Abstract: Mitigating external influences on long signal lines. In accordance with an embodiment of the present invention, a column of a memory array includes first and second transistors configured to pull up the bit line of the column. The column includes a third transistor configured to selectively pull up the bit line of the column responsive to a level of the inverted bit line of the column and a fourth transistor configured to selectively pull up the inverted bit line of the column responsive to a level of the bit line of the column. The column further includes fifth and sixth transistors configured to selectively pull up the bit line and inverted bit line of the column responsive to the clamp signal and a seventh transistor configured to selectively couple the bit line of the column and the inverted bit line of the column responsive to the clamp signal.

Abstract: In embodiments of the invention, an apparatus may include a display comprising a plurality of pixels and a computer system coupled with the display and operable to instruct the display to display images. The apparatus may further include a microlens array located adjacent to the display and comprising a plurality of microlenses, wherein the microlens array is operable to produce a light field by altering light emitted by the display to simulate an object that is in focus to an observer while the display and the microlens array are located within a near-eye range of the observer.

Abstract: One embodiment of the present disclosure sets forth an effective way to maintain fairness and order in the scheduling of common resource access requests related to replay operations. Specifically, a streaming multiprocessor (SM) includes a total order queue (TOQ) configured to schedule the access requests over one or more execution cycles. Access requests are allowed to make forward progress when needed common resources have been allocated to the request. Where multiple access requests require the same common resource, priority is given to the older access request. Access requests may be placed in a sleep state pending availability of certain common resources. Deadlock may be avoided by allowing an older access request to steal resources from a younger resource request. One advantage of the disclosed technique is that older common resource access requests are not repeatedly blocked from making forward progress by newer access requests.

Abstract: A printed circuit board, an in-circuit test structure and a method for producing the in-circuit test structure thereof are disclosed. The in-circuit test structure comprises a via and a test pad. The via passes through the printed circuit board for communicating with an electrical device to be tested on the printed circuit board. The test pad is formed on an upper surface of the printed circuit board and covering the via, wherein a center of the via deviates from a center of the test pad. In the in-circuit test, the accuracy of the test data can be improved by means of the in-circuit test structure provided by the present invention, and thus the reliability of the test result is ensured. Also, the test efficiency of the in-circuit test is improved.

Abstract: A method, computer program product, and system for selectively disabling temporal dithering is disclosed. The method includes the steps of configuring a display device to refresh utilizing a dynamic refresh rate to display images and selectively disabling temporal dithering of the images based on the dynamic refresh rate. Selectively disabling temporal dithering may comprise determining a dynamic refresh rate associated with a current frame of image data and disabling temporal dithering for the current frame of image data when the dynamic refresh rate is less than a first threshold value, or enabling temporal dithering for the current frame of image data when the dynamic refresh rate is greater than or equal to a second threshold value.

Abstract: A system, method, and computer program product are provided for processing primitive-specific attributes. A portion of a graphics processor is determined to operate in a fast geometry shader mode and a vertex associated with a set of per-vertex attributes is determined to be a shared vertex. The shared vertex is determined to be a non-provoking vertex corresponding to a first primitive that is associated with a first set of per-primitive attributes and the shared vertex is determined to be a provoking vertex corresponding to a second primitive that is associated with a second set of per-primitive attributes. Only one set of the per-vertex attributes associated with the shared vertex is stored and only one of the second set of per-primitive attributes associated with the second primitive is stored.

Abstract: One embodiment of the present invention sets forth a technique for optimizing parallel thread execution in a temporal single-instruction multiple thread (SIMT) architecture. When the threads in a parallel thread group execute temporally on a common processing pipeline rather than spatially on parallel processing pipelines, execution cycles may be reduced when some threads in the parallel thread group are inactive due to divergence. Similarly, an instruction can be dispatched for execution by only one thread in the parallel thread group when the threads in the parallel thread group are executing a scalar instruction. Reducing the number of threads that execute an instruction removes unnecessary or redundant operations for execution by the processing pipelines. Information about scalar operands and operations and divergence of the threads is used in the instruction dispatch logic to eliminate unnecessary or redundant activity in the processing pipelines.

Abstract: A solution is proposed that performs global histogramming of pre-regionally-enhanced pixel values accounting for inter-regional illumination contributions to verify that over-saturation of an image is prevented. According to an embodiment, pixel values that have been regionally enhanced—that is, with applied gains calculated for the respective regions—are further added to illumination values corresponding to the pixel values, with the resultant summed pixel values being histogrammed again to determine the amount of over-saturated pixels. An over-abundance of over-saturated pixels results in a calculation of a global modifier applied to each pixel to reduce the number of over-saturated pixels below an acceptable threshold.

Abstract: One embodiment of the present invention is a parallel processing unit (PPU) that includes one or more streaming multiprocessors (SMs) and implements a replay unit per SM. Upon detecting a page fault associated with a memory transaction issued by a particular SM, the corresponding replay unit causes the SM, but not any unaffected SMs, to cease issuing new memory transactions. The replay unit then stores the faulting memory transaction and any faulting in-flight memory transaction in a replay buffer. As page faults are resolved, the replay unit replays the memory transactions in the replay buffer—removing successful memory transactions from the replay buffer—until all of the stored memory transactions have successfully executed. Advantageously, the overall performance of the PPU is improved compared to conventional PPUs that, upon detecting a page fault, stop performing memory transactions across all SMs included in the PPU until the fault is resolved.

Abstract: One embodiment of the present invention sets forth a technique for speculatively issuing instructions to allow a processing pipeline to continue to process some instructions during rollback of other instructions. A scheduler circuit issues instructions for execution assuming that, several cycles later, when the instructions reach multithreaded execution units, that dependencies between the instructions will be resolved, resources will be available, operand data will be available, and other conditions will not prevent execution of the instructions. When a rollback condition exists at the point of execution for an instruction for a particular thread group, the instruction is not dispatched to the multithreaded execution units. However, other instructions issued by the scheduler circuit for execution by different thread groups, and for which a rollback condition does not exist, are executed by the multithreaded execution units.

Abstract: One embodiment of the present invention is a parallel processing unit (PPU) that includes one or more streaming multiprocessors (SMs) and implements a selective fault-stalling pipeline. Upon detecting a memory access fault associated with an operation executing on a particular SM, a replay unit in the selective fault-stalling pipeline considers the operation as a faulting operation. Subsequently, instead of notifying the SM of the memory access fault, the replay unit recirculates the operation—reinserting the operation into the selective fault-stalling pipeline. Recirculating faulting operations in such a fashion enables the SM to execute other operation while the replay unit stalls the faulting request until the associated access fault is resolved. Advantageously, the overall performance of the PPU is improved compared to conventional PPUs that, upon detecting a memory access fault, cancel the associated operation and subsequent operations.

Abstract: One embodiment of the present invention sets forth a method for transmitting data rendered on a primary computer to a secondary computer. The method includes transmitting to GPU graphics processing commands received from a graphics application, where the graphics processing commands are configured to cause the GPU to render a first set of graphics data, determining that graphics data should be collected for transmission to the secondary computer, conveying to the GPU that the first set of graphics data should be stored in a first buffer within a frame buffer memory, transmitting to the GPU graphics processing commands received from a process application executing on the primary computer, where the graphics processing commands are configured to cause the GPU to perform operations on the first set of graphics data to generate a second set of graphics data, and transmitting the second set of graphics data to the secondary computer.

Abstract: An interposer having decaps formed in blind-vias, a packaged semiconductor structure having decaps formed in blind-vias, and methods for forming the same are provided. In one embodiment, an interposer is provided that includes an interconnect layer disposed on a substrate. A plurality of through-vias are formed through the substrate in an isolated region of the substrate. At least one of the plurality of conductive vias are electrically coupled to at least one of a plurality of top wires formed in the interconnect layer. A plurality of blind-vias are formed through the substrate in a dense region of the substrate during a common etching step with the through-vias. At least one blind-via includes (a) a dielectric material lining the blind-vias, and (b) a conductive material filling the lined blind-vias and forming a decoupling capacitor.

Abstract: Techniques are disclosed for processing graphics objects in a stage of a graphics processing pipeline. The techniques include receiving a graphics primitive associated with the graphics object, and determining a plurality of attributes corresponding to one or more vertices associated with the graphics primitive. The techniques further include determining values for one or more state parameters associated with a downstream stage of the graphics processing pipeline based on a visual effect associated with the graphics primitive. The techniques further include transmitting the state parameter values to the downstream stage of the graphics processing pipeline. One advantage of the disclosed techniques is that visual effects are flexibly and efficiently performed.

Abstract: Embodiments of the present invention are directed to provide a method and system for automatically applying artificial limits to display resolutions in a computing system to improve performance. Embodiments are described herein that automatically limits the display resolution of an application executing in a discrete graphics processing unit operating from configurations with limited means of data transfer to the system memory. By automatically limiting the resolution in certain detected circumstances, the rate of generated graphics data may be dramatically increased. Another embodiment is also provided which allows for the automatic detection of an application's initialization and pro-actively limiting the user-selectable resolutions in which the output of the application may be displayed in to a maximum resolution calculated for optimal performance. The application's termination is also detected, whereupon a comprehensive list of supported resolutions becomes available.

Abstract: In one embodiment, a multiple input signature register (MISR) shadow works with a MISR to compress test responses of a layout partition in a functional region of an integrated circuit. In operation, for each test pattern in a test pattern split, the MISR generates a MISR signature based on the responses of the layout partition. As the test patterns in the test pattern split execute, the MISR shadow accumulates the MISR signatures and stores the result as MISR shadow data. After the final test pattern included in the test pattern split executes, the MISR shadow combines the bits in the MISR shadow data to form a single bit MISR shadow status that indicates whether the layout partition, and therefore the functional region, responds properly to the test pattern split. By efficiently summarizing the test responses, the MISR shadow optimizes the resources required to identify defective functional regions.

Abstract: The invention provides an eyewear device for transmitting a signal and a communication method thereof. The eyewear device comprises a receiving unit, a shutter and a transmitting unit. For example, the receiving unit is capable of receiving a synchronization signal, and the shutter performs an operation in response to the synchronization signal. Meanwhile, the transmitting unit transmits the synchronization signal to another eyewear device. By this way, each eyewear device is capable of receiving the synchronization signal, and re-transmits the synchronization signal to another eyewear device.

Abstract: A system includes a semiconductor die mounted on a packaging substrate, a signal redistribution layer that is formed within the packaging substrate, a power plane that is formed on a surface of the packaging substrate, and a ground plane that is formed within the packaging substrate. The power plane couples the semiconductor die to a capacitor disposed on the packaging substrate and the ground plane is disposed between the power plane and the signal redistribution layer. An advantage of the disclosed system is that loop inductance between power and ground paths to a packaged semiconductor die is reduced, thereby lowering the impedance of the packaged semiconductor die system and signal noise associated with the packaged semiconductor system.

Abstract: A computer-implemented method for designing an integrated circuit includes determining a timing slack associated with a first cell of the integrated circuit that is physically adjacent to a second cell of the integrated circuit, the second cell including an implant region that is in violation of an implant width design rule associated with the integrated circuit, determining that the timing slack is greater than a change in timing slack associated with expanding the implant region into the first cell, and, in response, expanding the implant region from first cell into the second cell to form a larger implant region.

Abstract: One embodiment of the invention sets forth a technique for determining the frame rate of video content and modifying the refresh rate of a display device to be a multiple of the determined frame rate. A video player application accesses video content and transmits video content frames associated with the video content to a driver. Based on the received video content frames, the driver generates display frames for display on a display device. The driver also determines a frame rate associated with the video content and then modifies the refresh rate of the display device to be a multiple of the video content frame rate.