Inventor

SURTI PRASOONKUMAR

US367 patents

⚠️ This page may combine multiple inventors who share the name “SURTI PRASOONKUMAR”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

SURTI PRASOONKUMAR

INTEL CORP

Coordination and increased utilization of graphics processors during inference

Systems and methods for improving cache efficiency and utilization

Sparse optimizations for a matrix accelerator architecture

Lossless compression for multisample render targets alongside fragment compression

Apparatus and method for asynchronous ray tracing

Cluster of scalar engines to accelerate intersection in leaf node

Surface normal vector processing mechanism

Autonomous vehicle advanced sensing and response

Display engine surface blending and adaptive texel to pixel ratio sample rate system, apparatus and method

Render-cache controller for multithreading, multi-core graphics processor

Compression in machine learning and deep learning processing

Lossless compression for multisample render targets alongside fragment compression

Compression and decompression of graphics data using pixel region bit values

Power savings for neural network architecture with zero activations during inference

Graphics processor data access and sharing

Systolic arithmetic on sparse data

Graphics processor with tiled compute kernels

Systems and methods for improving cache efficiency and utilization

Multi-tile architecture for graphics operations

Dynamic memory reconfiguration

Efficient data sharing for graphics data processing operations

Sparse optimizations for a matrix accelerator architecture

Adaptive resolution of point cloud and viewpoint prediction for video streaming in computing environments

Video refinement mechanism

Patch processing mechanism

Multi-tile memory management

Systolic disaggregation within a matrix accelerator architecture

Multi-tile memory management for detecting cross tile access providing multi-tile inference scaling and providing page migration

Lossless compression for multisample render targets alongside fragment compression

Multi-tile graphics processor rendering

Lossless compression for multisample render targets alongside fragment compression

Page cache system and method for multi-agent environments

Data prefetching for graphics data processing

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

Efficient sharing and compression expansion of data across processing systems

Lossless compression for multisample render targets alongside fragment compression

Efficient multi-context thread distribution

Collaborative multi-user virtual reality

Hierarchical general register file (GRF) for execution block

Compute optimization mechanism for deep neural networks

Autonomous machines through cloud, error corrections, and predictions

Shared local memory tiling mechanism

Power management of memory chips based on working set size

Hierarchical lossless compression and null data support

Extend GPU/CPU coherency to multi-GPU cores

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

Adaptive multisampling based on vertex attributes

Controlling coarse pixel size from a stencil buffer

Ordering threads as groups in a multi-threaded, multi-core graphics compute system

SURTI PRASOONKUMAR

Subset based compression and decompression of graphics data