摘要:
An image processor is described. The image processor includes an I/O unit to read input image data from external memory for processing by the image processor and to write output image data from the image processor into the external memory. The I/O unit includes multiple logical channel units. Each logical channel unit is to form a logical channel between the external memory and a respective producing or consuming component within the image processor. Each logical channel unit is designed to utilize reformatting circuitry and addressing circuitry. The addressing circuitry is to control addressing schemes applied to the external memory and reformatting of image data between external memory and the respective producing or consuming component. The reformatting circuitry is to perform the reformatting.
摘要:
Techniques related to graphics processor workload acceleration are discussed. Such techniques may include combining multiple media tasks into one function call, providing a single batched media command set for the media tasks based on the one function call and a batched media command template, and performing the media tasks based on the single batched media command set to generate output media data.
摘要:
A method for processing data in a graphics processing unit including receiving an indication that all threads of a warp in a graphics processing unit (GPU) are to execute a same branch in a first set of instructions, storing one or more predicate bits in a memory as a single set of predicate bits, wherein the single set of predicate bits applies to all of the threads in the warp, and executing a portion of the first set of instructions in accordance with the single set of predicate bits. Executing the first set of instructions may include executing the first set of instruction in accordance with the single set of predicate bits using a single instruction, multiple data (SIMD) processing core and/or executing the first set of instruction in accordance with the single set of predicate bits using a scalar processing unit.
摘要:
A virtual primaries transform controller maps a color of a first pixel in a scene received from an imaging pipeline to a color of a second pixel, which is displayed on a monitor. The first color and the second color are the same color. The direct mapping performed by the controller assures that the colors of pixels displayed using two different display technologies are identical.
摘要:
An electronic device is described. The electronic device includes a processor. The processor is configured to render a first zone of an image. The processor is also configured to render a second zone of the image. The first zone has a higher tessellated level of detail than the second zone. The processor is further configured to present the first zone and the second zone on at least one vehicle window.
摘要:
A first user input is received when a client program executed by a client computing device is in a first state. The first user input is sent to a server computing device to render a view of a virtual scene. A state change from the first state in the client program due to a second user input or a program event is identified. One or more gaps in a server-rendered current view due to the state change are determined. A rendering of the one or more gaps is selected from among the server-rendered current view, a server-rendered predicted view and one or more prior-rendered views. A current view is rendered using a simplified model of the virtual scene by rendering the one or more gaps from the selected rendering. The current rendered view is visually presented via a display of the client computing device.
摘要:
Techniques are described for a method, one or more non-transitory computer readable media and an apparatus for rasterization based on partial spans, the method comprising: dividing a pixel input into blocks; determining a number of said blocks based on the maximum number of the partial spans; and rasterizing said blocks. The number of blocks that are evaluated may be reduced to the maximum number of blocks that can be partial. Reducing the number of the blocks reduces the power consumption and die area.
摘要:
A mechanism is described for facilitating efficient clustering and compression of graphics data at computing devices. A method of embodiments, as described herein, includes detecting a tile having pixels representing graphics contents capable of being processed by a graphics processor of a computing device. The method may further include splitting the tile into a plurality of clusters, where each cluster includes a set of pixels of one or more colors. The method may further include determining a center color for each cluster of the plurality of colors, where determining further includes deciding whether the center color is classified as acceptable for compression. The method may further include compressing contents of one or more of clusters if one or more center colors of the one or more clusters are classified as acceptable.
摘要:
Embodiments are disclosed for presenting a multi-view user interface in which a plurality of application interfaces are displayed simultaneously. An example in-vehicle computing system includes a display, a user input interface, a processor, and a storage device storing instructions executable by the processor to present a multi-view user interface including a plurality of simultaneously-displayed application interfaces displaying content for different applications, each application interface filling at least one cell of a grid. The instructions are further executable to detect user input requesting the application interfaces to be resized, the user input indicating an updated location of at least one boundary of at least two of the application interfaces, and adjust the size of each application interface by snapping the at least one boundary of the at least two application interfaces to a nearest cell boundary of a cell of the grid.
摘要:
Described herein are technologies related to technologies to facilitate real-time computer vision applications, especially those with autonomous or semi-autonomous locomotive robots (e.g., drones or self-driving cars). More particularly, the technologies described herein facilitate, for example, real-time motion estimation using dense optical flow. The technologies accelerate dense optical flow (DOF) processing of images by using the parallel processing techniques of a single-instruction, multiple data (SIMD) computing system.