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.

Abstract: Methods and apparatus relating to tile-aware sector cache for graphics are described. One embodiment enables a sector cache implementation (e.g., in graphics implementations) to reduce the size of the tag space. The reduction in tag space, in turn, reduces power consumption, (e.g., via reduced ways). Moreover, cache efficiency is maintained by keeping the sector utilization at a high rate in one or more embodiments. Other embodiments are also disclosed and claimed.

Abstract: An apparatus to facilitate doorbell notifications is disclosed. The apparatus includes memory-mapped I/O (MMIO) base address registers including a physical function (PF) and plurality of virtual functions (VF), wherein each function's base address register comprises a plurality of doorbell pages and doorbell hardware including doorbell registers, each having an assignable function identifier (ID) and offset, and comprising a plurality of doorbells to activate a doorbell notification in response to receiving a doorbell trigger from an associated doorbell page set upon detection of an access request.

Abstract: An apparatus to facilitate doorbell notifications is disclosed. The apparatus includes memory-mapped I/O (MMIO) base address registers including a physical function (PF) and plurality of virtual functions (VF), wherein each function's base address register comprises a plurality of doorbell pages and doorbell hardware including doorbell registers, each having an assignable function identifier (ID) and offset, and comprising a plurality of doorbells to activate a doorbell notification in response to receiving a doorbell trigger from an associated doorbell page set upon detection of an access request.

Abstract: Apparatus and method for simultaneous command streamers. For example, one embodiment of an apparatus comprises: a plurality of work element queues to store work elements for a plurality of thread contexts, each work element associated with a context descriptor identifying a context storage region in memory; a plurality of command streamers, each command streamer associated with one of the plurality of work element queues, the command streamers to independently submit instructions for execution as specified by the work elements; a thread dispatcher to evaluate the thread contexts including priority values, to tag each instruction with an execution identifier (ID), and to responsively dispatch each instruction including the execution ID in accordance with the thread context; and a plurality of graphics functional units to independently execute each instruction dispatched by the thread dispatcher and to associate each instruction with a thread context based on its execution ID.

Abstract: A processing apparatus is described. The apparatus includes a graphics processing unit (GPU), including a register file having a plurality of channels to store data and an execution unit to examine data at each of the plurality of channels, read a data value from a first of the plurality of channels upon a determination that each of the plurality of channels has the same data and execute a single input multi data (SIMD) instruction based on the data value.

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 and method for scalable interrupt reporting.

Abstract: In one embodiment, a method includes: receiving, in a root tile of an accelerator device having a plurality of tiles, a message from a processor, the message comprising a register write request to a register of a first remote tile of the plurality of remote tiles; decoding, in an endpoint controller of the root tile, a system address of the message to identify a destination tile for the message, based at least in part on a base address register decode of the system address; and in response to identifying the first remote tile as the destination tile, updating a first portion of an address offset field of the system address to a predetermined value and directing the message to the first remote tile coupled to the root tile via a sideband interconnect. Other embodiments are described and claimed.

Abstract: A processing apparatus is described. The apparatus includes a graphics processing unit (GPU), including a register file having a plurality of channels to store data and an execution unit to examine data at each of the plurality of channels, read a data value from a first of the plurality of channels upon a determination that each of the plurality of channels has the same data and execute a single input multi data (SIMD) instruction based on the data value.

Abstract: Techniques are disclosed for processing rendering engine workload of a graphics system in a secure fashion, wherein at least some security processing of the workload is offloaded from software-based security parsing to hardware-based security parsing. In some embodiments, commands from a given application are received by a user mode driver (UMD), which is configured to generate a command buffer delineated into privileged and/or non-privileged command sections. The delineated command buffer can then be passed by the UMD to a kernel-mode driver (KMD), which is configured to parse and validate only privileged buffer sections, but to issue all other batch buffers with a privilege indicator set to non-privileged.

Abstract: Described herein are computer graphics technologies to facilitate effective and efficient memory handling for blocks of memory including texture maps. More particularly, one or more implementations described herein facilitates hierarchical lossless compression of memory with null data support for memory resources, including texture maps. More particularly still, one or more implementations described herein facilitates the use of meta-data for lossless compression and the support of null encodings for Tiled Resources. This technology also permits use of the fast-clear compression method, where meta-data specifies that the entire access should return some specified clear value.

Abstract: Methods and apparatus relating to tile-aware sector cache for graphics are described. One embodiment enables a sector cache implementation (e.g., in graphics implementations) to reduce the size of the tag space. The reduction in tag space, in turn, reduces power consumption, (e.g., via reduced ways). Moreover, cache efficiency is maintained by keeping the sector utilization at a high rate in one or more embodiments. Other embodiments are also disclosed and claimed.

Abstract: Systems, apparatus and methods are described including distributing batches of geometric objects to a multi-core system, at each processor core, performing vertex processing and geometry setup processing on the corresponding batch of geometric objects, storing the vertex processing results shared memory accessible to all of the cores, and storing the geometry setup processing results in local storage. Each particular core may then perform rasterization using geometry setup results obtained from local storage within the particular core and from local storage of at least one of the other processor cores.

Abstract: In an embodiment, a system includes a graphics processing unit (GPU) that includes one or more GPU engines, and a microcontroller. The microcontroller is to assign a respective schedule slot for each of a plurality of virtual machines (VMs). When a particular VM is scheduled to access a first GPU engine, the particular VM has exclusive access to the first GPU engine. Other embodiments are described and claimed.

Abstract: Memory-based semaphores are described that are useful for synchronizing processes between different processing engines. In one example, operations include executing a first process at a first processing engine, the executing including updating a memory register, sending a signal from the first processing engine to a second processing engine that the memory register has been updated, the signal including a memory register address to identify the updated memory register inline data and a dataword, fetching data from the memory register by the second processing engine, comparing the fetched data to the received dataword, and conditionally executing a next command of a second process at the second processing engine based on the comparison.

Abstract: A processing apparatus is described. The apparatus includes a graphics processing unit (GPU), including a register file having a plurality of channels to store data and an execution unit to examine data at each of the plurality of channels, read a data value from a first of the plurality of channels upon a determination that each of the plurality of channels has the same data and execute a single input multi data (SIMD) instruction based on the data value.

Abstract: Methods and apparatus relating to mid-thread pre-emption with software assisted context switch are described. In an embodiment, one or more threads executing on a Graphics Processing Unit (GPU) are stopped at an instruction level granularity in response to a request to pre-empt the one or more threads. The context data of the one or more threads is copied to memory in response to completion of the one or more threads at the instruction level granularity and/or one or more instructions. Other embodiments are also disclosed and claimed.

Abstract: Systems and methods may provide for receiving a plurality of signals from a software module associated with a shared resource such as, for example, an unordered access view (UAV). The plurality of signals may include a first signal that indicates whether a draw call accesses the shared resource, a second signal that indicates whether a boundary of the draw call has been reached, and a third signal that indicates whether the draw call has a coherency requirement. Additionally, a workload corresponding to the draw call may be selectively dispatched in a shader invocation based on the plurality of signals.

Abstract: Methods and apparatus are disclosed for efficient TLB (translation look-aside buffer) shoot-downs for heterogeneous devices sharing virtual memory in a multi-core system. Embodiments of an apparatus for efficient TLB shoot-downs may include a TLB to store virtual address translation entries, and a memory management unit, coupled with the TLB, to maintain PASID (process address space identifier) state entries corresponding to the virtual address translation entries. The PASID state entries may include an active reference state and a lazy-invalidation state. The memory management unit may perform atomic modification of PASID state entries responsive to receiving PASID state update requests from devices in the multi-core system and read the lazy-invalidation state of the PASID state entries. The memory management unit may send PASID state update responses to the devices to synchronize TLB entries prior to activation responsive to the respective lazy-invalidation state.