An image rendering method for an electronic device includes, according to a first image displayed at a first moment, obtaining from a server at least one second image rendered in advance and to be displayed at a second moment, and after the second moment arrives and if a target image in the at least one second image coincides with an operation before or at the second moment, using the target image rendered in advance as an image corresponding to the operation. The second moment is later than the first moment.

The present disclosure discloses a game rendering method and a terminal device. The terminal device includes a JS layer, a bridge layer, and a system framework layer. The method includes the follows. The JS layer transmits drawing instructions cached in an instruction set to the bridge layer, when a number of the drawing instructions cached in the instruction set is greater than or equal to a first threshold. The bridge layer obtains a rendering result by using an OpenGL capability to process the drawing instructions, and transmits the rendering result to the system framework layer. The system framework layer performs rendering based on the rendering result.

Systems and methods may provide for determining a start time for an output image scanner to begin scanning an output image to a display device, determining a processing start time for each row of blocks of image pixel data within a rasterizer to ensure its completion before each row of blocks of image pixel data within the output image begin to be scanned out, and scheduling the start of processing of each row of blocks of image pixel data. In one example, the start time for the rasterizer to process a row of blocks of image pixel data uses the number of graphical objects to rendered into the output image and the processing times required by prior images.

An apparatus to facilitate compute optimization is disclosed. The apparatus includes a mixed precision core to perform a mixed precision multi-dimensional matrix multiply and accumulate operation on 8-bit and/or 32 bit signed or unsigned integer elements.

A method of operating a configurable gaze tracking system includes initializing a plurality of sensors by determining positional information of the sensors, wherein the sensors establish a virtual framework, initializing a plurality of target objects by determining positional information of the target objects within the virtual framework, determining a current user using data output by the sensors, determining a gaze of the current user, matching the gaze to one of the target objects in the virtual framework, wherein a target object matched to the gaze is a current target object, and activating the current target object to receive input.

In accordance with some embodiments, the render rate is varied across and/or up and down the display screen. This may be done based on where the user is looking in order to reduce power consumption and/or increase performance. Specifically the screen display is separated into regions, such as quadrants. Each of these regions is rendered at a rate determined by at least one of what the user is currently looking at, what the user has looked at in the past and/or what it is predicted that the user will look at next. Areas of less focus may be rendered at a lower rate, reducing power consumption in some embodiments.

In an embodiment, a computing device includes a processor and a machine-readable storage medium storing instructions. The instructions may be executable by the hardware processor to: receive a request for an expanded refresh rate that is not supported by a display device; in response to the received request, determine a native refresh rate that is supported by a display device; mask a plurality of interrupts generated by display hardware at the determined native refresh rate; and send, at the requested expanded refresh rate, a plurality of emulated interrupts to an operating system in place of the masked plurality of interrupts generated by the display hardware. Other embodiments are described and claimed.

A mechanism is described for facilitating using of a shared local memory for register spilling/filling relating to graphics processors at computing devices. A method of embodiments, as described herein, includes reserving one or more spaces of a shared local memory (SLM) to perform one or more of spilling and filling relating to registers associated with a graphics processor of a computing device.

A system and method for performing image scrolling are disclosed. In one embodiment, a system for image scrolling determines the scroll rate for image scrolling. The scroll rate is based on selection of a scroll rate range, through a user input device, and is further based on movement indicated by the user input device. The system writes a sequence of images from the image cache to the frame buffer for image scrolling on the display at the determined scroll rate.

A system includes reception of a request to display a data chart. In response to the request, a cached version of the data chart is retrieved from a memory, the cached version of the data chart is displayed, and while the cached version of the data chart is displayed, current data of the data chart is requested from a remote data source. Also while the cached version of the data chart is displayed, an active version of the data chart is rendered based on the current data. The displayed cached version is then replaced with a display of the rendered active version.