Abstract: Embodiments described herein provide a graphics, media, and compute device having a tiled architecture composed of a number of tiles of smaller graphics devices. The work distribution infrastructure for such device enables the distribution of workloads across multiple tiles of the device. Work items can be submitted to any one or more of the multiple tiles, with workloads able to span multiple tiles. Additionally, upon completion of a work item, graphics, media, and/or compute engines within the device can readily acquire new work items for execution with minimal latency.

Abstract: An apparatus comprising a sorting unit to sort primitives of a graphics image, the primitives to be grouped, each group to form a first level node of a hierarchical acceleration structure; a parallel reconfigurable clustering array to construct the hierarchical acceleration structure, the parallel reconfigurable clustering array comprising a plurality of processing clusters, each cluster comprising: parallel efficiency analysis circuitry to evaluate different groupings of the first level nodes for a next level of the hierarchical acceleration structure to determine efficiency values for the different groupings; and node merge circuitry to merge the first level nodes based on the efficiency values to form second level nodes.

Abstract: A graphics processing apparatus includes a graphics processor and a constant cache. The graphics processor has a number of execution instances that will generate requests for constant data from the constant cache. The constant cache stores constants of multiple constant types. The constant cache has a single level of hierarchy to store the constant data. The constant cache has a banking structure based on the number of execution instances, where the execution instances generate requests for the constant data with unified messaging that is the same for the different types of constant data.

Abstract: Described herein are devices, systems and methods to utilize non-volatile memory to save and retrieve data that is used to accelerate the load and resume of GPU accelerated applications. Non-volatile memory and GPU logic are configured to enable the GPU to directly access the non-volatile memory to enable data to be read without requiring the data to traverse the CPU and CPU memory. This data access path creates a faster method for loading data into GPU local memory.

Abstract: Position-based rendering apparatus and method for multi-die/GPU graphics processing. For example, one embodiment of a method comprises: distributing a plurality of graphics draws to a plurality of graphics processors; performing position-only shading using vertex data associated with tiles of a first draw on a first graphics processor, the first graphics processor responsively generating visibility data for each of the tiles; distributing subsets of the visibility data associated with different subsets of the tiles to different graphics processors; limiting geometry work to be performed on each tile by each graphics processor using the visibility data, each graphics processor to responsively generate rendered tiles; and wherein the rendered tiles are combined to generate a complete image frame.

Abstract: Apparatus and method for speculative execution of hit and intersection shaders on programmable ray tracing architectures. For example, one embodiment of an apparatus comprises: single-instruction multiple-data (SIMD) or single-instruction multiple-thread (SIMT) execution units (EUs) to execute shaders; and ray tracing circuitry to execute a ray traversal thread, the ray tracing engine comprising: traversal/intersection circuitry, responsive to the traversal thread, to traverse a ray through an acceleration data structure comprising a plurality of hierarchically arranged nodes and to intersect the ray with a primitive contained within at least one of the nodes; and shader deferral circuitry to defer and aggregate multiple shader invocations resulting from the traversal thread until a particular triggering event is detected, wherein the multiple shaders are to be dispatched on the EUs in a single shader batch upon detection of the triggering event.

Abstract: An apparatus to facilitate dynamic cache control is disclosed. The apparatus includes one or more processors to profile execution characteristics of a graphics workload at a processing resource to generate profile data indicating a quantity of cache hits that occur at a cache memory and apply one or more cache settings to the cache memory based on the profile data.

Abstract: A memory local to a graphics execution unit stores a shareable resource that has a constant value across different instances of an application. The system can include a shared resource manager to identify resources of an application as static resources. For multiple instances of the application executed on the graphics execution unit, the shared resource manager makes the static resource shareable among the multiple instances of the application, and maps the static resource to the multiple instances for runtime execution. The graphic execution unit executes the multiple instances of the application.

Abstract: An apparatus comprising a sorting unit to sort primitives of a graphics image, the primitives to be grouped, each group to form a first level node of a hierarchical acceleration structure; a parallel reconfigurable clustering array to construct the hierarchical acceleration structure, the parallel reconfigurable clustering array comprising a plurality of processing clusters, each cluster comprising: parallel efficiency analysis circuitry to evaluate different groupings of the first level nodes for a next level of the hierarchical acceleration structure to determine efficiency values for the different groupings; and node merge circuitry to merge the first level nodes based on the efficiency values to form second level nodes.

Abstract: Methods, systems and apparatuses may provide for technology that determines measured timing data in response to a presentation request from an application, wherein the measured timing data is associated with one or more previous frames and the presentation request is associated with one or more subsequent frames. The technology may also determine scheduling times for the subsequent frame(s) based on the measured timing data, wherein the scheduling times include a simulation time, a rendering time, a driver submission time, a hardware submission time, and a display time. In one example, the technology controls a pacing of the subsequent frame(s) on a display in accordance with the scheduling times.

Abstract: Systems, methods and apparatuses may provide for technology to reduce rendering overhead associated with light field displays. The technology may conduct data formatting, re-projection, foveation, tile binning and/or image warping operations with respect to a plurality of display planes in a light field display.

Abstract: Embodiments are generally directed to GPU mixed primitive topology type processing. An embodiment of an apparatus includes one or more processor cores; and a memory to store data for graphics processing, wherein the one or more processing cores are to generate in the memory a vertex buffer to store vertex data for a mesh to be rendered and an index buffer to index the vertex data stored in the vertex buffer, the index buffer being structured to include index data for multiple primitive topology types. The one or more processor cores are to process the index data for the plurality of primitive topology types from the index buffer and fetch vertex data from the vertex buffer; and are to set up each primitive topology type of the plurality of primitive topology types for processing in a single draw operation.

Abstract: An apparatus to facilitate dynamic cache control is disclosed. The apparatus includes one or more processors to profile execution characteristics of a graphics workload at a processing resource to generate profile data indicating a quantity of cache hits that occur at a cache memory and apply one or more cache settings to the cache memory based on the profile data.

Abstract: Described herein are devices, systems and methods to utilize non-volatile memory to save and retrieve data that is used to accelerate the load and resume of GPU accelerated applications. Non-volatile memory and GPU logic are configured to enable the GPU to directly access the non-volatile memory to enable data to be read without requiring the data to traverse the CPU and CPU memory. This data access path creates a faster method for loading data into GPU local memory.

Abstract: Apparatus and method for speculative execution of hit and intersection shaders on programmable ray tracing architectures. For example, one embodiment of an apparatus comprises: single-instruction multiple-data (SIMD) or single-instruction multiple-thread (SIMT) execution units (EUs) to execute shaders; and ray tracing circuitry to execute a ray traversal thread, the ray tracing engine comprising: traversal/intersection circuitry, responsive to the traversal thread, to traverse a ray through an acceleration data structure comprising a plurality of hierarchically arranged nodes and to intersect the ray with a primitive contained within at least one of the nodes; and shader deferral circuitry to defer and aggregate multiple shader invocations resulting from the traversal thread until a particular triggering event is detected, wherein the multiple shaders are to be dispatched on the EUs in a single shader batch upon detection of the triggering event.

Abstract: One embodiment provides a graphics processor comprising a hardware graphics rendering pipeline configured to perform multisample anti-aliasing, the hardware graphics rendering pipeline including pixel processing logic to determine that each sample location of a pixel of a multisample surface is associated with a clear value and resolve a color value for the pixel to a non-multisample surface via a write of metadata to indicate that the pixel has the clear value. The resolve can be a stenciled resolve that automatically bypasses execution of a pixel shader for pixels having clear color data.

Abstract: Position-based rendering apparatus and method for multi-die/GPU graphics processing. For example, one embodiment of a method comprises: distributing a plurality of graphics draws to a plurality of graphics processors; performing position-only shading using vertex data associated with tiles of a first draw on a first graphics processor, the first graphics processor responsively generating visibility data for each of the tiles; distributing subsets of the visibility data associated with different subsets of the tiles to different graphics processors; limiting geometry work to be performed on each tile by each graphics processor using the visibility data, each graphics processor to responsively generate rendered tiles; and wherein the rendered tiles are combined to generate a complete image frame.

Abstract: Systems, methods and apparatuses may provide for technology to reduce rendering overhead associated with light field displays. The technology may conduct data formatting, re-projection, foveation, tile binning and/or image warping operations with respect to a plurality of display planes in a light field display.

Abstract: Graphics processors for implementing multi-tile memory management are disclosed. In one embodiment, a graphics processor includes a first graphics device having a local memory, a second graphics device having a local memory, and a graphics driver to provide a single virtual allocation with a common virtual address range to mirror a resource to each local memory of the first and second graphics devices.

Abstract: An apparatus to facilitate asynchronous execution at a processing unit. The apparatus includes one or more processors to detect independent task passes that may be executed out of order in a pipeline of the processing unit, schedule a first set of processing tasks to be executed at a first set of processing elements at the processing unit and schedule a second set of tasks to be executed at a second set of processing elements, wherein execution of the first set of tasks at the first set of processing elements is to be performed simultaneous and in parallel to execution of the second set of tasks at the second set of processing elements.