Abstract: A processing device includes an automated overclocking system and a processor. The automated overclocking system is data-driven and includes an inference engine that executes a machine learning model configured to generate a first output based on a current configuration of the processing device. The first output includes a first set of overclocking parameters. The processor is configured to adjust one or more operating characteristics of at least one component of the processing device based on the first set of overclocking parameters.

Abstract: A semiconductor package includes a substrate having opposing first and second surfaces as well as a semiconductor chip component disposed at the second surface and having third and fourth opposing surfaces. A package lid structure is affixed to the second surface of the substrate and the fourth surface of the semiconductor chip component, and has a planar component overlying the semiconductor chip component and having a fifth surface facing the fourth surface and an opposing sixth surface. The planar component includes an aperture extending between the fifth surface and the sixth surface so as to expose at least a portion of the fourth surface of the semiconductor chip component. A thermal exchange structure can be mounted on the package lid structure to form a thermal extraction pathway with the semiconductor die component via the aperture, either directly or via an interposing thermally conductive plate.

Abstract: One or more components of a computing device are run by default in a boost mode state. The one or more components continue to run in the boost mode state until the boost mode state is no longer sustainable, e.g., due to power consumption of the one or more components or temperature of the one or more components. The one or more components are switched to a reduced power state (e.g., a non-boost mode state) in response to the boost mode state no longer being sustainable. When operating the one or more components in the boost mode state again becomes sustainable due to power consumption or temperature of the one or more components, the one or more components are returned to the default boost mode state.

Abstract: A technique for performing ray tracing operations is provided. The technique includes determining a set of keys and a set of values corresponding to dimensions of a bounding box for a scene; sorting the set of keys and the set of values to generate a sorted set of values; and based on the sorted set of values, generating a Morton code for a triangle of the scene.

Abstract: A method can include overriding settings of an integrated circuit device by reading one or more settings from a setting record that correspond to a part number of the integrated circuit device. The method can also include performing an override of the settings of the integrated circuit device based on the one or more settings of the setting record that correspond to the part number of the integrated circuit device. Various other methods and systems are also disclosed.

Abstract: A system and method for efficiently creating layout for memory bit cells are described. In various implementations, a memory bit cell uses Cross field effect transistors (FETs) that include vertically stacked gate all around (GAA) transistors with conducting channels oriented in an orthogonal direction between them. The channels of the vertically stacked transistors use opposite doping polarities. The memory bit cell includes one of a read bit line and a write word line routed in no other metal layer other than a local interconnect layer. In addition, a six transistor (6T) random access data storage of the given memory bit cell consumes a planar area above a silicon substrate of four transistors.

Abstract: Systems, methods, and devices for integrated circuit power management. A mode of a power management state is entered, from the power management state, in response to an entry condition of the mode. A device that is otherwise powered off in the power management state is powered on in the mode of the power management state. In some implementations, the device includes a communications path between a second device and a third device. In some implementations, the device is in a power domain that is powered off in the power management state. In some implementations, the power domain is powered off in the mode. In some implementations, the device is powered on in the mode via a power rail that is specific to the mode. In some implementations, the entry condition of the mode includes an amount of data stored for display in a display buffer falling below a threshold amount.

Abstract: An apparatus and method for efficiently managing performance among multiple integrated circuits in separate semiconductor chips. In various implementations, a computing system includes at least a first processing node and a second processing node. While processing tasks, the first processing node accesses a first memory and the second processing node accesses a second memory. A first communication channel transfers data between the first and second processing nodes. The first processing node accesses the second memory using a second communication channel different from the first communication channel and supports point-to-point communication. The second memory services access requests from the first and second processing nodes as the access requests are received while foregoing access conflict detection. The first processing node accesses the second memory after a particular amount of time has elapsed after reception of an indication from the second processing node specifying that a particular task has begun.

Abstract: The disclosed device includes a memory-semantic fabric comprising memory components accessible by multiple processors and a controller for the memory-semantic fabric. The controller receives, from multiple processes, memory requests for a memory-semantic fabric. The controller also identifies, within the processes, a source process for each of the memory requests and prioritizes forwarding the memory requests to the memory-semantic fabric based on the source processes. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Concurrently with performing a visibility pass to generate visibility data for two or more bins of an image, a processing system determines whether a primitive to be rendered covers at least a predetermined threshold percentage of a tile of the image. In response to the primitive coving at least the predetermined threshold percentage of the tile, the processing system stores the depth data of the primitive in a depth buffer for pixel-based rendering. In response to the primitive not covering at least the predetermined threshold percentage of the tile, the processing system fuses the primitive with one or more preceding primitives sharing an edge with the primitive in the tile to generate a fused primitive. In response to the fused primitive being valid in the tile, the processing system passes the depth data of the fused primitive to the depth buffer.

Abstract: A memory package includes first, second, third, and fourth channels arranged consecutively in a clockwise direction on the memory package, each of the first, second, third, and fourth channels having access circuitry and memory arrays. In a first mode, the first channel controls access to the memory arrays in the second channel and the fourth channel controls access to the memory arrays in the third channel.

Abstract: Systems and methods for allocating computing resources within a distributed computing system are disclosed. Computing resources such as CPUs, GPUs, network cards, and memory are allocated to jobs submitted to the system by a scheduler. System configuration and interconnectivity information is gathered by a mapper and used to create a graph. Resource allocation is optimized based on one or more quality of service (QoS) levels determined for the job. Job performance characterization, affinity models, computer resource power consumption, and policies may also be used to optimize the allocation of computing resources.

Abstract: Enhanced methods for memory context restore are described. A device may include a physical layer (PHY) having an interface to support communication of command signals and data with a physical memory. The PHY implements a training mode to train the interface, detect values of a plurality of parameters as part of training the interface, and store the detected values as initial training data. The PHY also implements a retraining mode to use the initial training data as seed data to retrain the interface.

Abstract: A technique for rendering is provided. The technique includes performing a visibility operation to generate shade space visibility information and reconstruction information; performing a shade space shading operation based on the shade space visibility information generate shaded shade space textures; and performing a reconstruction operation based on the reconstruction information and the shaded shade space textures.

Abstract: Disclosed is a computer-implemented method for model ensemble acceleration in an active learning loop. The method includes receiving a set of datapoint inputs, where each datapoint input is an unlabeled equivalent of other datapoint inputs in the set of datapoint inputs and has a different applied weight value. The method then executes a set of neural network models, where the execution of each neural network model is based on the received set of datapoint inputs. The outputs from the set of neural network models are analyzed, where an inference computation is performed, and a label for the set of datapoints is determined. The method then stores the labeled set of datapoint inputs in a database. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Selectively bypassing cache directory lookups for processing-in-memory instructions is described. In one example, a system maintains information describing a status—clean or dirty—of a memory address, where a dirty status indicates that the memory address is modified in a cache and thus different than the memory address as represented in system memory. A processing-in-memory request involving the memory address is assigned a cache directory bypass bit based on the status of the memory address. The cache directory bypass bit for a processing-in-memory request controls whether a cache directory lookup is performed after the processing-in-memory request is issued by a processor core and before the processing-in-memory request is executed by a processing-in-memory component.

Abstract: The disclosed device includes a processor and an interconnect connecting the processor to a memory. The interconnect includes an interconnect agent that can forward memory requests from the processor to the memory and receive requested data returned by the memory. The requested data can include information for a next memory request such that the interconnect agent can send, to the memory, a speculative memory request using information for the next memory request that was received in response to the memory request. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: The disclosed device includes a cache organized by sets and ways and a control circuit that selects a first way for a cache replacement from a first half of a set of ways. The control circuit also selects another way from a second half of the set of ways, and uses the second way for the cache replacement when the first way is unavailable. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A technique for performing ray tracing operations is provided. The technique includes for a ray being tested for intersection with geometry associated with a bounding volume hierarchy, traversing to a pre-filtering node that includes information for filtering out triangles of a leaf node of the bounding volume hierarchy; evaluating a quantized ray that corresponds to the ray against quantized triangles of the pre-filtering node to filter out one or more triangles of the leaf node from consideration; and testing the triangles of the leaf node that are not filtered out and not testing the triangles of the leaf node that are filtered out.

Abstract: Efficient memory operation using a destructive read memory array is described. In accordance with the described techniques, a system may include a memory configured to store data of a first logic state in a ferroelectric capacitor when an electric polarization of the ferroelectric capacitor is in a first direction. A system may include a controller configured to erase the data from the memory by commanding the electric polarization of the ferroelectric capacitor in a second direction, opposite of the first direction and skipping a subsequent write operation of a null value to the memory.