Abstract: A method for enhanced forward rendering is disclosed which includes a depth pre-pass, light culling and a final shading. The depth pre-pass minimizes the cost of final shading by avoiding high pixel overdraw. The light culling stage calculates a list of light indices overlapping a pixel. The light indices are calculated on a per-tile basis, where the screen has been split into units of tiles. The final shading evaluates materials using information stored for each light. The forward rendering method may be executed on a processor, such as a single graphics processing unit (GPU) for example.

Abstract: A processor core is configured to execute a parent task that is described by a data structure stored in a memory. A coprocessor is configured to dispatch a child task to the at least one processor core in response to the coprocessor receiving a request from the parent task concurrently with the parent task executing on the at least one processor core. In some cases, the parent task registers the child task in a task pool and the child task is a future task that is configured to monitor a completion object and enqueue another task associated with the future task in response to detecting the completion object. The future task is configured to self-enqueue by adding a continuation future task to a continuation queue for subsequent execution in response to the future task failing to detect the completion object.

Abstract: A method for configuring replicas in a distributed computing system is disclosed. In one example embodiment, a plurality of replicas with associated bootstrap modules may be created. The same bootstrap module code may be used for each replica, thereby simplifying configuration. Using the bootstrap module, the replicas may automatically configure themselves and self-assign a role for a set of predetermined roles such as master and worker. The bootstrap module may check a predetermined location such as a shared network folder for earlier registration entries and then self-select based on the remaining available roles. The bootstrap module may also store its own registration entry to inform subsequent replicas of the role and network address for the current replica so that they may self-configure correctly.

Abstract: A processing unit employs a residue code (RC) to perform error detection and correction for a multi-round transformation data encryption process. The processing unit generates a cipher based on a plurality of transformations. For each of the plurality of transformations, the processing unit generates a corresponding residue code of a plurality of residue codes. The processing unit performs error detection for the cipher based on the plurality of residue codes.

Abstract: A method and system for operating in a single display mode operation and a dual pipe mode of operation is disclosed. The method and system includes operating in a dual pipe mode of operation in which each display pipe transmits data from a respective buffer to an associated display. The method and system further includes operating in a single display mode of operation in which one display pipe transmits data from a plurality of buffers to an associated display.

Abstract: Adaptive scheduling of memory requests and processing-in-memory requests is described. In accordance with the described techniques, a memory controller receives a plurality of processing-in-memory requests and a plurality of non-processing-in-memory requests from a host. The memory controller schedules an order of execution for the plurality of processing-in-memory requests and the plurality of non-processing-in-memory requests based at least in part on a processing-in-memory request stall threshold and a non-processing-in-memory request stall threshold. In response to a system switching (e.g., from executing processing-in-memory requests to executing non-processing-in-memory requests or from executing non-processing-in-memory requests to executing processing-in-memory requests), the memory controller modifies the processing-in-memory request stall threshold and the non-processing-in-memory request stall threshold.

Abstract: A computing device for calibrating high-speed communication interfaces to transmission lines may include an impedance-matching driver with a plurality of independently controllable impedance stages that facilitate matching an impedance of a transmission line. The computing device may also include a controller communicatively coupled to the impedance-matching driver via a plurality of control signals grouped into a first group of control signals that control a first stage included in the independently controllable impedance stages and a second group of control signals that control a second stage included in the independently controllable impedance stages. Various other apparatuses, systems, and methods are also disclosed.

Abstract: Systems, apparatuses, and methods for implementing a multi-tiered approach to cache compression are disclosed. A cache includes a cache controller, light compressor, and heavy compressor. The decision on which compressor to use for compressing cache lines is made based on certain resource availability such as cache capacity or memory bandwidth. This allows the cache to opportunistically use complex algorithms for compression while limiting the adverse effects of high decompression latency on system performance. To address the above issue, the proposed design takes advantage of the heavy compressors for effectively reducing memory bandwidth in high bandwidth memory (HBM) interfaces as long as they do not sacrifice system performance. Accordingly, the cache combines light and heavy compressors with a decision-making unit to achieve reduced off-chip memory traffic without sacrificing system performance.

Abstract: A processing system monitors and synchronizes parallel execution of workgroups (WGs). One or more of the WGs perform (e.g., periodically or in response to a trigger such as an indication of oversubscription) a waiting atomic instruction. In response to a comparison between an atomic value produced as a result of the waiting atomic instruction and an expected value, WGs that fail to produce a correct atomic value are identified as being in a waiting state (e.g., waiting for a synchronization variable). Execution of WGs in the waiting state is prevented (e.g., by a context switch) until corresponding synchronization variables are released.

Abstract: An apparatus includes a processor, a sleep state duration prediction module, and a system management unit. The sleep state duration prediction module is configured to predict a sleep state duration for component of the processing device. The system management unit is to transition the component into a sleep state selected from a plurality of sleep states based on a comparison of the predicted sleep state duration to at least one duration threshold. Each sleep state of the plurality of sleep states is a lower power state than a previous sleep state of the plurality of sleep states.

Abstract: Voltage range for training physical memory is described. A device is configurable to include a 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 over a training voltage range to communicate the command signals or data and an operational mode to use the trained interface to communicate the command signals or data over an operational voltage range that is smaller than the training voltage range.

Abstract: A method, system, and computer-readable medium for executing a task is disclosed. The method includes receiving input data and computing instructions, launching a workgroup including wavefronts to execute the task, wherein the launching causes the wavefronts to process the input data by sharing intermediate results and resources, and adjusting the operation based on characteristics of the wavefronts. The characteristics include data dependencies, computational load, memory usage, and execution timing requirements. The wavefronts execute the task in stages, where each stage processes portions of input data and data generated by other wavefronts.

Abstract: A method for handling engineering change orders (ECOs) for an integrated circuit design is described herein. An ECO program performs operations for an ECO flow. The ECO flow includes the ECO program generating a changed design by applying ECO changes for a set of ECOs to integrated circuits in an initial design. The ECO program then finds ECO change rule violations for the changed design. The ECO program next identifies selected ECOs associated with ECO change rule violations. The ECO program then removes the selected ECOs from the set of ECOs.

Abstract: A processing unit includes compute units partitioned into one or islands that are provided with operating voltages and clock signals having clock frequencies independent of providing operating voltages or clock signals to other islands of compute units. The processing unit also includes dynamic voltage and frequency scaling (DVFS) hardware configured to compute one or more numbers of active memory barriers in the one or more islands. The DVFS hardware is also configured to modify the operating voltages or clock frequencies provided to the one or more islands in response to a change in numbers of active memory barriers in the one or more islands. In some cases, the operating voltage or clock frequency provided to an island is increased in response to the number of active memory barriers in the island decreasing. The operating voltage or clock frequency provided to the island is decreased in response to the number of active memory barriers in the island increasing.

Abstract: A processing device including a plurality of clusters of processor cores and a method for use in the processing device is disclosed. Each processor core in a cluster of processor cores is in communication with the other processor cores in the cluster and at least one processor core of each cluster is in communication with at least a processor core of a different cluster of processor cores. Each processor core is configured to store a product of a portion of a first matrix and a first portion of a second matrix in the memory, and store a product of the portion of the first matrix and a second portion of the second matrix in the memory, where the second portion of the second matrix is received from a processor core in the cluster of processor cores.

Abstract: A device and method for processing Virtual Reality (VR) data is disclosed. The method comprises transmitting feedback information from the device to a server, wherein the feedback information is captured in the device, receiving data from the server to be presented on the device based on the feedback information, wherein the data includes video data and audio data where the video data is a frame of video data in a sequence of frames and the audio data is the corresponding audio data of the frame, decoding the video data and corresponding audio data of the frame, and controlling the presentation of the video data and corresponding audio data on the device such that the video data is synchronized with the corresponding audio data.

Abstract: Systems, methods, and apparatuses are disclosed for implementation and management of a network of computing clusters and interfaces. In various embodiment, a dynamic supercomputing resource marketplace system can include a cluster network having one or more interconnected computing clusters. The dynamic supercomputing resource marketplace system also can include a user interface system or an application program interface system for enabling a user to access the computing clusters. Advantageously, the dynamic supercomputing resource marketplace system can be used to facilitate increased utilization of computing clusters.

Abstract: A technique for accessing accelerated processing device (“APD”) memory is provided. The technique includes identifying whether to activate one or both of a first direct mapping unit and a second direct mapping unit, wherein the first direct mapping unit is associated with a small address size and the second direct mapping unit is associated with a large address size; activating the identified one or both of the first direct mapping unit and the second direct mapping unit; and accessing memory of the accelerated processing device using the one or both of the first direct mapping unit and the second direct mapping unit.

Abstract: A memory controller includes an arbiter. The arbiter is configured to elevate a priority of memory access requests that generate row activate commands in response to receiving a same-bank refresh request, and to send a same-bank refresh command in response to receiving the same-bank refresh request.

Abstract: A processing system selectively allocates storage at a local cache of a parallel processing unit for cache lines of a repeating pattern of data that exceeds the storage capacity of the cache. The processing system identifies repeating patterns of data having cache lines that have a reuse distance that exceeds the storage capacity of the cache. A cache controller allocates storage for only a subset of cache lines of the repeating pattern of data at the cache and excludes the remainder of cache lines of the repeating pattern of data from the cache. By restricting the cache to store only a subset of cache lines of the repeating pattern of data, the cache controller increases the hit rate at the cache for the subset of cache lines.