Abstract: Systems, apparatuses, and methods for block type prediction leveraging block-based pixel activities are disclosed. A pre-encoder generates predictions of block types for the blocks of a video frame based on associated pixel activities. For each block, the pre-encoder calculates the difference between the pixel activities of the block of a current frame and the pixel activities of a corresponding block of a previous video frame. If the difference is less than a first threshold, the pre-encoder predicts that the block will be a skip block. If the difference is in between the first threshold and a second threshold, the pre-encoder predicts that the block will be a P-block. Otherwise, if the difference is greater than the second threshold, then the pre-encoder predicts that the block will be an I-block. The pre-encoder uses the predictions to select quantization parameter (QP) ranges for encoding the blocks of the video frame.

Abstract: Systems, apparatuses, and methods for implementing memory bandwidth reduction techniques for low power convolutional neural network inference applications are disclosed. A system includes at least a processing unit and an external memory coupled to the processing unit. The system detects a request to perform a convolution operation on input data from a plurality of channels. Responsive to detecting the request, the system partitions the input data from the plurality of channels into 3D blocks so as to minimize the external memory bandwidth utilization for the convolution operation being performed. Next, the system loads a selected 3D block from external memory into internal memory and then generates convolution output data for the selected 3D block for one or more features. Then, for each feature, the system adds convolution output data together across channels prior to writing the convolution output data to the external memory.

Abstract: Power management in a computing device. A driver is registered with an operating system (OS) executing on the computing device to receive information about a position of a user interface control. If the user interface control is moved, the driver receives a notification of the user interface control position and determines a power management intervention based on the position The driver transmits the power management intervention to power control circuitry which sets a power setting of the computing device based on the intervention.

Abstract: In a stack of chips which each include active circuit regions, a plurality of through-silicon via (TSV) structures are formed for thermally conducting heat from the multi-chip stack by patterning, etching and filling with thermally conductive material a plurality of TSV openings in the multi-chip stack, including a first larger TSV opening that extends through substantially the entirety of the multi-chip stack without penetrating any active circuit region, and a second smaller TSV opening that extends down to but not through an active circuit region.

Abstract: Techniques for performing ray tracing operations are provided. The techniques include receiving a request to determine whether a ray intersects any primitive of a set of primitives, evaluating the ray against non-leaf nodes of a bounding volume hierarchy to determine whether to eliminate portions of the bounding volume hierarchy from consideration, evaluating the ray against at least one early-termination node not eliminated from consideration, and determining whether to terminate traversal of the bounding volume hierarchy early and to identify that the ray hits a primitive, based on the result of the evaluation of the ray against the at least one early-termination node.

Abstract: A method and system for allocating memory to a memory operation executed by a processor in a computer arrangement having a plurality of processors. The method includes receiving a memory operation from a processor that references an address in a shared memory, mapping the received memory operation to at least one virtual memory pool to produce a mapping result, and providing the mapping result to the processor.

Abstract: Disclosed herein is a region-based reference management system using in video frame encoding. Source content, such as video game streaming or remote desktop sharing, that includes scene changes or significant instantaneous changes in a region from one frame to the next can present encoding challenges. Techniques disclosed herein use hints about changes in regional frame content, dissect frame content into regions, and associate the dissected regions with stored reference frame data using the hints and information about the regions to more efficiently encode frames.

Abstract: Systems, apparatuses, and methods for implementing a safety monitor framework for a safety-critical computer vision (CV) application are disclosed. A system includes a safety-critical CV application, a safety monitor, and a CV accelerator engine. The safety monitor receives an input image, test data, and a CV graph from the safety-critical CV application. The safety monitor generates a modified image by adding additional objects outside of the input image. The safety monitor provides the modified image and CV graph to the CV accelerator which processes the modified image and provides outputs to the safety monitor. The safety monitor determines the likelihood of erroneous processing of the original input image by comparing the outputs for the additional objects with a known good result. The safety monitor complements the overall fault coverage of the CV accelerator engine and covers faults only observable at the level of the CV graph.

Abstract: A technique for generating a trained discriminator is provided. The technique includes applying one or more of a glitched image or an unglitched image to a discriminator; receiving classification output from the discriminator; adjusting weights of the discriminator to improve classification accuracy of the discriminator; applying noise to a generator; receiving an output image from the generator; applying the output image to the discriminator to obtain a classification; and adjusting weights of one of the discriminator or the generator to improve ability of the generator to reduce classification accuracy of the discriminator, based on the classification.

Abstract: A technique for detecting a glitch in an image is provided. The technique includes providing an image to a plurality of individual classifiers to generate a plurality of individual classifier outputs and providing the plurality of individual classifier outputs to an ensemble classifier to generate a glitch classification.

Abstract: A technique for varying firmware for different virtual functions in a virtualized device is provided. The virtualized device includes a hardware accelerator and a microcontroller that executes firmware. The virtualized device is virtualized in that the virtualized device performs work for different virtual functions (with different virtual functions associated with different virtual machines), each function getting a “time-slice” during which work is performed for that function. To vary the firmware, each time the virtualized device switches from performing work for a current virtual function to work for a subsequent virtual function, one or more microcontrollers of the virtualized device examines memory storing addresses for firmware for the subsequent virtual function and begins executing the firmware for that subsequent virtual function. The addresses for the firmware are provided by a corresponding virtual machine at configuration time.

Abstract: Techniques for generating a task graph for workload scheduling based on a task graph specification program are provided. The techniques include executing control flow instructions of the task graph specification program to traverse the task graph specification program; generating pass nodes of the task graph based on pass instructions of the task graph specification program; generating resource nodes and directed edges based on resource declarations of the task graph specification program; and outputting the task graph specification program to a command scheduler for scheduling.

Abstract: Techniques for scheduling operations for a task graph on a processing device are provided. The techniques include receiving a task graph that specifies one or more passes, one or more resources, and one or more directed edges between passes and resources; identifying independent passes and dependent passes of the task graph; based on performance criteria of the processing device, scheduling commands to execute the passes; and transmitting scheduled commands to the processing device for execution as scheduled.

Abstract: A system configured to perform scalable video encoding is provided. The system includes a memory; and a processing unit, wherein the processing unit is configured to: receive inter-layer data and a current picture, wherein the current picture has a base layer; upsample the inter-layer data to generate residual data and reconstruction data, wherein the inter-layer data includes a base mode flag; and encode the current picture to an enhanced layer using the upsampled inter-layer data based on a block type of the base layer and the base mode flag.

Abstract: Integrated circuit layouts are disclosed that include metal layers with metal tracks having separate metal sections along the metal tracks. The separate metal sections along a single track may be electrically isolated from each other. The separate metal sections may then be electrically connected to different voltage tracks in metal layers above and/or below the metal layer with the separate metal sections. One or more of the metal layers in the integrated circuit layouts may also include metal tracks at different voltages (e.g., power and ground) that are adjacent to each other within a power grid layout. The metal tracks may be separated by electrically insulating material. The metal tracks and the electrically insulating material between the tracks may create capacitance in the power grid layout.

Abstract: A technique for recovering from a hang in a virtualized accelerated processing device (“APD”) is provided. In the virtualization scheme, different virtual machines are assigned different “time-slices” in which to use the APD. When a time-slice expires, the APD stops operations for a current VM and starts operations for another VM. To stop operations on the APD, a virtualization scheduler sends a request to idle the APD. The APD responds by completing work and idling. If one or more portions of the APD do not complete this idling process before a timeout expires, then a hang occurs. In response to the hang, the virtualization scheduler informs the hypervisor that a hang has occurred. The hypervisor performs a function level reset on the APD and informs the VM that the hang has occurred. The VM responds by stopping command issue to the APD and re-initializing the APD for the function.

Abstract: A display system includes a display device having a plurality of individually-controllable illumination regions and a rendering device. The rendering device is to render a frame for display at the display device during a frame period, to determine a motion estimate representation for each region of a plurality of regions of the frame, each region of the frame corresponding to an illumination region of the display device, and to set, for each illumination region, an illumination configuration to be applied by the display device for the illumination region during at least one of the frame period or a subsequent frame period based on the motion estimate representation for the corresponding region of the frame.

Abstract: A texture decompression method is described. The method comprises receiving a compressed texture block, determining a partition of pixels used for the compressed texture block, wherein the partition includes one or more disjoint subsets into which data in the compressed texture block is to be unpacked, unpacking data for each subset based on the determined partition, and decompressing each of the one or more disjoint subsets to form an approximation of an original texture block.

Abstract: A display system includes a display device and a rendering device having a plurality of individually-controllable illumination regions. The rendering device is to render a frame for display at the display device during a frame period, to determine a gaze position of a user relative to the display device for the frame period, and to set, for each illumination region, an illumination configuration to be applied by the display device for the illumination region during at least one of the frame period or a subsequent frame period based on a classification of the illumination region that is representative of a location of the gaze position relative to the illumination region.

Abstract: Platform power management includes boosting performance in a platform power boost mode or restricting performance to keep a power or temperature under a desired threshold in a platform power cap mode. Platform power management exploits the mutually exclusive nature of activities and the associated headroom created in a temperature and/or power budget of a server platform to boost performance of a particular component while also keeping temperature and/or power below a threshold or budget.