Abstract: Disclosed techniques relate to work distribution in graphics processors. In some embodiments, an apparatus includes circuitry that implements a plurality of logical slots and a set of graphics processor sub-units that each implement multiple distributed hardware slots. The circuitry may determine different distribution rules for first and second sets of graphics work and map logical slots to distributed hardware slots based on the distribution rules. In various embodiments, disclosed techniques may advantageously distribute work efficiently across distributed shader processors for graphics kicks of various sizes.

Abstract: Disclosed embodiments relate to controlling sets of graphics work (e.g., kicks) assigned to graphics processor circuitry. In some embodiments, tracking slot circuitry implements entries for multiple tracking slots. Slot manager circuitry may store, using an entry of the tracking slot circuitry, software-specified information for a set of graphics work, where the information includes: type of work, dependencies on other sets of graphics work, and location of data for the set of graphics work. The slot manager circuitry may prefetch, from the location and prior to allocating shader core resources for the set of graphics work, configuration register data for the set of graphics work. Control circuitry may program configuration registers for the set of graphics work using the prefetched data and initiate processing of the set of graphics work by the graphics processor circuitry according to the dependencies. Disclosed techniques may reduce kick-to-kick transition time, in some embodiments.

Abstract: Systems, apparatuses, and methods for efficiently allocating data in a cache are described. In various embodiments, a processor decodes an indication in a software application identifying a temporal data set. The data set is flagged with a data set identifier (DSID) indicating temporal data to drop after consumption. When the data set is allocated in a cache, the data set is stored with a non-replaceable attribute to prevent a cache replacement policy from evicting the data set before it is dropped. A drop command with an indication of the DSID of the data set is later issued after the data set is read (consumed). A copy of the data set is not written back to the lower-level memory although the data set is removed from the cache. An interrupt is generated to notify firmware or other software of the completion of the drop command.

Abstract: Systems, apparatuses, and methods for efficiently allocating data in a cache are described. In various embodiments, a processor decodes an indication in a software application identifying a temporal data set. The data set is flagged with a data set identifier (DSID) indicating temporal data to drop after consumption. When the data set is allocated in a cache, the data set is stored with a non-replaceable attribute to prevent a cache replacement policy from evicting the data set before it is dropped. A drop command with an indication of the DSID of the data set is later issued after the data set is read (consumed). A copy of the data set is not written back to the lower-level memory although the data set is removed from the cache. An interrupt is generated to notify firmware or other software of the completion of the drop command.

Abstract: Systems, apparatuses, and methods for efficiently allocating data in a cache are described. In various embodiments, a processor decodes an indication in a software application identifying a temporal data set. The data set is flagged with a data set identifier (DSID) indicating temporal data to drop after consumption. When the data set is allocated in a cache, the data set is stored with a non-replaceable attribute to prevent a cache replacement policy from evicting the data set before it is dropped. A drop command with an indication of the DSID of the data set is later issued after the data set is read (consumed). A copy of the data set is not written back to the lower-level memory although the data set is removed from the cache. An interrupt is generated to notify firmware or other software of the completion of the drop command.

Abstract: Systems, apparatuses, and methods for efficiently allocating data in a cache are described. In various embodiments, a processor decodes an indication in a software application identifying a temporal data set. The data set is flagged with a data set identifier (DSID) indicating temporal data to drop after consumption. When the data set is allocated in a cache, the data set is stored with a non-replaceable attribute to prevent a cache replacement policy from evicting the data set before it is dropped. A drop command with an indication of the DSID of the data set is later issued after the data set is read (consumed). A copy of the data set is not written back to the lower-level memory although the data set is removed from the cache. An interrupt is generated to notify firmware or other software of the completion of the drop command.

Abstract: A method of processing commands is provided. The method includes holding commands in queues and executing the commands in an order based on their respective priority. Commands having the same priority are held in the same queue.

Abstract: Techniques are disclosed relating to flushing cache lines. In some embodiments, a graphics processing unit includes a cache and one or more storage elements configured to store a plurality of command buffers that include instructions executable to manipulate data stored in the cache. In some embodiments, ones of the cache lines in the cache are configured to store data to be operated on by instructions in the command buffers and a first tag portion that identifies a command buffer that has stored data in the cache line. In some embodiments, the graphics processing unit is configured to receive a request to flush cache lines that store data of a particular command buffer, and to flush ones of the cache lines having first tag portions indicating the particular command buffer as having data stored in the cache lines while maintaining data stored in other ones of the cache lines as valid.

Abstract: A method of processing commands is provided. The method includes holding commands in queues and executing the commands in an order based on their respective priority. Commands having the same priority are held in the same queue.

Abstract: A method of processing commands is provided. The method includes holding commands in queues and executing the commands in an order based on their respective priority. Commands having the same priority are held in the same queue.

Abstract: The present disclosure provides for systems and methods to process a non-resident page that may include attempting to access the non-resident page, an address for the non-resident page pointing to a memory page containing default values, determining that the non-resident page should not cause a page fault based on an indicator indicating that a particular non-resident page should not generate a page fault, returning an indication that a memory read did not translate and returning the default value when the access of the non-resident page is a read and the non-resident page should not cause a page fault. Another example may discontinue a write when the access of the non-resident page is a write and the non-resident page should not cause a page fault.

Abstract: The present disclosure provides for systems and methods to process a non-resident page that may include attempting to access the non-resident page, an address for the non-resident page pointing to a memory page containing default values, determining that the non-resident page should not cause a page fault based on an indicator indicating that a particular non-resident page should not generate a page fault, returning an indication that a memory read did not translate and returning the default value when the access of the non-resident page is a read and the non-resident page should not cause a page fault. Another example may discontinue a write when the access of the non-resident page is a write and the non-resident page should not cause a page fault.

Abstract: A multiprocessor system includes a plurality of special purpose processors that perform different portions of a related processing task. A set of commands that cause each of the processors to perform the portions of the related task are distributed, and the set of commands includes a predicated execution command that precedes other commands within the set of commands. It is determined whether commands subsequent to the predicated execution command are intended to be executed by a first processor or a second processor based on information in the predicated execution command and the set of commands includes all commands to be executed by each processor.

Abstract: A method of managing resources is provided. The method includes identifying a resource associated with a processor responsive to an impending transition, and copying the identified resource from a memory associated with the GPU or to the memory associated with the GPU.

Abstract: A processing unit, method, and graphics processing system are provided for processing a plurality of frames of graphics data. For instance, the processing unit can include a first plurality of graphics processing units (GPUs), a second plurality of GPUs, and a plurality of compositors. The first plurality of GPUs can be configured to process a first frame of graphics data. Likewise, the second plurality of GPUs can be configured to process a second frame of graphics data. Further, each compositor in the plurality of compositors can be coupled to a respective GPU from the first and second pluralities of GPUs, where the plurality of compositors is configured to sequentially pass the first and second frames of graphics data to a display module.

Abstract: A method, computer program product, and computing system are provided for processing a graphics operation. For instance, the method can include receiving the graphics operation from an application. The method can also include allocating a first portion of the graphics operation to a first processing unit and a second portion of the graphics operation to a second processing unit. This allocation between the first and second processing units can be based on at least one of a performance profile and a functionality profile of the first and second processing units.

Abstract: A method of processing commands is provided. The method includes holding commands in queues and executing the commands in an order based on their respective priority. Commands having the same priority are held in the same queue.

Abstract: A multiprocessor system includes a plurality of special purpose processors that perform different portions of a related processing task. A set of commands that cause each of the processors to perform the portions of the related task are distributed, and the set of commands includes a predicated execution command that precedes other commands within the set of commands. It is determined whether commands subsequent to the predicated execution command are intended to be executed by a first processor or a second processor based on information in the predicated execution command and the set of commands includes all commands to be executed by each processor.

Abstract: A system and method for applying non-homogeneous properties to multiple video processing units (VPUs) in a multiple VPU system are described. Respective VPUs in the system cooperate to produce a frame to be displayed. In various embodiments, data output by different VPUs in the system is combined, or merged, or composited to produce a frame to be displayed. In load balancing modes, each VPU in the system performs different tasks as part of rendering a same frame, and therefore typically executes different commands. In various embodiments, efficiency of the system is enhanced by forming a single command buffer for execution by all of the VPUs in the system even though each VPU may have a different set of commands to execute in the command buffer.

Abstract: A method of managing resources is provided. The method includes identifying a resource associated with a processor responsive to an impending transition, and copying the identified resource from a memory associated with the GPU or to the memory associated with the GPU.