Abstract: In one or more embodiments, a framework is provided in which image decoding can be delayed based on heuristics, and later initiated based on a use type associated with the image or the likelihood that the image is going to be used. For example, a use history and priority system can enable images that are currently being rendered and/or are likely to get rendered to be decoded before images that have a history of being downloaded but never used. Accordingly, by decoupling image download from image decoding, CPU resources and memory can be more efficiently utilized.

Abstract: In one or more embodiments, a framework is provided in which image decoding can be delayed based on heuristics, and later initiated based on a use type associated with the image or the likelihood that the image is going to be used. For example, a use history and priority system can enable images that are currently being rendered and/or are likely to get rendered to be decoded before images that have a history of being downloaded but never used. Accordingly, by decoupling image download from image decoding, CPU resources and memory can be more efficiently utilized.

Abstract: Various embodiments provide techniques for partitioning high resolution images into sub-images for display. In at least some embodiments, the techniques can enable a device to display an image in its native resolution (e.g., the image capture resolution) even when the image exceeds a threshold image size for the device. In example implementations, techniques determine that a size of an image exceeds a threshold image size for a system. Further to some embodiments, the techniques can determine that the image is to be partitioned into multiple sub-images that can each be processed and reassembled to display the image. The sub-images can each be rendered by a graphics processing functionality (e.g., a graphics processing unit) and displayed on a display device to present a version of the image in its native resolution.

Abstract: In one or more embodiments, a framework is provided in which image decoding can be delayed based on heuristics, and later initiated based on a use type associated with the image or the likelihood that the image is going to be used. For example, a use history and priority system can enable images that are currently being rendered and/or are likely to get rendered to be decoded before images that have a history of being downloaded but never used. Accordingly, by decoupling image download from image decoding, CPU resources and memory can be more efficiently utilized.

Abstract: In one or more embodiments, a framework is provided in which image decoding can be delayed based on heuristics, and later initiated based on a use type associated with the image or the likelihood that the image is going to be used. For example, a use history and priority system can enable images that are currently being rendered and/or are likely to get rendered to be decoded before images that have a history of being downloaded but never used. Accordingly, by decoupling image download from image decoding, CPU resources and memory can be more efficiently utilized.

Abstract: Techniques for surface caching are described in which a cache for surfaces is provided to enable existing surfaces to be reused. Surfaces in the cache can be assigned to one of multiple surface lists used to service requests for surfaces. The multiple lists can include at least a main list and an auxiliary list configured to group existing surfaces according to corresponding surface constraints. When a surface is requested, the multiple lists can be searched to find an existing surface based on constraints including, for example, the type of surface and size requirements for the requested surface. If an existing surface is discovered, the existing surface can be returned to service the request. If a suitable surface is not found in the multiple lists, a new surface is created for the request and the new surface can be added to a corresponding one of the multiple surface lists.

Abstract: In one or more embodiments, a framework is provided in which image decoding can be delayed based on heuristics, and later initiated based on a use type associated with the image or the likelihood that the image is going to be used. For example, a use history and priority system can enable images that are currently being rendered and/or are likely to get rendered to be decoded before images that have a history of being downloaded but never used. Accordingly, by decoupling image download from image decoding, CPU resources and memory can be more efficiently utilized.

Abstract: Techniques for hardware accelerated caret rendering are described in which a system based caret is emulated using hardware acceleration technology. The hardware accelerated caret can be rendered using dedicated graphics processing hardware to look and feel like a system caret. This can involve using pixel shaders to produce the hardware accelerated caret and a employing a back-up texture to remove the caret after it is drawn and cause the caret to blink. In addition, rendering of the caret can be coordinated with other animations and/or other presentations of a frame buffer to piggy back drawing of the caret onto other drawing operations. This can reduce the number of times the frame buffer is presented and therefore improve performance.

Abstract: Techniques for hardware accelerated caret rendering are described in which a system based caret is emulated using hardware acceleration technology. The hardware accelerated caret can be rendered using dedicated graphics processing hardware to look and feel like a system caret. This can involve using pixel shaders to produce the hardware accelerated caret and a employing a back-up texture to remove the caret after it is drawn and cause the caret to blink. In addition, rendering of the caret can be coordinated with other animations and/or other presentations of a frame buffer to piggy back drawing of the caret onto other drawing operations. This can reduce the number of times the frame buffer is presented and therefore improve performance.

Abstract: Techniques for surface caching are described in which a cache for surfaces is provided to enable existing surfaces to be reused. Surfaces in the cache can be assigned to one of multiple surface lists used to service requests for surfaces. The multiple lists can include at least a main list and an auxiliary list configured to group existing surfaces according to corresponding surface constraints. When a surface is requested, the multiple lists can be searched to find an existing surface based on constraints including, for example, the type of surface and size requirements for the requested surface. If an existing surface is discovered, the existing surface can be returned to service the request. If a suitable surface is not found in the multiple lists, a new surface is created for the request and the new surface can be added to a corresponding one of the multiple surface lists.

Abstract: Various embodiments provide techniques for partitioning high resolution images into sub-images for display. In at least some embodiments, the techniques can enable a device to display an image in its native resolution (e.g., the image capture resolution) even when the image exceeds a threshold image size for the device. In example implementations, techniques determine that a size of an image exceeds a threshold image size for a system. Further to some embodiments, the techniques can determine that the image is to be partitioned into multiple sub-images that can each be processed and reassembled to display the image. The sub-images can each be rendered by a graphics processing functionality (e.g., a graphics processing unit) and displayed on a display device to present a version of the image in its native resolution.

Abstract: In one or more embodiments, a framework is provided in which image decoding can be delayed based on heuristics, and later initiated based on a use type associated with the image or the likelihood that the image is going to be used. For example, a use history and priority system can enable images that are currently being rendered and/or are likely to get rendered to be decoded before images that have a history of being downloaded but never used. Accordingly, by decoupling image download from image decoding, CPU resources and memory can be more efficiently utilized.

Abstract: Techniques for hardware accelerated caret rendering are described in which a system based caret is emulated using hardware acceleration technology. The hardware accelerated caret can be rendered using dedicated graphics processing hardware to look and feel like a system caret. This can involve using pixel shaders to produce the hardware accelerated caret and a employing a back-up texture to remove the caret after it is drawn and cause the caret to blink. In addition, rendering of the caret can be coordinated with other animations and/or other presentations of a frame buffer to piggy back drawing of the caret onto other drawing operations. This can reduce the number of times the frame buffer is presented and therefore improve performance.