Abstract: Techniques are disclosed relating to performing mid-render auxiliary compute tasks for graphics processing. In some embodiments, auxiliary compute tasks are performed during a render pass, using at least a portion of a memory context of the render pass, without accessing a shared memory during the render pass. Relative to flushing render data to shared memory to perform compute tasks, this may reduce memory accesses and/or cache thrashing, which may in turn increase performance and/or reduce power consumption.

Abstract: Ubershaders may be used in a graphics development environment as an efficiency tool because many options and properties may be captured in a single shader program. Each selectable option of property in the shader code may be tagged with an attribute to indicate the presence of the selection. The single shader program embodying the many selectable options and properties may be compiled to an intermediate version that also embodies the many options and properties, along with at least remnants of the tagging attributes. Upon a request for executable code including indications of the desired selectable options or properties, generation of the executable code may proceed such that it includes only the desire selectable options and properties and not other selectable options and properties embodied in the source code.

Abstract: A method and an apparatus for a parallel computing program calling APIs (application programming interfaces) in a host processor to perform a data processing task in parallel among compute units are described. The compute units are coupled to the host processor including central processing units (CPUs) and graphic processing units (GPUs). A program object corresponding to a source code for the data processing task is generated in a memory coupled to the host processor according to the API calls. Executable codes for the compute units are generated from the program object according to the API calls to be loaded for concurrent execution among the compute units to perform the data processing task.

Abstract: A method and an apparatus that allocate one or more physical compute devices such as CPUs or GPUs attached to a host processing unit running an application for executing one or more threads of the application are described. The allocation may be based on data representing a processing capability requirement from the application for executing an executable in the one or more threads. A compute device identifier may be associated with the allocated physical compute devices to schedule and execute the executable in the one or more threads concurrently in one or more of the allocated physical compute devices concurrently.

Abstract: Techniques are disclosed relating to performing mid-render auxiliary compute tasks for graphics processing. In some embodiments, auxiliary compute tasks are performed during a render pass, using at least a portion of a memory context of the render pass, without accessing a shared memory during the render pass. Relative to flushing render data to shared memory to perform compute tasks, this may reduce memory accesses and/or cache thrashing, which may in turn increase performance and/or reduce power consumption.

Abstract: Techniques are disclosed relating to a hardware-supported flexible data structure for graphics processing. In some embodiments, dimensions of the data structure are configurable in an X direction, a Y direction, a number of samples per pixel, and an amount of data per sample. In some embodiments, these attributes are configurable using hardware registers. In some embodiments, the data structure is persistent across a tile being processed such that local memory context is accessible to both rendering threads of a render pass and mid-render compute threads.

Abstract: Techniques are disclosed relating to memory consistency in a memory hierarchy with relaxed ordering. In some embodiments, an apparatus includes a first level cache that is shared by a plurality of shader processing elements and a second level cache that is shared by the shader processing elements and at least a texture processing unit. In some embodiments, the apparatus is configured to execute operations specified by graphics instructions that include (1) an attribute of the operation that specifies a type of memory consistency to be imposed for the operation and (2) scope information for the attribute that specifies whether the memory consistency specified by the attribute should be enforced at the first level cache or the second level cache. In some embodiments, the apparatus is configured to determine whether to sequence memory accesses at the first level cache and the second level cache based on the attribute and the scope.

Abstract: A method and an apparatus that allocate one or more physical compute devices such as CPUs (Central Processing Units) or GPUs (Graphical Processing Units) attached to a host processing unit running an application for executing one or more threads of the application are described. The allocation may be based on data representing a processing capability requirement from the application for executing an executable in the one or more threads. A compute device identifier may be associated with the allocated physical compute devices to schedule and execute the executable in the one or more threads concurrently in one or more of the allocated physical compute devices concurrently.

Abstract: A method and an apparatus that execute a parallel computing program in a programming language for a parallel computing architecture are described. The parallel computing program is stored in memory in a system with parallel processors. The parallel computing program is stored in a memory to allocate threads between a host processor and a GPU. The programming language includes an API to allow an application to make calls using the API to allocate execution of the threads between the host processor and the GPU. The programming language includes host function data tokens for host functions performed in the host processor and kernel function data tokens for compute kernel functions performed in one or more compute processors, e.g., GPUs or CPUs, separate from the host processor.

Abstract: An improved tessellation graphics pipeline that obviates that use of early stage vertex shaders and hull shaders and allows greater efficiency and flexibility. Embodiments provide a graphics pipeline beginning with a tessellator that may obtain tessellation factors in any manner such as reading from a memory of factors provided by a developer or computing the factors using a compute kernel. In some embodiments, a single vertex shader may follow the tessellator and perform all the necessary vertex shading for the pipeline. Furthermore, in some embodiments, a compute kernel is used to generate the tessellation factors. The compute kernel provides flexibility that allows its employment for some graphic portions and not others. In addition, the streamlined pipeline facilitates the efficient use of scaling to determine tessellation factors for the same graphic portion at different camera distances or desired levels of replication of the mathematical model.

Abstract: A system decouples the source code language from the eventual execution environment by compiling the source code language into a unified intermediate representation that conforms to a language model allowing both parallel graphical operations and parallel general-purpose computational operations. The intermediate representation may then be distributed to end-user computers, where an embedded compiler can compile the intermediate representation into an executable binary targeted for the CPUs and GPUs available in that end-user device. The intermediate representation is sufficient to define both graphics and non-graphics compute kernels and shaders. At install-time or later, the intermediate representation file may be compiled for the specific target hardware of the given end-user computing system.

Abstract: A method and an apparatus that execute a parallel computing program in a programming language for a parallel computing architecture are described. The parallel computing program is stored in memory in a system with parallel processors. The system includes a host processor, a graphics processing unit (GPU) coupled to the host processor and a memory coupled to at least one of the host processor and the GPU. The parallel computing program is stored in the memory to allocate threads between the host processor and the GPU. The programming language includes an API to allow an application to make calls using the API to allocate execution of the threads between the host processor and the GPU. The programming language includes host function data tokens for host functions performed in the host processor and kernel function data tokens for compute kernel functions performed in one or more compute processors, e.g. GPUs or CPUs, separate from the host processor.

Abstract: A system decouples the source code language from the eventual execution environment by compiling the source code language into a unified intermediate representation that conforms to a language model allowing both parallel graphical operations and parallel general-purpose computational operations. The intermediate representation may then be distributed to end-user computers, where an embedded compiler can compile the intermediate representation into an executable binary targeted for the CPUs and GPUs available in that end-user device. The intermediate representation is sufficient to define both graphics and non-graphics compute kernels and shaders. At install-time or later, the intermediate representation file may be compiled for the specific target hardware of the given end-user computing system.

Abstract: A method and an apparatus that partition a total number of threads to concurrently execute executable codes compiled from a single source for target processing units in response to an API (Application Programming Interface) request from an application running in a host processing unit are described. The total number of threads is based on a multi-dimensional value for a global thread number specified in the API. The target processing units include GPUs (Graphics Processing Unit) and CPUs (Central Processing Unit). Thread group sizes for the target processing units are determined to partition the total number of threads according to either a dimension for a data parallel task associated with the executable codes or a dimension for a multi-dimensional value for a local thread group number. The executable codes are loaded to be executed in thread groups with the determined thread group sizes concurrently in the target processing units.

Abstract: A method and an apparatus for a parallel computing program using subbuffers to perform a data processing task in parallel among heterogeneous compute units are described. The compute units can include a heterogeneous mix of central processing units (CPUs) and graphic processing units (GPUs). A system creates a subbuffer from a parent buffer for each of a plurality of heterogeneous compute units. If a subbuffer is not associated with the same compute unit as the parent buffer, the system copies data from the subbuffer to memory of that compute unit. The system further tracks updates to the data and transfers those updates back to the subbuffer.

Abstract: Ubershaders may be used in a graphics development environment as an efficiency tool because many options and properties may be captured in a single shader program. Each selectable option of property in the shader code may be tagged with an attribute to indicate the presence of the selection. The single shader program embodying the many selectable options and properties may be compiled to an intermediate version that also embodies the many options and properties, along with at least remnants of the tagging attributes. Upon a request for executable code including indications of the desired selectable options or properties, generation of the executable code may proceed such that it includes only the desire selectable options and properties and not other selectable options and properties embodied in the source code.

Abstract: A method and an apparatus for a parallel computing program calling APIs (application programming interfaces) in a host processor to perform a data processing task in parallel among compute units are described. The compute units are coupled to the host processor including central processing units (CPUs) and graphic processing units (GPUs). A program object corresponding to a source code for the data processing task is generated in a memory coupled to the host processor according to the API calls. Executable codes for the compute units are generated from the program object according to the API calls to be loaded for concurrent execution among the compute units to perform the data processing task.

Abstract: A method and an apparatus that allocate one or more physical compute devices such as CPUs or GPUs attached to a host processing unit running an application for executing one or more threads of the application are described. The allocation may be based on data representing a processing capability requirement from the application for executing an executable in the one or more threads. A compute device identifier may be associated with the allocated physical compute devices to schedule and execute the executable in the one or more threads concurrently in one or more of the allocated physical compute devices concurrently.

Abstract: A method and an apparatus that schedule a plurality of executables in a schedule queue for execution in one or more physical compute devices such as CPUs or GPUs concurrently are described. One or more executables are compiled online from a source having an existing executable for a type of physical compute devices different from the one or more physical compute devices. Dependency relations among elements corresponding to scheduled executables are determined to select an executable to be executed by a plurality of threads concurrently in more than one of the physical compute devices.

Abstract: A method and an apparatus for a parallel computing program calling APIs (application programming interfaces) in a host processor to perform a data processing task in parallel among compute units are described. The compute units are coupled to the host processor including central processing units (CPUs) and graphic processing units (GPUs). A program object corresponding to a source code for the data processing task is generated in a memory coupled to the host processor according to the API calls. Executable codes for the compute units are generated from the program object according to the API calls to be loaded for concurrent execution among the compute units to perform the data processing task.