprising a systolic array having multiple pipelines, each of the multiple pipelines including multiple pipeline stages, wherein the multiple pipelines include a first pipeline, a second pipeline, and a common input shared between the first pipeline and the second pipeline.

Abstract: A processing apparatus includes a processing resource including a general-purpose parallel processing engine and a matrix accelerator. The matrix accelerator includes first circuitry to receive a command to perform operations associated with an instruction, second circuitry to configure the matrix accelerator according to a physical depth of a systolic array within the matrix accelerator and a logical depth associated with the instruction, third circuitry to read operands for the instruction from a register file associated with the systolic array, fourth circuitry to perform operations for the instruction via one or more passes through one or more physical pipeline stages of the systolic array based on a configuration performed by the second circuitry, and fifth circuitry to write output of the operations to the register file associated with the systolic array.

Abstract: Methods and apparatus relating to an instruction and/or micro-architecture support for decompression on core are described. In an embodiment, decode circuitry decodes a decompression instruction into a first micro operation and a second micro operation. The first micro operation causes one or more load operations to fetch data into one or more cachelines of a cache of a processor core. Decompression Engine (DE) circuitry decompresses the fetched data from the one or more cachelines of the cache of the processor core in response to the second micro operation. Other embodiments are also disclosed and claimed.

Abstract: Techniques to improve performance of matrix multiply operations are described in which a compute kernel can specify one or more element-wise operations to perform on output of the compute kernel before the output is transferred to higher levels of a processor memory hierarchy.

Abstract: This disclosure describes systems, methods, and devices related to high throughput (HT) control information. A device may determine a frame comprising HT control information. The device may determine to extend a size of the HT control information. The device may cause to generate a management or data frame for sending to a first station device of one or more station devices, the management or data frame comprising extended high throughput (HT) control information, define a new control identification (ID) associated with the extended HT control information, and cause to send the management or data frame to the first station device.

Abstract: Techniques described herein address the above challenges that arise when using host executed software to manage vector databases by providing a vector database accelerator and shard management offload logic that is implemented within hardware and by software executed on device processors and programmable data planes of a programmable network interface device. In one embodiment, a programmable network interface device includes infrastructure management circuitry configured to facilitate data access for a neural network inference engine having a distributed data model via dynamic management of a node associated with the neural network inference engine, the node including a database shard of a vector database.

Abstract: Logic may monitor quality of communication of data to a wireless receiver device based on transport characteristics at a wireless source device. Logic may evaluate the transport characteristics to identify indication(s) of a problem with the quality of the communication. Logic may identify a root cause associated with the indication(s). Logic may associate the root cause with one or more actions to mitigate the degradation of the quality. And logic may cause performance of an operation to mitigate the degradation of the quality based on the one or more actions. The logic to evaluate the transport characteristics may determine an upper limit for an achievable mean opinion score (MOS) based on the transport characteristics; and, based on the upper limit for the achievable MOS being less than a threshold MOS, may identify the indication(s) associated with the upper limit for the achievable MOS.

Abstract: In an example, an apparatus comprises logic, at least partially comprising hardware logic, to receive an input from one or more detectors proximate a display to present an output from a graphics pipeline, determine that a user is not interacting with the display, and in response to a determination that the user is not interacting with the display, to reduce a frame rendering rate of the graphics pipeline. Other embodiments are also disclosed and claimed.

Abstract: One embodiment provides an apparatus comprising a memory stack including multiple memory dies and a parallel processor including a plurality of multiprocessors. Each multiprocessor has a single instruction, multiple thread (SIMT) architecture, the parallel processor coupled to the memory stack via one or more memory interfaces. At least one multiprocessor comprises a multiply-accumulate circuit to perform multiply-accumulate operations on matrix data in a stage of a neural network implementation to produce a result matrix comprising a plurality of matrix data elements at a first precision, precision tracking logic to evaluate metrics associated with the matrix data elements and indicate if an optimization is to be performed for representing data at a second stage of the neural network implementation, and a numerical transform unit to dynamically perform a numerical transform operation on the matrix data elements based on the indication to produce transformed matrix data elements at a second precision.

Abstract: Technologies for an optical interposer with actuator beams are disclosed. In one embodiment, an integrated circuit package includes an optical interposer and a photonics integrated circuit (PIC) die. The optical interposer includes actuator beams and waveguides embedded in the actuator beams. An electrical trace is disposed on the actuator beams. In use, current can pass through the electrical trace, expanding the trace through thermal expansion. The trace expands more than the actuator beam underneath it, causing the actuator beam and the waveguides to be deflected. In this manner, the waveguides in the optical interposer can be positioned to align to waveguides in the PIC die.

Abstract: A ferrule of an optical connector device is to accept one or more optical fibers in one or more fiber holes of the ferrule, the ferrule is formed from a dielectric material. The ferrule includes a face to interface with an optical socket of another device, where ends of the one or more optical fibers are exposed at the face to communicate photon signals with another device. The ferrule further includes alignment features formed in the dielectric layer to align the ends of the one or more optical fibers with one or more waveguides of the other device.

Abstract: An embodiment discloses a method comprising receiving a substrate comprising a first layer, a second layer over the first layer, and a third layer over the second layer, the third layer comprising a plurality of integrated circuit (IC) components, and applying a laser to ablate portions of the first layer, wherein the second layer protects the third layer from cracking during application of the laser.

Abstract: An apparatus of an aspect includes a plurality of cores and shared core extension logic coupled with each of the plurality of cores. The shared core extension logic has shared data processing logic that is shared by each of the plurality of cores. Instruction execution logic, for each of the cores, in response to a shared core extension call instruction, is to call the shared core extension logic. The call is to have data processing performed by the shared data processing logic on behalf of a corresponding core. Other apparatus, methods, and systems are also disclosed.

Abstract: For example, a radar Radio Head (RH) may be configured to determine Range-Doppler (RD) information corresponding to a plurality of RD bins based on digital radar Receive (Rx) signals representing radar Radio Frequency (RF) Rx signals received by one or more Rx antennas; to detect one or more detected RD bins based on the RD information; to provide filtered RD information including RD information corresponding to the one or more detected RD bins and excluding RD information of one or more excluded RD bins, which are not included in the one or more detected RD bins; and to send the filtered RD information to another processor via a communication interconnect.

Abstract: The substrate of an integrated circuit component comprises a multi-layer die structure conductively coupled to the substrate. The multi-die layered structure includes a first primary integrated circuit die attached to the substrate and communicatively coupled to a first photonic integrated circuit (PIC) die, and a second primary integrated circuit die vertically spaced from the first primary integrated circuit die and communicatively coupled to a second PIC die. The integrated circuit component further includes a first intermediate waveguide optically coupling a first PIC waveguide of the first PIC die to a first substrate waveguide in the substrate, and a second intermediate waveguide optically coupling a second PIC waveguide of the second PIC die to a second substrate waveguide in the substrate. The integrated circuit component may further include a third intermediate waveguide optically coupling the first PIC die to the second PIC die.

Abstract: Technologies for diamond composite materials are disclosed. In one embodiment, field-assisted sintering technology (FAST) is used to create a diamond composite material that includes diamond particles, copper, and chromium. The chromium can help bond the copper and the diamond particles. The diamond composite material has a high thermal conductivity, such as 500-1,000 W/(m·K). In one embodiment, the diamond composite material may be used in an integrated heat spreader in an integrated circuit component. In other embodiments, the diamond composite material may be used in a heat sink, a cold plate, an internal frame, a chassis, etc.

Abstract: A surface of an integrated circuit (IC) die structure and a substrate to which the IC die structure is to be bonded include biphilic regions suitable for liquid droplet formation and droplet-based fine alignment of the IC die structure to the substrate. To ensure warpage of the IC die structure does not interfere with droplet-based fine alignment process, an IC die structure of greater thickness is aligned to the substrate and thickness of the IC die structure subsequently reduced. In some embodiments, a back side of the IC die structure is polished back post attachment. In some alternative embodiments, the IC die structure includes sacrificial die-level carrier is removed after fine alignment and/or bonding.

Abstract: An electronic package comprises a substrate core; one or more dielectric material layers over the substrate core and having a lower dielectric material layer, and a plurality of metallization layers comprising an upper-most metallization layer; an integrated circuit (IC) die embedded within the dielectric material and below the upper-most metallization layer; and at least one conductive feature below and coupled to the IC die. A downwardly facing surface of the conductive feature is located on the lower dielectric material layer and defines a horizontal plane at a junction between the conductive feature and the lower dielectric material layer. The lower dielectric material layer has an upper facing surface facing in a direction of the IC die adjacent the conductive feature that is vertically offset from the horizontal plane.

Abstract: An IC die package includes a substrate comprising glass and a plurality of holes extending through the glass. A via metallization is present within the holes. A liner is between the via metallization and the glass. The liner can comprise a beta-titanium alloy layer, polymer hydrogel layer and an MXene seed layer, an organic material layer and a metal layer, or an organic material layer between first and second metal layers. A polymer layer may be formed by electrodeposition of charged nanoparticles.

Abstract: An example apparatus includes memory; machine-readable instructions; and at least one programmable circuit to at least one of execute or instantiate the machine-readable instructions to at least adjust a frequency of a clock signal of the memory based on workload demands of a processor circuit.

Abstract: Techniques for dynamic cache fill prioritization are described. In an embodiment, an apparatus includes a cache at a mid-level of a cache hierarchy; and a mid-level cache (MLC) unit including the cache, a local queue to store MLC lookup requests, an external queue to store MLC fill requests, and an MLC access control hardware. The MLC access control hardware is to dynamically switch prioritization of servicing the MLC lookup requests versus servicing the MLC fill requests.

Abstract: Techniques for partitioned home snoop filtering are described. In an embodiment, an apparatus includes multiple caching agent circuits and a home agent circuit. The home agent circuit controls cache coherency using a snoop filter including multiple partitions, each corresponding to a corresponding one of the caching agent circuits.

Abstract: Various techniques for edge stress reduction in glass cores and related devices and methods are disclosed. In one example, a microelectronic assembly includes a glass core having a bottom surface, a top surface opposite the bottom surface, and one or more sidewalls extending between the bottom surface and the top surface, and further includes a panel of an organic material, wherein the glass core is embedded within the panel. In another example, a microelectronic assembly includes a glass core as in the first example, where an angle between a portion of an individual sidewall and one of the bottom surface or the top surface is greater than 90 degrees. In yet another example, a microelectronic assembly includes a glass core as in the first example, and further includes a pattern of a material on one of the one or more sidewalls.

Abstract: A hardware accelerator device is provided with accelerator hardware to perform dictionary compressions in hardware based on a request from an application executed by a processor device coupled to the hardware accelerator device to compress data for the application.

Abstract: A semiconductor package carrier used to support a semiconductor package (e.g., a semiconductor, a microprocessor, etc.) as the semiconductor package is moved from a shipping tray to a land grid array (LGA) socket during assembly of an electronic device. The semiconductor package carrier including a carrier body including a plurality of support structures arranged to support a portion of the semiconductor package. The semiconductor package carrier further including a locking structure moveable between a first position and a second position, wherein the first position allows the support structures to receive the semiconductor package and the second position secures the semiconductor package to the carrier body. In some embodiments, the semiconductor package carrier may also include a thermal interface material (TIM) breaker to facilitate removal of a heatsink from the semiconductor package. Other embodiments are described and claimed.

Abstract: Hybrid bonded die stacks, related apparatuses, systems, and methods of fabrication are disclosed. One or both of an integrated circuit (IC) die hybrid bonding region and a base substrate hybrid bonding region surrounded by hydrophobic structures that include a cross-linked material. The hybrid bonding regions are brought together with a liquid droplet therebetween, and capillary forces cause the IC die to self-align. A hybrid bond is formed by evaporating the droplet and a subsequent anneal. The cross-linked material hydrophobic structures contain the liquid droplet for alignment and are resistant to plasma treatment prior to bonding.

Abstract: Integrated circuit (IC) devices and systems with virtual ground nets, and methods of forming the same, are disclosed herein. In one embodiment, an integrated circuit die includes a device layer with transistors, a first interconnect over the device layer, and a second interconnect under the device layer. Moreover, the first interconnect includes ground traces, which are electrically coupled to each other in the first interconnect or the second interconnect.

Abstract: Described herein is a technique to approximate photorealistic indirect illumination shown in path traced images for dynamic lighting environments using a neural network. Given a lightly ray traced image, intermediate buffers from rendering pipeline, and light and camera information, the photorealism of rendered images can be enhanced via the neural network to approximate path traced indirect illumination.

Abstract: A shared memory controller receives, from a computing node, a request associated with a memory transaction involving a particular line in a memory pool. The request includes a node address according to an address map of the computing node. An address translation structure is used to translate the first address into a corresponding second address according to a global address map for the memory pool, and the shared memory controller determines that a particular one of a plurality of shared memory controllers is associated with the second address in the global address map and causes the particular shared memory controller to handle the request.

Abstract: A set of optical fibers are set within grooves a substrate to align the optical fibers with a waveguide associated with photonic processing circuitry. The set of optical fibers are adhered within the grooves using a polyethylene oxide (PEO)-based adhesive. The PEO-based adhesive may have a refractive index matched to the refractive index of one or both of the optical fibers or the waveguide.

Abstract: A neural network model for anomaly detection may include convolutional blocks with different spatial scales. The model may be trained with training data, which may be normal data that lacks anomaly. The convolutional blocks may generate embedding features having different spatial scales. A distance between each embedding feature and a corresponding model embedding may be determined. The distances for the embedding features may be accumulated for determining a loss of the model. The model may be trained based on the loss. An accuracy of the trained model may be tested with testing data that has verified anomaly. One or more convolutional blocks may be selected from all the convolutional blocks in the model, e.g., based on the spatial scales of the convolutional blocks and the spatial scale of data on which anomaly detection is to be performed. The selected convolutional block(s) may be used to detect anomaly in the data.

Abstract: An apparatus to facilitate supporting 8-bit floating point format for parallel computing and stochastic rounding operations in a graphics architecture is disclosed. The apparatus includes a processor comprising: a decoder to decode an instruction fetched for execution into a decoded instruction, wherein the decoded instruction is a matrix instruction that is to operate on 8-bit floating point operands to perform a parallel dot product operation; a scheduler to schedule the decoded instruction and provide input data for the 8-bit floating point operands in accordance with an 8-bit floating data format indicated by the decoded instruction; and circuitry to execute the decoded instruction to perform 32-way dot-product using 8-bit wide dot-product layers, each 8-bit wide dot-product layer comprises one or more sets of interconnected multipliers, shifters, and adders, wherein each set of multipliers, shifters, and adders is to generate a dot product of the 8-bit floating point operands.