Abstract: A scheme to improve performance of power-constrained computers, comprising a heterogeneous mix of compute elements, by dynamically reacting to changes in the switching capacitance that present workload induces in each heterogeneous compute element and learning the coefficients of a power-frequency model for each compute element for the present workload. At each time step, the scheme forecasts a maximum frequency that the compute element can run at without exceeding an input power limit for a given workload. The scheme rapidly re-learns coefficients of the power model and rapidly adapts the frequency as the workload's characteristics shift ensuring that compute elements run at the maximum frequency they can while not exceeding the input power limit.

Abstract: A mechanism is described for facilitating smart compression/decompression schemes at computing devices. A method of embodiments, as described herein, includes unifying a first compression scheme relating to three-dimensional (3D) content and a second compression scheme relating to media content into a unified compression scheme to perform compression of one or more of the 3D content and the media content relating to a processor including a graphics processor.

Abstract: Described herein are IC devices that include TFT based memory arrays on both sides of a layer of logic devices. An example IC device includes a support structure (e.g., a substrate) on which one or more logic devices may be implemented. The IC device further includes a first memory cell on one side of the support structure, and a second memory cell on the other side of the support structure, where each of the first memory cell and the second memory cell includes a TFT as an access transistor. Providing TFT based memory cells on both sides of a layer of logic devices allows significantly increasing density of memory cells in a memory array having a given footprint area, or, conversely, significantly reducing the footprint area of the memory array with a given memory cell density.

Abstract: A mechanism is described for facilitating fabric-based compression and/or decompression of data at computing devices. A method of embodiments, as described herein, includes compressing contents of a data stream traveling through an internal fabric between a source component and a destination component, wherein the contents are compressed on the internal fabric.

Abstract: This disclosure describes systems, methods, and devices related to null data packet (NDP) frame format. A device may cause to send a null data packet announcement (NDPA) frame to a responding station device (RSTA). The device may cause to send a first sounding NDP frame comprising one or more fields formatted to support 2.4 gigahertz (GHz) and 5 GHz bands in a non-trigger-based ranging measurement with the RSTA. The device may identify after a passage of a short inter-frame space (SIFS) time a second NDP frame received from the RSTA. The device may identify a location measurement report frame from the RSTA.

Abstract: A thermal interface material may be formed comprising a liquid metal and a corrosion resistant filler material. The thermal interface material may be used in an integrated circuit assembly between at least one integrated circuit device and a heat dissipation device, wherein the corrosion resistant filler material changes the physical properties of the thermal interface material, which may prevent failure modes from occurring during the operation of the integrated circuit assembly and may assist in maintaining a bond line thickness between the at least one integrated circuit device and the heat dissipation device.

Abstract: Embodiments may relate to a microelectronic package that includes a substrate with an overmold material. The microelectronic package may include a die in the overmold material, and an inactive side of the die may be coupled with a face of the substrate. A through-mold via (TMV) may be present in the overmold material. The TMV may be communicatively coupled with the substrate, and an active side of the die may be communicatively coupled with the TMV by a trace in the overmold material. Other embodiments may be described or claimed.

Abstract: An apparatus and method are provided which take advantage of heterogeneous compute capability to dynamically pick the best operating core for BIOS power-up flows and sleep exit flows (e.g., S3, S4, and/or S5). The selection of the BSP is moved to an early power-up time instead of a fixed hardware selection at any time. For maximum boot performance, the system selects the fastest capable core as the BSP at an early power-up time. In addition, for maximum power saving, the system selects the most power efficient core as the BSP. Processor or switching for selecting the BSP happens during the boot-up as well as power-up flows (e.g., S3, S4, and/or S5 flows).

Abstract: One embodiment provides for a graphics processing unit to accelerate machine-learning operations, the graphics processing unit comprising a multiprocessor having a single instruction, multiple thread (SIMT) architecture, the multiprocessor to execute at least one single instruction; and a first compute unit included within the multiprocessor, the at least one single instruction to cause the first compute unit to perform a two-dimensional matrix multiply and accumulate operation, wherein to perform the two-dimensional matrix multiply and accumulate operation includes to compute a 32-bit intermediate product of 16-bit operands and to compute a 32-bit sum based on the 32-bit intermediate product.

Abstract: A one-shot inductor current scheme which includes a controller to generate a signal to control a high-side switch and a low-side switch such that the high-side switch remains turned on beyond a turn-on time if a voltage level on an output supply rail remains below a reference. The scheme reduces the minimum operating voltage Vmin and/or frequency guard-band of the SoCs (system-on-chips).

Abstract: An embodiment of a semiconductor package apparatus may include technology to analyze an electronic image to determine indirect information including one or more of shadow information and reflection information, and provide the indirect information to a vehicle guidance system. Other embodiments are disclosed and claimed.

Abstract: A mechanism is described for facilitating using of a shared local memory for register spilling/filling relating to graphics processors at computing devices. A method of embodiments, as described herein, includes reserving one or more spaces of a shared local memory (SLM) to perform one or more of spilling and filling relating to registers associated with a graphics processor of a computing device.

Abstract: Described is a voltage regulator with adaptive gain, which comprises: a plurality of power-gate transistors controllable by a digital bus, the plurality of power-gate transistors operable to provide a first power supply to a load, and to receive a second power supply as input; an analog-to-digital converter (ADC) to receive the first power supply and to generate a digital output representative of the first power supply; and a controller to receive the digital output representative of the first power supply and to generate the digital bus for controlling the plurality of power-gate transistors such that a transfer function of the plurality of power-gate transistors is substantially linear over an operating range.

Abstract: A processor includes a plurality of cores, at least two of which may execute redundantly, a configuration register to store a first synchronization domain indicator to indicate that a first core and a second core are associated with a first synchronization domain, and a power controller having a synchronization circuit to cause a dynamic adjustment to a frequency of at least one of the first and second cores to cause these cores to operate at a common frequency, based at least in part on the first synchronization domain indicator.

Abstract: Disclosed embodiments relate to systems for performing instructions to quickly convert and use matrices (tiles) as one-dimensional vectors. In one example, a processor includes fetch circuitry to fetch an instruction having fields to specify an opcode, locations of a two-dimensional (2D) matrix and a one-dimensional (1D) vector, and a group of elements comprising one of a row, part of a row, multiple rows, a column, part of a column, multiple columns, and a rectangular sub-tile of the specified 2D matrix, and wherein the opcode is to indicate a move of the specified group between the 2D matrix and the 1D vector, decode circuitry to decode the fetched instruction; and execution circuitry, responsive to the decoded instruction, when the opcode specifies a move from 1D, to move contents of the specified 1D vector to the specified group of elements.

Abstract: In embodiments, an apparatus includes a burst current monitor, to detect a burst of input current drawn by a SSD from a host above a pre-defined burst threshold, and control logic coupled to the burst current monitor. The control logic, in response to the detection by the burst current monitor of the input current above the burst threshold, causes a capacitor of the SSD to supply an assistance current to the SSD, to reduce the input current drawn by the SSD. In embodiments, the capacitor is a hold-up capacitor disposed in a PLI circuit of the SSD, and the apparatus is integrated within a hold-up control logic sub-circuit of the PLI circuit.

Abstract: An integrated circuit may include a mixed instruction multiple data (xIMD) computing system. The xIMD computing system may include a plurality of data processors, each data processor representative of a lane of a single instruction multiple data (SIMD) computing system, wherein the plurality of data processors are configured to use a first dominant lane for instruction execution and to fork a second dominant lane when a data dependency instruction that does not share a taken/not-taken state with the first dominant lane is encountered during execution of a program by the xIMD computing system.

Abstract: Methods and apparatus to implement efficient communications between components of computing systems are disclosed. An example apparatus includes a message generator to: add a first value associated with a first field of a message to a shift register based on a first push operation, the message including multiple fields, at least two of the fields having different bit widths; and add a second value associated with a second field of the message to the shift register based on a second push operation, the second value to be adjacent the first value in the shift register in accordance with a structure of the message. The example apparatus further includes a communications interface to transmit content stored in the shift register to a hardware device via a bus having a width corresponding to a width of the shift register, the content including the message.

Abstract: In one embodiment, a processor includes at least one core to execute instructions and a power controller coupled to the at least one core. The power controller may include a first logic to cause the at least one core to exit an idle state and enter into a maximum performance state for a first time duration, thereafter enter into an intermediate power state for a second time duration, and thereafter enter into a sustained performance state. Other embodiments are described and claimed.

Abstract: A system for communication using a register management array circuit is disclosed, including a processor, including a processing core, the processing core including a local core register, a register management array circuit coupled to the local core register, and a remote circuit coupled to the register management array circuit, the remote circuit including a remote register. The register management array circuit includes circuitry to cause the data in the local core register to match the data in the remote register. Methods and circuits are also disclosed.

Abstract: A processor includes a plurality of cores, at least two of which may execute redundantly, a configuration register to store a first synchronization domain indicator to indicate that a first core and a second core are associated with a first synchronization domain, and a power controller having a synchronization circuit to cause a dynamic adjustment to a frequency of at least one of the first and second cores to cause these cores to operate at a common frequency, based at least in part on the first synchronization domain indicator.

Abstract: Techniques and mechanisms for capturing an image of processor state at one node of multiple nodes of a multi-processor platform, where the processor state includes some version of data which the node retrieved from another node of the platform. In an embodiment, a disruption of power is detected when a processor of a first node has a cached version of data which was retrieved from a second node. In response to detection of the disruption, the data is saved to a system memory of the first node as part of an image of the processor's state. The image further comprises address information, corresponding to the data, which indicates a memory location at the second node. In another embodiment, processor state is restored during a boot-up of the node, wherein the state includes the captured version of data which was previously retrieved from the second node.

Abstract: A processing system includes a processor and a VM-to-VM communication accelerator circuit comprising a first interface device to support direct memory access (DMA) data transfers by the first VM, a register to store a reference to a primary physical function (PF) associated with the first interface device, wherein the first primary PF is associated with an access control table (ACT) specifying an access permission for the first VM with respect to a second VM, and a direct memory access (DMA) descriptor processing circuit to process, using a working queue associated with the first primary PF, a DMA descriptor referencing a request for a DMA data transfer between the first VM and the second VM, and execute, using the first interface device, the DMA data transfer based on the access permission.

Abstract: Techniques are disclosed for forming group III-N transistors including a source to channel heterostructure design. As will be apparent in light of this disclosure, the source to channel heterostructure design may include inserting a relatively high bandgap material layer (e.g., relative to the bandgap of the channel material) between the source and channel of the III-N transistor. In some such embodiments, the relatively high bandgap material layer may be a portion of the polarization charge inducing layer formed over the III-N layer including the channel (e.g., to form a heterojunction/2DEG configuration) that is purposefully left in the source region when forming the source/drain trenches. The source to channel heterostructure design can be used to enhance the high frequency performance of the III-N transistor. Other embodiments may be described and/or disclosed.

Abstract: Methods, apparatus, and systems for facilitating effective power management through dynamic reconfiguration of interrupts. Interrupt vectors are mapped to various processor cores in a multi-core processor, and interrupt workloads on the processor cores are monitored. When an interrupt workload for a given processor core is detected to fall below a threshold, the interrupt vectors are dynamically reconfigured by remapping interrupt vectors that are currently mapped to the processor core to at least one other processor core, such that there are no interrupt vectors mapped to the processor core after reconfiguration. The core is then enabled to be put in a deeper idle state. Similar operations can be applied to additional processor cores, effecting a collapsing of interrupt vectors onto fewer processor cores.

Abstract: Systems, apparatuses and methods may provide for technology that in response to one or more of an installation of an application or a modification to the application, generates a lookup key based on a first file that is associated with the application, determines that the lookup key is to be transmitted to a server, and determines whether to store at least a portion of the first file in a memory cache based on a first frequency indicator associated with the first file from the server.

Abstract: A compute device to manage workflow to disaggregated computing resources is provided. The compute device comprises a compute engine receive a workload processing request, the workload processing request defined by at least one request parameter, determine at least one accelerator device capable of processing a workload in accordance with the at least one request parameter, transmit a workload to the at least one accelerator device, receive a work product produced by the at least one accelerator device from the workload, and provide the work product to an application.

Abstract: A dual screen display device may include a set of displays including a first display and a second display. A base may support the displays. A hinge may be coupled between the first and second displays. A channel and post may be provided in the displays and the base to provide a sliding translation between the base and the displays. In some embodiments of the dual screen device, the hinge, channel and post cooperate to provide a coupled translation of the first and second displays relative to the base.

Abstract: Systems, methods, and apparatuses relating to a matrix operations accelerator are described. In one embodiment, a processor includes a matrix operations accelerator circuit that includes a two-dimensional grid of fused multiply accumulate circuits; a first plurality of registers that represents an input two-dimensional matrix coupled to the matrix operations accelerator circuit; a decoder, of a core coupled to the matrix operations accelerator circuit, to decode an instruction into a decoded instruction; and an execution circuit of the core to execute the decoded instruction to cause the two-dimensional grid of fused multiply accumulate circuits to form a transpose of the input two-dimensional matrix when the matrix operations accelerator circuit is in a transpose mode.

Abstract: Self-aligned via and plug patterning for back end of line (BEOL) interconnects is described. In an example, an interconnect structure for an integrated circuit includes a first layer of the interconnect structure disposed above a substrate. The first layer includes a grating of alternating metal lines and dielectric lines in a first direction. A second layer of the interconnect structure is disposed above the first layer. The second layer includes a grating of alternating metal lines and dielectric lines in a second direction, perpendicular to the first direction. Each metal line of the grating of the second layer is disposed on a recessed dielectric line having alternating distinct regions of a first dielectric material and a second dielectric material corresponding to the alternating metal lines and dielectric lines of the first layer of the interconnect structure.

Abstract: One embodiment provides a compute apparatus to perform machine learning operations, the compute apparatus comprising a hardware accelerator including a compute unit to perform a Winograd convolution, the compute unit configurable to perform the Winograd convolution for a first kernel size using a transform associated with a second kernel size.

Abstract: A method performed by a first hardware element in a hierarchical arrangement of hardware elements in an object storage system is described. The method includes performing a hash on a name of an object of the object storage system. The name is part of a request that is associated with the object. A result of the hash is to identify a second hardware element directly beneath the first hardware element in the hierarchical arrangement. The request is to be sent to the second hardware element to advance the request toward being serviced by the object storage system.

Abstract: Systems, apparatuses and methods may provide away to blend two or more of the scene surfaces based on the focus area and an offload threshold. More particularly, systems, apparatuses and methods may provide a way to blend, by a display engine, two or more of the focus area scene surfaces and blended non-focus area scene surfaces. The systems, apparatuses and methods may include a graphics engine to render the focus area surfaces at a higher sample rate than the non-focus area scene surfaces.

Abstract: An apparatus to facilitate control flow in a graphics processing system is disclosed. The apparatus includes logic a plurality of execution units to execute single instruction, multiple data (SIMD) and flow control logic to detect a diverging control flow in a plurality of SIMD channels and reduce the execution of the control flow to a subset of the SIMD channels.

Abstract: A system in package includes a stair-stacked memory module that is stacked vertically with respect to a processor die. A spacer is used adjacent to the processor die to create a bridge for the stair-stacked memory module. Each memory die in the stair-stacked memory module includes a vertical bond wire that emerges from a matrix for connection. The matrix encloses the stair-stacked memory module and at least a portion of the processor die.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to improve spatial-temporal data management. An example apparatus includes a hypervoxel data structure generator to generate a root hexatree data structure having sixteen hypernodes, an octree manager to improve a spatiotemporal data access efficiency by generating a first degree of symmetry in the root hexatree, the octree manager to assign a first portion of the hypernodes to a positive temporal subspace and to assign a second portion of the hypernodes to a negative temporal subspace, and a quadtree manager to improve the spatiotemporal data access efficiency by generating a second degree of symmetry in the root hexatree, the quadtree manager to assign respective hypernodes of the positive temporal subspace and the negative temporal subspace to respective positive and negative spatial subspaces.

Abstract: Power management techniques are disclosed. For instance, an apparatus may include a bidirectional voltage converter circuit, and a control module that selectively operates the bidirectional voltage converter circuit in a charging mode and a delivery mode. The charging mode converts a voltage provided by an interface (e.g., a USB interface) into a charging voltage employed by an energy storage module (e.g., a rechargeable battery). Conversely, the delivery mode converts a voltage provided by the energy storage module into a voltage employed by the interface. Other embodiments are described and claimed.

Abstract: Embodiments are generally directed to a wireless stylus with force expression capability. An embodiment of an apparatus includes a body; a microcontroller; a force sensor to detect a pressure applied against the body of the apparatus; one or more motion sensors; and a wireless transmitter and antenna, the microcontroller to transmit force data from the force sensor and motion data from the one or more motion sensors via the wireless transmitter and antenna.

Abstract: A semiconductor package and a packaged electronic device are described. The semiconductor package has a foundation layer and a planar filtering circuit. The circuit is formed in the foundation layer to provide EMI/RFI mitigation. The circuit has one or more conductive traces that are patterned to form an equivalent circuit of inductors and capacitors. The one or more conductive traces include planar metal shapes, such as meanders, loops, inter-digital fingers, and patterned shapes, to reduce the z-height of the package. The packaged electronic device has a semiconductor die, a foundation layer, a motherboard, a package, and the circuit. The circuit removes undesirable interferences generated from the semiconductor die. The circuit has a z-height that is less than a z-height of solder balls used to attach the foundation layer to the motherboard. A method of forming a planar filtering circuit in a foundation layer is also described.

Abstract: In one embodiment, an apparatus includes: a control circuit to enable a comparison circuit based on a dynamic update to a hook table and a patch table; and the comparison circuit coupled to the control circuit to compare an address of a program counter to at least one address stored in the hook table, and in response to a match between the address of the program counter and the at least one address stored in the hook table, cause a jump from code stored in a read only memory to patch code stored in a patch storage. Other embodiments are described and claimed.

Abstract: A vertical flash device (e.g., such as a field effect transistor, charge trap gate transistor, or charge trap flash device) is placed in series with a selector device. The selector's threshold voltage may be modulated depending upon the channel resistance of the flash device allowing for the storage of a state via the selector device. In this manner, the selector device may exhibit a voltage-dependent volatile resistance state change that occurs between a first state of said selector device and a second state of said selector device. A first binary value can be represented by the first state of the selector device, and a second binary value can be represented by the second state of the selector device.

Abstract: Apparatuses and methods for initiating a discovery of accessible network resources between Internet-of-Things (IoT) devices upon detection of a user and in advance of a user command are disclosed. A detector is to detect the presence of a user prior to the user issuing a command to an IoT device, and a resource discoverer is to discover and connect to accessible network resources. User commands may be processed following discovery and connection. The detector and resource discoverer may be part of a device controller, and may be part of an IoT device.

Abstract: Embodiments of the invention include a mm-wave waveguide connector and methods of forming such devices. In an embodiment the mm-wave waveguide connector may include a plurality of mm-wave launcher portions, and a plurality of ridge based mm-wave filter portions each communicatively coupled to one of the mm-wave launcher portions. In an embodiment, the ridge based mm-wave filter portions each include a plurality of protrusions that define one or more resonant cavities. Additional embodiments may include a multiplexer portion communicatively coupled to the plurality of ridge based mm-wave filter portions and communicative coupled to a mm-wave waveguide bundle. In an embodiment the plurality of protrusions define resonant cavities with openings between 0.5 mm and 2.0 mm, the plurality of protrusions are spaced apart from each other by a spacing between 0.5 mm and 2.0 mm, and wherein the plurality of protrusions have a thickness between 200 ?m and 1,000 ?m.

Abstract: Briefly, in accordance with one or more embodiments, a display includes a housing comprising a first surface and a second surface opposite to the first surface. The second surface comprises a transparent material covering the second surface and the housing includes two or more microphone ports disposed along a parting line between the first surface and the second surface exterior to the transparent material. The housing further includes two or more microphones coupled with the two or more microphone ports. A microphone signal processing system may be utilize to increase directional sensitivity of the two more microphones toward an audio source. An angle detector to detect an angle of the may be utilized to accommodate the directional sensitivity provided by the microphone signal processing system.

Abstract: Embodiments of the invention may include packaged device that may be used for reducing cross-talk between neighboring antennas. In an embodiment the packaged device may comprise a first package substrate that is mounted to a printed circuit board (PCB). A plurality of first antennas may also be formed on the first package. Embodiments may also include a second package substrate that is mounted to the PCB, and the second package substrate may include a second plurality of antennas. According to an embodiment, the cross-talk between the first and second plurality of antennas is reduced by forming a guiding structure between the first and second packages. In an embodiment the guiding structure comprises a plurality of fins that define a plurality of pathways between the first antennas and the second antennas.

Abstract: Embodiments may relate to a dielectric waveguide that includes a substrate and a waveguide material disposed within the substrate. The dielectric waveguide may further include a waveguide launcher electromagnetically and physically coupled with the waveguide material, wherein the waveguide launcher is exposed at a side of the dielectric substrate. Other embodiments may be described or claimed.

Abstract: Disclosed herein are quantum dot devices with gate interface materials, as well as related computing devices and methods. For example, a quantum dot device may include a quantum well stack, a gate interface material, and a high-k gate dielectric. The gate interface material may be disposed between the high-k gate dielectric and the quantum well stack.

Abstract: Systems, methods, and computer-readable media are provided for wireless sensor networks (WSNs), including sensor deployment mechanisms for road surveillance. Disclosed embodiments are applied to design roadside infrastructure with optimal perception for a given geographic area. The deployment mechanisms account for the presence of static and dynamic obstacles, as well as symmetry aspects of the underlying environment. The deployment mechanisms minimize the number of required sensors to reduce costs and conserve compute and network resources, and extended infrastructure the sensing capabilities of sensor networks. Other embodiments are disclosed and/or claimed.

Abstract: An integrated circuit structure is provided which comprises: a stack of source regions of a stack of transistors and a stack of drain regions of the stack of transistors; and a gate stack that forms gate regions for the stack of transistors, wherein the gate stack comprises traces of a first polymer of a block copolymer, the block copolymer comprising the first polymer and a second polymer.