Abstract: Systems, apparatuses and methods may provide for technology that activates a first context on a graphics processor and detects a context switch condition with respect to the first context. Additionally, a second context may be activated, in response to the context switch condition, on the graphics processor while the first context is active on the graphics processor. In one example, activating the second context includes adding a group identifier to a plurality of threads corresponding to the second context and launching the plurality of threads with the group identifier on the graphics processor.

Abstract: An image processing device includes: a sub-image generation section, the sub-image generation section configured to generate a third sub-image by providing a peripheral image including at least a first region that is a transparent region around a first sub-image and to perform a filtering process on the entire or a part of a second sub-image including the first sub-image and the peripheral image; and a composition section configured to composite together a frame image and the third sub-image.

Abstract: Multiple simultaneous representations are achieved through the capture essential geometry and topology in a master graph. Object information is captured in metadata associated with elements of this graph. An algorithm builds multiple domain specific representations based on the master graph and metadata. The summary of model objects is created based on metadata. Through this abstraction, desired representations (in this case for design and for manufacturing) may be generated and presented simultaneously with associativity.

Abstract: A system configured for providing views of virtual content in an augmented reality environment may comprise one or more of a light source, an optical element, one or more physical processor, non-transitory electronic storage, and/or other components. The light source may be configured to emit light. The optical element being configured to reflect light emitted from the light source into one or more eyes of a user. The non-transitory electronic storage may be configured to store virtual content information defining virtual content. The virtual content may include one or more of an annular dock, one or more virtual objects, and/or other virtual content. The annular dock may comprise a set of sockets. The annular dock may be configured to simulate removable engagement of individual virtual objects to individual sockets. The light source may be controlled to generate views of the annular dock to be perceived as surrounding the user.

Abstract: Providing an image combination device and/or a display system comprising the same. The image combination device including an SGL control unit separating a plurality of layers into a first group layer and a second group layer not overlapping the first group layer, and a multi-layer blender combining the first group layer to produce a first composite image in a first frame and combining the second group layer including updated layers with the first composite image of the first frame to produce a second composite image in a second frame subsequent to the first frame.

Abstract: One embodiment of the present invention includes a method for tracking which cache tiles included in a plurality of cache tiles are intersected by a plurality of bounding boxes. The method includes receiving the plurality of bounding boxes, wherein each bounding box is associated with one or more graphics primitives being rendered to a render surface, and wherein the render surface is divided into the plurality of cache tiles. The method further includes, for each bounding box included in the plurality of bounding boxes, determining one or more cache tiles included in the plurality of cache tiles that are intersected by the bounding box, and storing a result in an array for each cache tile that is intersected by the bounding box. Finally, the method includes determining not to process a cache tile included in the plurality of cache tiles based on the results stored in the array.

Abstract: A method comprises providing video data representing at least part of virtual space to a user for viewing, identifying a current viewed sector of the virtual space based on user position, determining a sub-portion of said viewing sector, identifying an event occurring in a non-viewed sector of the virtual space, and displaying content indicative of the event in the sub-portion of said current viewing sector. The displaying step may comprise displaying a graphical notification of the event in the sub-portion, or in alternative embodiments, displaying video data showing the event in the sub-portion.

Abstract: The disclosure relates to a system and method for determining and pre-fetching projection data in image reconstruction. The method may include: determining a sequence of a plurality of pixels including a first pixel and a second pixel relating to the first pixel; determining a first geometry calculation used for at least one processor to access a first set of projection data relating to the first pixel from a first storage; determining a second geometry calculation based on the first geometry calculation; determining a first data template relating to the first pixel and a second data template relating to the second pixel based on the second geometry calculation; and pre-fetching a second set of projection data based on the first data template and the second data template, from a storage.

Abstract: Aspects of the subject technology relate to display circuitry including pixel overdrive circuitry. The pixel overdrive circuitry includes a compression engine that compresses a previous display frame, for storage and comparison to a current display frame without compression or decompression of the current display frame. The compression engine compresses the previous frame in such a way that the maximum compression error is always known and can be used to determine whether to perform overdrive operations for the current frame without compressing and decompressing the current display frame. The compression engine selects gradient encoding or decimation encoding for the compression of the previous display frame and can perform successive decimation operations within the gradient encoding operations to help reduce the size of the compressed previous frame while maintaining the quality of the ultimate overdriven current frame.

Abstract: Systems and methods are disclosed to receive a request for a virtual reality render project that includes information specifying virtual reality video data to be used to create a virtual reality render; determine a plurality of virtual reality jobs required to create the virtual reality render from the virtual reality video data; determine the availability of a plurality of virtual reality nodes across the network; create a virtual reality render map that specifies a processing sequence of the plurality of virtual reality jobs across the one or more virtual reality nodes to create the virtual reality render, the virtual reality render map being created based on at least the availability of the plurality of virtual reality nodes; and process the plurality of virtual reality jobs at the plurality of virtual reality nodes to create the virtual reality.

Abstract: A display controller is able to selectively perform a rearward normal display mode in which a first view-angle image is displayed in the display unit as an image of a first area of the rearward image and a rearward enlarged display mode in which a second view-angle image is displayed in the display unit as an image of a second area of the rearward image smaller than the first view-angle image in an enlarged manner. The display controller performs the rearward enlarged display mode when: an upward slope of a road on which an own car is traveling has increased; a vehicle speed of the own car has decreased after the upward slope of the road has increased; there is no preceding car that is closely lined up with the own car; and there is a following car that is not closely lined up with the own car.

Abstract: A profile adjustment system displays, in a display device 115, an input field of a coordinate of an adjustment point P0 disposed on a color space, and includes an adjustment coordinate reception unit U1, an adjustment influence range reception unit U3, a linking configuration reception unit U4, a linking configuration display processing unit UA, an adjustment coordinate configuration unit U5, an adjustment influence range configuration unit U6, a whole adjustment influence range display processing unit UB configured to display, in the display device 115, a whole adjustment influence range including U3, U4, U5, and U6, and a profile adjustment unit U7 configured to adjust a profile based on all adjustment points P0 configured in the adjustment coordinate reception unit U1 and an adjustment point Qx added by the adjustment coordinate configuration unit U5.

Abstract: A method for rendering a shape partially defined by quadratic Bézier curves computes the winding number with respect to one or more closed contours to determine whether a sample position is colored. Numerical robustness is achieved by classifying the controls points of each Bézier curve in order to partition the set of all possible Bézier curves into eight equivalence classes that can each be processed in the same manner. A small table of binary values specifies whether the roots of a classified Bézier curve are eligible to modify the winding number at a particular pixel location.

Abstract: Systems, methods, and computer readable media to improve task switching operations in a graphics processing unit (GPU) are described. As disclosed herein, the clock rate (and voltages) of a GPU's operating environment may be altered so that a low priority task may be rapidly run to a task switch boundary (or completion) so that a higher priority task may begin execution. In some embodiments, only the GPU's operating clock (and voltage) is increased during the task switch operation. In other embodiments, the clock rate (voltages) of supporting components may also be increased. For example, the operating clock for the GPU's supporting memory, memory controller or memory fabric may also be increased. Once the lower priority task has been swapped out, one or more of the clocks (and voltages) increased during the switch operation could be subsequently decreased, though not necessarily to their pre-switch rates.

Abstract: A processor comprising hardware logic configured to execute of a first wavefront in a hardware resource and stop execution of the first wavefront before the first wavefront completes. The processor schedules a second wavefront for execution in the hardware resource.

Abstract: Systems and methods consistent with the present disclosure may be utilized to negate the distinction between a display device operating in video and command modes in that commands associated with either mode are prioritized and executed according to a command scheduler consistent with the present disclosure. A command scheduler consistent with the present disclosure includes a display driver stack and a scheduler coupled to the display driver stack. The scheduler is configured to receive commands from the driver stack. Further, the scheduler is configured to queue and schedule the commands to be executed during a boot environment and during runtime. A host controller may also be coupled to the scheduler and may receive at least one of the commands from the scheduler. In time, the host controller transfers the commands to a device for execution.

Abstract: The invention provides a computer server with a graphical processor that can process data from multiple medical imaging systems simultaneously. Data sets can be provided by any suitable imaging system (x-ray, angiography, PET scans, MRI, IVUS, OCT, cath labs, etc.) and a processing system of the invention allocates resources in the form of a virtual machine, processing power, operating system, applications, etc., as-needed. Embodiments of the invention may find particular application with cath labs due to the particular processing requirements of typical cath lab systems.

Abstract: Provided are a display device and an image processing method thereof. The display device according an embodiment includes a display panel including pixels formed of red, green, blue, and white sub pixels, an image processing unit that converts a three-color input image supplied to the red, green, blue, and white sub pixels into four-color image data, calculates a color contrast ratio using a luminance weight and a hue weight by scaling luminance and hue values of the input image, and outputs an output image by considering the color contrast ratio, and a timing controller which aligns and outputs the output image from the image processing unit.

Abstract: A parallel data processing method based on multiple graphic processing units (GPUs) is provided, including: creating, in a central processing unit (CPU), a plurality of worker threads for controlling a plurality of worker groups respectively, the worker groups including one or more GPUs; binding each worker thread to a corresponding GPU; loading a plurality of batches of training data from a nonvolatile memory to GPU video memories in the plurality of worker groups; and controlling the plurality of GPUs to perform data processing in parallel through the worker threads. The method can enhance efficiency of multi-GPU parallel data processing. In addition, a parallel data processing apparatus is further provided.

Abstract: A multi-user virtual reality and/or augmented reality cluster system enabling the projection and tracking of users in a simulated environment is described. The disclosed cluster system enables both timely user action display in the first person and a timely view of a user's action by other participants of the simulation. The cluster system integrates motion capture cameras, distributed computing, and tracking devices to provide a simulation which seems lifelike to all participants and observers.