Abstract: In an example, an apparatus comprises logic, at least partially comprising hardware logic, to receive an input from one or more detectors proximate a display to present an output from a graphics pipeline, determine that a user is not interacting with the display, and in response to a determination that the user is not interacting with the display, to reduce a frame rendering rate of the graphics pipeline. Other embodiments are also disclosed and claimed.

Abstract: An apparatus to facilitate compute optimization is disclosed. The apparatus includes a plurality of processing units each comprising a plurality of execution units (EUs), wherein the plurality of EUs comprise a first EU type and a second EU type.

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 dynamic provisioning and traffic control on a memory fabric.

Abstract: A processing apparatus is provided comprising a multiprocessor having a multithreaded architecture. The multiprocessor can execute at least one single instruction to perform parallel mixed precision matrix operations. In one embodiment the apparatus includes a memory interface and an array of multiprocessors coupled to the memory interface. At least one multiprocessor in the array of multiprocessors is configured to execute a fused multiply-add instruction in parallel across multiple threads.

Abstract: Methods and apparatus relating to techniques for a dual path sequential element to reduce toggles in data path are described. In an embodiment, switching logic causes signals for a single data path of a processor to be directed to at least two separate data paths. At least one of the two separate data paths is power gated to reduce signal toggles in the at least one data path. Other embodiments are also disclosed and claimed.

Abstract: One embodiment provides for a compute apparatus comprising a decode unit to decode a single instruction into a decoded instruction that specifies multiple operands including a multi-bit input value and a bipolar binary weight associated with a neural network and an arithmetic logic unit including a multiplier, an adder, and an accumulator register. To execute the decoded instruction, the multiplier is to perform a multiplication operation on the multi-bit input based on the bipolar binary weight to generate an intermediate product and the adder is to add the intermediate product to a value stored in the accumulator register and update the value stored in the accumulator register.

Abstract: Techniques to improve performance of matrix multiply operations are described in which a compute kernel can specify one or more element-wise operations to perform on output of the compute kernel before the output is transferred to higher levels of a processor memory hierarchy.

Abstract: A mechanism is described for facilitating optimization of cache associated with graphics processors at computing devices. A method of embodiments, as described herein, includes introducing coloring bits to contents of a cache associated with a processor including a graphics processor, wherein the coloring bits to represent a signal identifying one or more caches available for use, while avoiding explicit invalidations and flushes.

Abstract: Methods and apparatus relating to techniques for avoiding cache lookup for cold cache. In an example, an apparatus comprises logic, at least partially comprising hardware logic, to monitor a thread switching overhead parameter for an application executing in a processing system and in response to a determination that the thread switching overhead parameter exceeds a threshold, to activate a thread management algorithm to reduce thread switching in the processing system. Other embodiments are also disclosed and claimed.

Abstract: An apparatus and method are described for allocating local memories to virtual machines. For example, one embodiment of an apparatus comprises: a command streamer to queue commands from a plurality of virtual machines (VMs) or applications, the commands to be distributed from the command streamer and executed by graphics processing resources of a graphics processing unit (GPU); a tile cache to store graphics data associated with the plurality of VMs or applications as the commands are executed by the graphics processing resources; and tile cache allocation hardware logic to allocate a first portion of the tile cache to a first VM or application and a second portion of the tile cache to a second VM or application; the tile cache allocation hardware logic to further allocate a first region in system memory to store spill-over data when the first portion of the tile cache and/or the second portion of the file cache becomes full.

Abstract: A mechanism is described for facilitating inference coordination and processing utilization for machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting, at training time, information relating to one or more tasks to be performed according to a training dataset relating to a processor including a graphics processor. The method may further include analyzing the information to determine one or more portions of hardware relating to the processor capable of supporting the one or more tasks, and configuring the hardware to pre-select the one or more portions to perform the one or more tasks, while other portions of the hardware remain available for other tasks.

Abstract: Methods and apparatus relating to techniques for power management. In an example, an apparatus comprises logic, at least partially comprising hardware logic, to generate a voltage/frequency curve for at least one of a core or a sub-core in a processor and manage an operating voltage level of the at least one of a core or a sub-core using the voltage/frequency curve. Other embodiments are also disclosed and claimed.

Abstract: An apparatus to facilitate compute compression is disclosed. The apparatus includes a graphics processing unit including mapping logic to map a first block of integer pixel data to a compression block and compression logic to compress the compression block.

Abstract: One embodiment provides an apparatus comprising an interconnect fabric comprising one or more fabric switches, a plurality of memory interfaces coupled to the interconnect fabric to provide access to a plurality of memory devices, an input/output (TO) interface coupled to the interconnect fabric to provide access to IO devices, an array of multiprocessors coupled to the interconnect fabric, scheduling circuitry to distribute a plurality of thread groups across the array of multiprocessors, each thread group comprising a plurality of threads and each thread comprising a plurality of instructions to be executed by at least one of the multiprocessors, and a first multiprocessor of the array of multiprocessors to be assigned to process a first thread group comprising a first plurality of threads, the first multiprocessor comprising a plurality of parallel execution circuits.

Abstract: In an example, an apparatus comprises a plurality of execution units, and a cache memory communicatively coupled to the plurality of execution units, wherein the cache memory is structured into a plurality of sectors, wherein each sector in the plurality of sectors comprises at least two cache lines. Other embodiments are also disclosed and claimed.

Abstract: A mechanism is described for facilitating localized load-balancing for processors in computing devices. A method of embodiments, as described herein, includes facilitating hosting, at a processor of a computing device, a local load-balancing mechanism. The method may further include monitoring balancing of loads at the processor and serving as a local scheduler to maintain de-centralized load-balancing at the processor and between the processor and other one or more processors.

Abstract: A processing apparatus is provided comprising a multiprocessor having a multithreaded architecture. The multiprocessor can execute at least one single instruction to perform parallel mixed precision matrix operations. In one embodiment the apparatus includes a memory interface and an array of multiprocessors coupled to the memory interface. At least one multiprocessor in the array of multiprocessors is configured to execute a fused multiply-add instruction in parallel across multiple threads.

Abstract: Embodiments described herein provide techniques enable a compute unit to continue processing operations when all dispatched threads are blocked. One embodiment provides for a method comprising executing multiple concurrent threads on a processing resource of a graphics processor, during execution, detecting that each of the multiple concurrent threads of the processing resource are blocked from execution, selecting a victim thread from the multiple concurrent threads, and suspending the victim thread. The thread state is stored to a thread scratch space in memory along with a blocking event associated with the victim thread.

Abstract: An embodiment of a graphics apparatus may include a graphics processor including a kernel executor, and a security engine communicatively coupled to the graphics processor. The security engine may be configured to create a kernel security key, encrypt an executable kernel for the kernel executor in accordance with the kernel security key, and share the kernel security key with the graphics processor.