Abstract: A hardware-based traversal coprocessor provides acceleration of tree traversal operations searching for intersections between primitives represented in a tree data structure and a ray. The primitives may include triangles used in generating a virtual scene. The hardware-based traversal coprocessor is configured to properly handle numerically challenging computations at or near edges and/or vertices of primitives and/or ensure that a single intersection is reported when a ray intersects a surface formed by primitives at or near edges and/or vertices of the primitives.

Abstract: A hardware-based traversal coprocessor provides acceleration of tree traversal operations searching for intersections between primitives represented in a tree data structure and a ray. The primitives may include opaque and alpha triangles used in generating a virtual scene. The hardware-based traversal coprocessor is configured to determine primitives intersected by the ray, and return intersection information to a streaming multiprocessor for further processing. The hardware-based traversal coprocessor is configured to omit reporting of one or more primitives the ray is determined to intersect. The omitted primitives include primitives which are provably capable of being omitted without a functional impact on visualizing the virtual scene.

Abstract: Software-only and software-hardware optimizations to reduce the overhead of intra-thread instruction duplication on a GPU or other instruction processor are disclosed. The optimizations trade off error containment for performance and include ISA extensions with limited hardware changes and area costs.

Abstract: A streaming multiprocessor (SM) includes a nanosleep (NS) unit configured to cause individual threads executing on the SM to sleep for a programmer-specified interval of time. For a given thread, the NS unit parses a NANOSLEEP instruction and extracts a sleep time. The NS unit then maps the sleep time to a single bit of a timer and causes the thread to sleep. When the timer bit changes, the sleep time expires, and the NS unit awakens the thread. The thread may then continue executing. The SM also includes a nanotrap (NT) unit configured to issue traps using a similar timing mechanism to that described above. For a given thread, the NT unit parses a NANOTRAP instruction and extracts a trap time. The NT unit then maps the trap time to a single bit of a timer. When the timer bit changes, the NT unit issues a trap.

Abstract: Embodiments of the present invention set forth techniques for allocating execution resources to groups of threads within a graphics processing unit. A compute work distributor included in the graphics processing unit receives an indication from a process that a first group of threads is to be launched. The compute work distributor determines that a first subcontext associated with the process has at least one processor credit. In some embodiments, CTAs may be launched even when there are no processor credits, if one of the TPCs that was already acquired has sufficient space. The compute work distributor identifies a first processor included in a plurality of processors that has a processing load that is less than or equal to the processor loads associated with all other processors included in the plurality of processors. The compute work distributor launches the first group of threads to execute on the first processor.

Abstract: A communication method between a source device and a target device utilizes speculative connection setup between the source device and the target device, target-device-side packet ordering, and fine-grained ordering to remove packet dependencies.

Abstract: A secure reconfigurable operating mode system includes a hardware device having multiple operating modes and an operating mode selector that is coupled to the hardware device. The operating mode selector has a virtual fusing register that selects an operating mode for the hardware device and a security processor that enables a secure virtual fusing based on documented security files authorizing selection of the operating mode. A method of secure hardware device operating mode reconfiguration is also provided.

Abstract: A technique is disclosed for a graphics processing unit (GPU) to enter and exit a power saving deep sleep mode. The technique involves preserving processing state within local memory by configuring the local memory to operate in a self-refresh mode while the GPU is powered off for deep sleep. An interface circuit coupled to the local memory is configured to prevent spurious GPU signals from disrupting proper self-refresh of the local memory. Spurious GPU signals may result from GPU power down and GPU power up events associated with the GPU entering and exiting the deep sleep mode.

Abstract: A system for data and clock recovery includes a timing error detector, a phase detector, and a phase increment injector. The phase increment injector may be used to determine an increment to affect an output of the phase detector or a clocking element. A sign of the increment is determined from a sign or direction of an accumulated version of a clock and data recovery gradient value.

Abstract: An image processing method transforms image sequences into luminances, filters the luminances, determines the temporal differences between the luminances, performs a frequency domain transformation on the temporal differences, and applies a temporal contrast sensitivity function envelope integral to the frequency transform output to generate a temporal image metric. The temporal image metric may be applied for example to train a neural network or to configure a display device to depict a visual indication of the temporal image metric.

Abstract: Systems and methods for improved texture mapping and graphics processing are described. According to an example implementation, whole or parts of texture blocks are prefetched to an intermediate cache by a processing unit so that the same processing unit or another processing unit can subsequently obtain the prefetched texture block from the intermediate cache. Moreover, in some example implementations, control circuitry associated with the intermediate cache may throttle prefetch requests in order to avoid the memory system and/or the interconnect system receiving excessive amounts of prefetch requests. Additionally, in some implementations, deduplication of prefetch requests can be performed at the intermediate cache and/or the processing unit. Some implementations also include an efficient technique for calculating the address of the next texture block to be prefetched.

Abstract: In a ray tracer, to prevent any long-running query from hanging the graphics processing unit, a traversal coprocessor provides a preemption mechanism that will allow rays to stop processing or time out early. The example non-limiting implementations described herein provide such a preemption mechanism, including a forward progress guarantee, and additional programmable timeout options that can be time or cycle based. Those programmable options provide a means for quality of service timing guarantees for applications such as virtual reality (VR) that have strict timing requirements.

Abstract: IR drop predictions are obtained using a maximum convolutional neural network. A circuit structure is partitioned into a grid. For cells of the circuit structure in sub-intervals of a clock period, power consumption of the cell is amortized into a set of grid tiles that include portions of the cell, thus forming a set of power maps. The power maps are applied to a neural network to generate IR drop predictions for the circuit structure.

Abstract: One embodiment of the present invention sets forth a technique for encapsulating compute task state that enables out-of-order scheduling and execution of the compute tasks. The scheduling circuitry organizes the compute tasks into groups based on priority levels. The compute tasks may then be selected for execution using different scheduling schemes. Each group is maintained as a linked list of pointers to compute tasks that are encoded as task metadata (TMD) stored in memory. A TMD encapsulates the state and parameters needed to initialize, schedule, and execute a compute task.

Abstract: A system, method, and computer program product are provided for simultaneously determining settings for a plurality of parameter variations. In use, a plurality of parameter variations associated with a device is identified. Additionally, settings for each of the plurality of parameter variations are determined simultaneously.

Abstract: A gaming system includes a network server and a gaming manager communicatively coupled to the network server. The gaming manager having a video control unit that starts a video game running remotely with a static video portion and a user interactive video portion and a video receiving unit, coupled to the video control unit, that receives the static video portion for local display while the user interactive video portion is being initialized remotely for subsequent local game play. The gaming system further includes a local user device, coupled to the gaming manager, that initially displays the static video portion and provides a user interface for the subsequent local game play following completion of remote initialization of the user interactive video portion. A method of managing a remote game is also provided.

Abstract: A method dynamically selects one of a first sampling order and a second sampling order for a ray trace of pixels in a tile where the selection is based on a motion vector for the tile. The sampling order may be a bowtie pattern or an hourglass pattern. Subframes generated based on the sampling order are communicated over a bus along with motion vectors for tiles of the subframes.

Abstract: A method dynamically selects one of a first sampling order and a second sampling order for a ray trace of pixels in a tile where the selection is based on a motion vector for the tile. The sampling order may be a bowtie pattern or an hourglass pattern.

Abstract: A power adapter has a solenoid actuated retaining latch controlled by an electronic circuit that detects the presence or absence of AC mains voltage. When the assembled AC-DC adapter and plug assembly are removed from the wall, the latch detects removal and unlocks the plug assembly for easy removal without undue force required by the user. The circuit is designed for minimal power consumption, and the solenoid only consumes power when it is engaging or disengaging the latch.

Abstract: Systems and techniques for synchronizing transactions between processing devices on an interconnection network are provided. Upon receiving a stream of posted transactions followed by a flush transaction from a source processing device connected to the interconnection network, the flush transaction is trapped before it enters the interconnecting network. Subsequently, based on monitoring for responses received from a destination processing device for transactions corresponding to the posted transactions, a flush response is generated and returned to the source processing device. The described techniques enable efficient synchronizing posted writes, posted atomics and the like over complex interconnection fabrics such that a first GPU can write data to a second GPU so that a third GPU can safely consume the data written to the second GPU.