Abstract: An apparatus to facilitate optimization of a neural network (NN) is disclosed. The apparatus includes optimization logic to define a NN topology having one or more macro layers, adjust the one or more macro layers to adapt to input and output components of the NN and train the NN based on the one or more macro layers.

Abstract: A mechanism is described for facilitating dynamic cache allocation in computing devices in computing devices. A method of embodiments, as described herein, includes facilitating monitoring one or more bandwidth consumptions of one or more clients accessing a cache associated with a processor; computing one or more bandwidth requirements of the one or more clients based on the one or more bandwidth consumptions; and allocating one or more portions of the cache to the one or more clients in accordance with the one or more bandwidth requirements.

Abstract: Systems and methods for providing shared virtual memory addressing support for a host system are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations. A memory management unit (MMU) is coupled to the processing resources. The MMU to support a first virtual address size for managing allocation of non-shared virtual memory and to support a second virtual address size for managing allocation of shared virtual memory that is shared between the graphics processor and a host.

Abstract: Embodiments described herein include, software, firmware, and hardware logic that provides techniques to perform arithmetic on sparse data via a systolic processing unit. Embodiment described herein provided techniques to skip computational operations for zero filled matrices and sub-matrices. Embodiments additionally provide techniques to maintain data compression through to a processing unit. Embodiments additionally provide an architecture for a sparse aware logic unit.

Abstract: Examples described herein relate to a decompression engine that can request compressed data to be transferred over a memory bus. In some cases, the memory bus is a width that requires multiple data transfers to transfer the requested data. In a case that requested data is to be presented in-order to the decompression engine, a re-order buffer can be used to store entries of data. When a head-of-line entry is received, the entry can be provided to the decompression engine. When a last entry in a group of one or more entries is received, all entries in the group are presented in-order to the decompression engine. In some examples, a decompression engine can borrow memory resources allocated for use by another memory client to expand a size of re-order buffer available for use. For example, a memory client with excess capacity and a slowest growth rate can be chosen to borrow memory resources from.

Abstract: Systems, apparatuses and methods may provide for technology that determines a position associated with one or more polygons in unresolved surface data and select an anti-aliasing sample rate based on a state of the one or more polygons with respect to the position. Additionally, the unresolved surface data may be resolved at the position in accordance with the selected anti-aliasing sample rate, wherein the selected anti-aliasing sample rate varies across a plurality of pixels. The position may be a bounding box, a display screen coordinate, and so forth.

Abstract: Apparatus and method for scalable error reporting. For example, one embodiment of an apparatus comprises error detection circuitry to detect an error in a component of a first tile within a tile-based hierarchy of a processing device; error classification circuitry to classify the error and record first error data based on the classification; a first tile interface to combine the first error data with second error data received from one or more other components associated with the first tile to generate first accumulated error data; and a master tile interface to combine the first accumulated error data with second accumulated error data received from at least one other tile interface to generate second accumulated error data and to provide the second accumulated error data to a host executing an application to process the second accumulated error data.

Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.

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 collect user information for a user of a data processing device, generate a user profile for the user of the data processing device from the user information, and set a power profile a processor in the data processing device using the user profile. Other embodiments are also disclosed and claimed.

Abstract: Systems, apparatuses and methods may provide for technology that activates a first context on a graphics processor and detects a context switch condition with respect to the first context. Additionally, a second context may be activated, in response to the context switch condition, on the graphics processor while the first context is active on the graphics processor. In one example, activating the second context includes adding a group identifier to a plurality of threads corresponding to the second context and launching the plurality of threads with the group identifier on the graphics processor.

Abstract: A mechanism is described for facilitating person tracking and data security in machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting, by a camera associated with one or more trackers, a person within a physical vicinity, where detecting includes capturing one or more images the person. The method may further include tracking, by the one or more trackers, the person based on the one or more images of the person, where tracking includes collect tracking data relating to the person. The method may further include selecting a tracker of the one or more trackers as a preferred tracker based on the tracking data.

Abstract: In accordance with some embodiments, the render rate is varied across and/or up and down the display screen. This may be done based on where the user is looking in order to reduce power consumption and/or increase performance. Specifically the screen display is separated into regions, such as quadrants. Each of these regions is rendered at a rate determined by at least one of what the user is currently looking at, what the user has looked at in the past and/or what it is predicted that the user will look at next. Areas of less focus may be rendered at a lower rate, reducing power consumption in some embodiments.

Abstract: A disaggregated processor package can be configured to accept interchangeable chiplets. Interchangeability is enabled by specifying a standard physical interconnect for chiplets that can enable the chiplet to interface with a fabric or bridge interconnect. Chiplets from different IP designers can conform to the common interconnect, enabling such chiplets to be interchangeable during assembly. The fabric and bridge interconnects logic on the chiplet can then be configured to confirm with the actual interconnect layout of the on-board logic of the chiplet. Additionally, data from chiplets can be transmitted across an inter-chiplet fabric using encapsulation, such that the actual data being transferred is opaque to the fabric, further enable interchangeability of the individual chiplets. With such an interchangeable design, higher or lower density memory can be inserted into memory chiplet slots, while compute or graphics chiplets with a higher or lower core count can be inserted into logic chiplet slots.

Abstract: An apparatus to facilitate guaranteed forward progress for graphics data is disclosed. The apparatus includes a plurality of ports to receive and transmit streams of graphics data, one or more buffers associated with each of the plurality of ports to store the graphics data and switching logic to virtually partition each of the one or more buffers to allocate a dedicated buffer to receive each of a plurality of independent streams of graphics data.

Abstract: Embodiments are generally directed to data prefetching for graphics data processing. An embodiment of an apparatus includes one or more processors including one or more graphics processing units (GPUs); and a plurality of caches to provide storage for the one or more GPUs, the plurality of caches including at least an L1 cache and an L3 cache, wherein the apparatus to provide intelligent prefetching of data by a prefetcher of a first GPU of the one or more GPUs including measuring a hit rate for the L1 cache; upon determining that the hit rate for the L1 cache is equal to or greater than a threshold value, limiting a prefetch of data to storage in the L3 cache, and upon determining that the hit rate for the L1 cache is less than a threshold value, allowing the prefetch of data to the L1 cache.

Abstract: A mechanism is described for facilitating intelligent dispatching and vectorizing at autonomous machines. A method of embodiments, as described herein, includes detecting a plurality of threads corresponding to a plurality of workloads associated with tasks relating to a graphics processor. The method may further include determining a first set of threads of the plurality of threads that are similar to each other or have adjacent surfaces, and physically clustering the first set of threads close together using a first set of adjacent compute blocks.

Abstract: An apparatus to facilitate memory data compression is disclosed. The apparatus includes a memory and having a plurality of banks to store main data and metadata associated with the main data and a memory management unit (MMU) coupled to the plurality of banks to perform a hash function to compute indices into virtual address locations in memory for the main data and the metadata and adjust the metadata virtual address locations to store each adjusted metadata virtual address location in a bank storing the associated main data.

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 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: 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.