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 detect zero value elements within a vector or a set of packed data elements output by a processing resource and generate metadata to indicate a location of the zero value elements within the plurality of data elements.

Abstract: One embodiment provides an apparatus comprising a memory stack including multiple memory dies and a parallel processor including a plurality of multiprocessors. Each multiprocessor has a single instruction, multiple thread (SIMT) architecture, the parallel processor coupled to the memory stack via one or more memory interfaces. At least one multiprocessor comprises a multiply-accumulate circuit to perform multiply-accumulate operations on matrix data in a stage of a neural network implementation to produce a result matrix comprising a plurality of matrix data elements at a first precision, precision tracking logic to evaluate metrics associated with the matrix data elements and indicate if an optimization is to be performed for representing data at a second stage of the neural network implementation, and a numerical transform unit to dynamically perform a numerical transform operation on the matrix data elements based on the indication to produce transformed matrix data elements at a second precision.

Abstract: Methods and apparatus relating to techniques for multi-tile memory management. In an example, a graphics processor includes an interposer, a first chiplet coupled with the interposer, the first chiplet including a graphics processing resource and an interconnect network coupled with the graphics processing resource, cache circuitry coupled with the graphics processing resource via the interconnect network, and a second chiplet coupled with the first chiplet via the interposer, the second chiplet including a memory-side cache and a memory controller coupled with the memory-side cache. The memory controller is configured to enable access to a high-bandwidth memory (HBM) device, the memory-side cache is configured to cache data associated with a memory access performed via the memory controller, and the cache circuitry is logically positioned between the graphics processing resource and a chiplet interface.

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: 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, cache or DRAM 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: Embodiments are generally directed to cache structure and utilization. An embodiment of an apparatus includes one or more processors including a graphics processor; a memory for storage of data for processing by the one or more processors; and a cache to cache data from the memory; wherein the apparatus is to provide for dynamic overfetching of cache lines for the cache, including receiving a read request and accessing the cache for the requested data, and upon a miss in the cache, overfetching data from memory or a higher level cache in addition to fetching the requested data, wherein the overfetching of data is based at least in part on a current overfetch boundary, and provides for data is to be prefetched extending to the current overfetch boundary.

Abstract: Systems and methods for improving cache efficiency and utilization are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations and a cache controller of a cache coupled to the processing resources. The cache controller is configured to control cache priority by determining whether default settings or an instruction will control cache operations for the cache.

Abstract: Embodiments described herein include software, firmware, and hardware logic that provides techniques to perform arithmetic on sparse data via a systolic processing unit. One embodiment provides techniques to optimize training and inference on a systolic array when using sparse data. One embodiment provides techniques to use decompression information when performing sparse compute operations. One embodiment enables the disaggregation of special function compute arrays via a shared reg file. One embodiment enables packed data compress and expand operations on a GPGPU. One embodiment provides techniques to exploit block sparsity within the cache hierarchy of a GPGPU.

Abstract: Systems and methods for improving cache efficiency and utilization are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations and a cache controller of a cache memory that is coupled to the processing resources. The cache controller is configured to set an initial aging policy using an aging field based on age of cache lines within the cache memory and to determine whether a hint or an instruction to indicate a level of aging has been received.

Abstract: Embodiments described herein provide an apparatus comprising a plurality of processing resources including a first processing resource and a second processing resource, a memory communicatively coupled to the first processing resource and the second processing resource, and a processor to receive data dependencies for one or more tasks comprising one or more producer tasks executing on the first processing resource and one or more consumer tasks executing on the second processing resource and move a data output from one or more producer tasks executing on the first processing resource to a cache memory communicatively coupled to the second processing resource. Other embodiments may be described and claimed.

Abstract: Apparatuses including a graphics processing unit, graphics multiprocessor, or graphics processor having an error detection correction logic for cache memory or shared memory are disclosed. In one embodiment, a graphics multiprocessor includes cache or local memory for storing data and error detection correction circuitry integrated with or coupled to the cache or local memory. The error detection correction circuitry is configured to perform a tag read for data of the cache or local memory to check error detection correction information.

Abstract: An apparatus and method are described for managing data which is biased towards a processor or a GPU. For example, an apparatus comprises a processor comprising one or more cores, one or more cache levels, and cache coherence controllers to maintain coherent data in the one or more cache levels; a graphics processing unit (GPU) to execute graphics instructions and process graphics data, wherein the GPU and processor cores are to share a virtual address space for accessing a system memory; a GPU memory addressable through the virtual address space shared by the processor cores and GPU; and bias management circuitry to store an indication for whether the data has a processor bias or a GPU bias, wherein if the data has a GPU bias, the data is to be accessed by the GPU without necessarily accessing the processor's cache coherence controllers.

Abstract: One embodiment provides a graphics processor comprising a system interface and circuitry coupled with the system interface. The circuitry includes an execution resource and a preemption status register. The execution resource is configured to execute an instruction. During execution of the instruction, the execution resource is to receive a request to preempt execution of a thread associated with the instruction and, based on a value stored in the preemption status register, execute at least one additional instruction after receipt of the request to preempt execution of the thread.

Abstract: One embodiment provides for a graphics processing unit to accelerate machine-learning operations, the graphics processing unit comprising a multiprocessor having a single instruction, multiple thread (SIMT) architecture, the multiprocessor to execute at least one single instruction; and a first compute unit included within the multiprocessor, the at least one single instruction to cause the first compute unit to perform a two-dimensional matrix multiply and accumulate operation, wherein to perform the two-dimensional matrix multiply and accumulate operation includes to compute a 32-bit intermediate product of 16-bit operands and to compute a 32-bit sum based on the 32-bit intermediate product.

Abstract: Apparatuses including general-purpose graphics processing units having on chip dense memory for temporal buffering are disclosed. In one embodiment, a graphics multiprocessor includes a plurality of compute engines to perform first computations to generate a first set of data, cache for storing data, and a high density memory that is integrated on chip with the plurality of compute engines and the cache. The high density memory to receive the first set of data, to temporarily store the first set of data, and to provide the first set of data to the cache during a first time period that is prior to a second time period when the plurality of compute engines will use the first set of data for second computations.

Abstract: Methods and apparatus relating to data initialization techniques. In an example, an apparatus comprises a processor to read one or more metadata codes which map to one or more cache lines in a cache memory and invoke a random number generator to generate random numerical data for the one or more cache lines in response to a determination that the one more metadata codes indicate that the cache lines are to contain random numerical data. Other embodiments are also disclosed and claimed.

Abstract: Methods and apparatus relating to scalar core integration in a graphics processor. In an example, an apparatus comprises a processor to receive a set of workload instructions for a graphics workload from a host complex, determine a first subset of operations in the set of operations that is suitable for execution by a scalar processor complex of the graphics processing device and a second subset of operations in the set of operations that is suitable for execution by a vector processor complex of the graphics processing device, assign the first subset of operations to the scalar processor complex for execution to generate a first set of outputs, assign the second subset of operations to the vector processor complex for execution to generate a second set of outputs. Other embodiments are also disclosed and claimed.

Abstract: Generation and storage of compressed z-planes in graphics processing is described. An example of a processor includes a rasterizer to generate a fragment of pixel data including blocks of pixel data; a depth pipeline to receive the fragment, the pipeline including a first and second depth test hardware, the first depth test hardware to perform a coarse depth test including determining minimum and maximum depths for each block; and a depth buffer, wherein the processor is to determine whether the fragment meets requirements that the fragment fully covers a tile of pixel data and passes a first depth test, and that each of the minimum and maximum depths of the fragment has a same sign and exponent, and, upon determining that the fragment meets the requirements, to generate a compressed depth plane utilizing the first depth test and update the depth buffer with the compressed depth plane.

Abstract: Embodiments described herein provide techniques to disaggregate an architecture of a system on a chip integrated circuit into multiple distinct chiplets that can be packaged onto a common chassis. In one embodiment, a graphics processing unit or parallel processor is composed from diverse silicon chiplets that are separately manufactured. A chiplet is an at least partially and distinctly packaged integrated circuit that includes distinct units of logic that can be assembled with other chiplets into a larger package. A diverse set of chiplets with different IP core logic can be assembled into a single device.

Abstract: Embodiments described herein provide a scalable coherency tracking implementation that utilizes shared virtual memory to manage data coherency. In one embodiment, coherency tracking granularity is reduced relative to existing coherency tracking solutions, with coherency tracking storage memory moved to memory as a page table metadata. For example and in one embodiment, storage for coherency state is moved from dedicated hardware blocks to system memory, effectively providing a directory structure that is limitless in size.