Abstract: Embodiments described herein include software, firmware, and hardware that provides techniques to enable deterministic scheduling across multiple general-purpose graphics processing units. One embodiment provides a multi-GPU architecture with uniform latency. One embodiment provides techniques to distribute memory output based on memory chip thermals. One embodiment provides techniques to enable thermally aware workload scheduling. One embodiment provides techniques to enable end to end contracts for workload scheduling on multiple GPUs.

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: Multi-tile Memory Management for Detecting Cross Tile Access, Providing Multi-Tile Inference Scaling with multicasting of data via copy operation, and Providing Page Migration are disclosed herein. In one embodiment, a graphics processor for a multi-tile architecture includes a first graphics processing unit (GPU) having a memory and a memory controller, a second graphics processing unit (GPU) having a memory and a cross-GPU fabric to communicatively couple the first and second GPUs. The memory controller is configured to determine whether frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU in the multi-GPU configuration and to send a message to initiate a data transfer mechanism when frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU.

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: Embodiments described herein provide techniques to enable the dynamic reconfiguration of memory on a general-purpose graphics processing unit. One embodiment described herein enables dynamic reconfiguration of cache memory bank assignments based on hardware statistics. One embodiment enables for virtual memory address translation using mixed four kilobyte and sixty-four kilobyte pages within the same page table hierarchy and under the same page directory. One embodiment provides for a graphics processor and associated heterogenous processing system having near and far regions of the same level of a cache hierarchy.

Abstract: Briefly, in accordance with one or more embodiments, a processor performs a coarse depth test on pixel data, and performs a final depth test on the pixel data. Coarse depth data is stored in a coarse depth cache, and per pixel depth data is stored in a per pixel depth cache. If a result of the coarse depth test is ambiguous, the processor is to read the per pixel depth data from the per pixel depth cache, and to update the coarse depth data with the per pixel depth data if the per pixel depth data has a smaller depth range than the coarse depth data.

Abstract: Apparatus and method for improved cache utilization and efficiency on a many-core processor. An apparatus comprising: a plurality of execution units to generate cache access requests responsive to executing instructions; a pending request queue to store pending cache access requests generated by the execution units; pending queue management circuitry to compare a current cache access request with entries in the pending request queue to determine whether the current cache access request can be merged with an entry in the pending request queue and, if so, to merge the current cache access request with the entry.

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: A mechanism is described to facilitate microcontroller-based flexible thread scheduling launching in computing environments. An apparatus of embodiments, as described herein, includes facilitating a graphics processor hosting a microcontroller having a thread scheduling unit, and detection and observation logic to detect a scheduling algorithm associated with an application at the apparatus. The apparatus may further include reading and dispatching logic to facilitate the microcontroller to prepare a flexible dispatch routine based on the scheduling algorithm. The apparatus may further include scheduling and launching logic to facilitate the thread scheduling unit to dynamically schedule and launch threads based on the flexible dispatch routine, where the threads are hosted by the graphics processor.

Abstract: An apparatus to facilitate efficient data sharing for graphics data processing operations is disclosed. The apparatus includes a processing resource to generate a stream of instructions, an L1 cache communicably coupled to the processing resource and comprising an on-page detector circuit to determine that a set of memory requests in the stream of instructions access a same memory page; and set a marker in a first request of the set of memory requests; and arbitration circuitry communicably coupled to the L1 cache, the arbitration circuitry to route the set of memory requests to memory comprising the memory page and to, in response to receiving the first request with the marker set, remain with the processing resource to process the set of memory requests.

Abstract: Apparatus and method for stack throttling.

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: Briefly, in accordance with one or more embodiments, a processor performs a coarse depth test on pixel data, and performs a final depth test on the pixel data. Coarse depth data is stored in a coarse depth cache, and per pixel depth data is stored in a per pixel depth cache. If a result of the coarse depth test is ambiguous, the processor is to read the per pixel depth data from the per pixel depth cache, and to update the coarse depth data with the per pixel depth data if the per pixel depth data has a smaller depth range than the coarse depth data.

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 for data aware sparsity via compressed bitstreams. One embodiment provides for block sparse dot product instructions. One embodiment provides for a depth-wise adapter for a systolic array.

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: A mechanism is described to facilitate microcontroller-based flexible thread scheduling launching in computing environments. An apparatus of embodiments, as described herein, includes facilitating a graphics processor hosting a microcontroller having a thread scheduling unit, and detection and observation logic to detect a scheduling algorithm associated with an application at the apparatus. The apparatus may further include reading and dispatching logic to facilitate the microcontroller to prepare a flexible dispatch routine based on the scheduling algorithm. The apparatus may further include scheduling and launching logic to facilitate the thread scheduling unit to dynamically schedule and launch threads based on the flexible dispatch routine, where the threads are hosted by the graphics processor.

Abstract: Briefly, in accordance with one or more embodiments, a processor performs a coarse depth test on pixel data, and performs a final depth test on the pixel data. Coarse depth data is stored in a coarse depth cache, and per pixel depth data is stored in a per pixel depth cache. If a result of the coarse depth test is ambiguous, the processor is to read the per pixel depth data from the per pixel depth cache, and to update the coarse depth data with the per pixel depth data if the per pixel depth data has a smaller depth range than the coarse depth data.

Abstract: Briefly, in accordance with one or more embodiments, a processor performs a coarse depth test on pixel data, and performs a final depth test on the pixel data. Coarse depth data is stored in a coarse depth cache, and per pixel depth data is stored in a per pixel depth cache. If a result of the coarse depth test is ambiguous, the processor is to read the per pixel depth data from the per pixel depth cache, and to update the coarse depth data with the per pixel depth data if the per pixel depth data has a smaller depth range than the coarse depth data.

Abstract: Apparatus and method for improved cache utilization and efficiency on a many-core processor. An apparatus comprising: a plurality of execution units to generate cache access requests responsive to executing instructions; a pending request queue to store pending cache access requests generated by the execution units; pending queue management circuitry to compare a current cache access request with entries in the pending request queue to determine whether the current cache access request can be merged with an entry in the pending request queue and, if so, to merge the current cache access request with the entry.

Abstract: A mechanism is described to facilitate microcontroller-based flexible thread scheduling launching in computing environments. An apparatus of embodiments, as described herein, includes facilitating a graphics processor hosting a microcontroller having a thread scheduling unit, and detection and observation logic to detect a scheduling algorithm associated with an application at the apparatus. The apparatus may further include reading and dispatching logic to facilitate the microcontroller to prepare a flexible dispatch routine based on the scheduling algorithm. The apparatus may further include scheduling and launching logic to facilitate the thread scheduling unit to dynamically schedule and launch threads based on the flexible dispatch routine, where the threads are hosted by the graphics processor.