Intel Corporation

James M Holland

Abhishek R Appu

Joydeep Ray

Altug Koker

Nikos Kaburlasos

Lidong Xu

Prasoonkumar Surti

Jill MacDonald Boyce

Stanley J Baran

Chandrasekaran Sakthivel

Satya N Yedidi

Elmoustapha Ould-Ahmed-Vall

Subramaniam M Maiyuran

Adam T Lake

Jeffery S Boles

Fangwen Fu

Radhakrishnan Venkataraman

Narayan Biswal

Gokcen Cilingir

Mayuresh M Varerkar

Travis T Schluessler

Michael Apodaca

Kai Xiao

Atsuo Kuwahara

John H Feit

Jacek Kwiatkowski

Barnan Das

Sumit Mohan

Srinivasan Embar Raghukrishnan

Vasanth Ranganathan

Kamal Sinha

Ankur N Shah

Deepak Shashidhar Vembar

Pattabhiraman K

Jonathan Kennedy

Nilesh V Shah

Archie Sharma

Louis Feng

Keith W Rowe

Sayan Lahiri

Sang-Hee Lee

Brent E Insko

Atthar H Mohammed

Jason Daniel Tanner

Sang-hee Lee

Jong Dae Oh

Dmitry E Ryzhov

Hong Jiang

Guei-Yuan Lueh

Scott R Janus

Hugues Labbe

Hiu-Fai R Chan

Vivek Tiwari

Sanjeev S Jahagirdar

Peter L Doyle

Daniel Pohl

Devan Burke

Philip R Laws

Xinmin Tian

Zhijun Lei

Anupreet S Kalra

Durgaprasad Bilagi

Christopher J Hughes

Wenhao Zhang

Qian Xu

Changliang Wang

Kristoffer Fleming

Ya-Ti Peng

Wen-Fu Kao

Yi-Jen Chiu

Paul S Diefenbaugh

Ximin Zhang

Vallabhajosyula S Somayazulu

Krishnan Rajamani

Yiting Liao

Ning Lu

Nilesh K Jain

Carson Brownlee

Brinda Ganesh

Jefferson Amstutz

Srikanth Potluri

Scott W Cheng

Vidhya Krishnan

Faouzi Kossentini

Naveen Matam

Sebastian Possos

Zhan Lou

Chekib Nouira

Foued Ben Amara

Jason Ross

Charu Srivastava

Ilya Brailovskiy

Satish Kumar Bhrugumalla

Venkata Prasad

Dmitry Ryzhov

Maruthi Sandeep Maddipatla

Muhammad Hamdan

Craig Hurst

Hassene Tmar

Embodiments described herein are generally directed to improvements relating to power, latency, bandwidth and/or performance issues relating to GPU processing/caching. According to one embodiment, a system includes a producer intellectual property (IP) (e.g., a media IP), a compute core (e.g., a GPU or an AI-specific core of the GPU), a streaming buffer logically interposed between the producer IP and the compute core. The producer IP is operable to consume data from memory and output results to the streaming buffer. The compute core is operable to perform AI inference processing based on data consumed from the streaming buffer and output AI inference processing results to the memory.

Graphics processing unit processing and caching improvements

This disclosure describes systems, methods, and devices related to generating visual quality metrics for encoded video frames. A method may include generating respective first visual quality metrics for pixels of an encoded video frame; generating respective second visual quality metrics for the pixels, the respective first visual quality metrics and the respective second visual quality metrics indicative of estimated human perceptions of the encoded video frame; generating a pixel block-based weight for the respective first visual quality metrics; generating a frame-based weight for the respective second visual quality metrics; and generating, based on the respective first visual quality metrics, the pixel block-based weight, the respective second visual quality metrics, and the frame-based weight, a human visual score indicative of a visual quality of the encoded video frame.

Enhanced real-time visual quality metric generation for video coding

Embodiments described herein provided for an instruction and associated logic to enable a processing resource including a tensor accelerator to perform optimized computation of sparse submatrix operations. One embodiment provides a parallel processor comprising a processing cluster coupled with the cache memory. The processing cluster includes a plurality of multiprocessors coupled with a data interconnect, where a multiprocessor of the plurality of multiprocessors includes a tensor core configured to load tensor data and metadata associated with the tensor data from the cache memory, wherein the metadata indicates a first numerical transform applied to the tensor data, perform an inverse transform of the first numerical transform, perform a tensor operation on the tensor data after the inverse transform is performed, and write output of the tensor operation to a memory coupled with the processing cluster.

Systolic arithmetic on sparse data

Techniques related to video coding using look ahead analysis and block based back propagation for block level quantization parameters are discussed. Such techniques include adaptively selecting frames subsequent to a target frame in a display order for use in the back propagation, propagating values to blocks of the target frame that are indicative of the importance of the blocks to the encode of the subsequent frames, and encoding the target frame using block level quantization parameters based on the propagated values.

Fine grain lookahead enhancement for video coding

Techniques related to adaptive quantization matrix selection using machine learning for video coding are discussed. Such techniques include applying a machine learning model to generate an estimated quantization parameter for a frame and selecting a set of quantization matrices for encode of the frame from a number of sets of quantization matrices based on the estimated quantization parameter.

Determining adaptive quantization matrices using machine learning for video coding

An example apparatus includes image processing circuitry to determine an uncovered region of a background image in a current video frame relative to the background image in a previous video frame, the uncovered region obscured in the previous video frame by a first foreground region of the previous video frame, and the uncovered region uncovered in the current video frame based on movement of a second foreground region in the current video frame relative to the first foreground region of the previous video frame, and encoder circuitry to generate an updated frame portion by encoding the second foreground region and dirty blocks of the background image corresponding to the uncovered region without encoding static blocks of the background image, the static blocks not corresponding to the uncovered region, and store the updated frame portion in the at least one memory.

Methods and apparatus to perform dirty region reads and writes to reduce memory bandwidth usage

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.

Data locality enhancement for graphics processing units

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.

Systems and methods for error detection and control for embedded memory and compute elements

Systems, apparatuses and methods may provide away to render augmented reality (AR) and/or virtual reality (VR) sensory enhancements using ray tracing. More particularly, systems, apparatuses and methods may provide a way to normalize environment information captured by multiple capture devices, and calculate, for an observer, the sound sources or sensed events vector paths. The systems, apparatuses and methods may detect and/or manage one or more capture devices and assign one or more the capture devices based on one or more conditions to provide observer an immersive VR/AR experience.

Augmented reality virtual reality ray tracing sensory enhancement system, apparatus and method

Techniques related to distributing the video encoding processing of an input video across hardware and software systems. Such techniques include evaluating the content of the video and determine whether or the encoding operation is best to be done on the hardware system only, software system only or a hybrid hardware and software system.

Offloading video coding processes to hardware for better density-quality tradeoffs

Systems, apparatuses and methods may provide away to enhance an augmented reality (AR) and/or virtual reality (VR) user experience with environmental information captured from sensors located in one or more physical environments. More particularly, systems, apparatuses and methods may provide a way to track, by an eye tracker sensor, a gaze of a user, and capture, by the sensors, environmental information. The systems, apparatuses and methods may render feedback, by one or more feedback devices or display device, for a portion of the environment information based on the gaze of the user.

Sensory enhanced augmented reality and virtual reality device

An embodiment of a graphics apparatus may include a focus identifier to identify a focus area, and a color compressor to selectively compress color data based on the identified focus area. Another embodiment of a graphics apparatus may include a motion detector to detect motion of a real object, a motion predictor to predict a motion of the real object, and an object placer to place a virtual object relative to the real object based on the predicted motion of the real object. Another embodiment of a graphics apparatus may include a frame divider to divide a frame into viewports, a viewport prioritizer to prioritize the viewports, a renderer to render a viewport of the frame in order in accordance with the viewport priorities, and a viewport transmitter to transmit a completed rendered viewport. Other embodiments are disclosed and claimed.

Predictive viewport renderer and foveated color compressor

A lossless pixel compressor may include technology to detect a format of a pixel memory region, and compress the pixel memory region together with embedded control information which indicates the detected format of the pixel memory region. Other embodiments are disclosed and claimed.

Lossless pixel compression based on inferred control information

Growing community of inventors

Folsom, CA, United States of America

James M Holland