Inventor
RAJKISHORE BARIK
Inventor
US
Overview
Patents· 34 as inventor
Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.
G06Fprimary
G06FElectric digital data processing29%
G06NComputing arrangements based on specific computational models26%
G06TImage data processing or generation, in general24%
Y02DClimate change mitigation technologies in information and communication technologies [ict], i.e. information and communication technologies aiming at the reduction of their own energy use10%
G09GArrangements or circuits for control of indicating devices using static means to present variable information6%
H03MCoding3%
B60WConjoint control of vehicle sub-units of different type or different function1%
G01CMeasuring distances, levels or bearings1%
G06KGraphical data reading1%
PatentTitleYear
12,430,131Compute optimizations for neural networks202512,367,382Training with adaptive runtime and precision profiling202512,346,798Dynamic precision for neural network compute operations202512,217,053Instructions and logic to perform floating point and integer operations for machine learning202512,210,900Efficient thread group scheduling202512,198,221Compute optimization mechanism for deep neural networks202512,147,849Work stealing in heterogeneous computing systems202412,141,578Instructions and logic to perform floating point and integer operations for machine learning202412,141,891Machine learning sparse computation mechanism202412,112,397Programmable coarse grained and sparse matrix compute hardware with advanced scheduling202412,050,984Specialized fixed function hardware for efficient convolution202412,039,331Instructions and logic to perform floating point and integer operations for machine learning202412,001,944Tool for facilitating efficiency in machine learning202411,922,535Compute optimization mechanism for deep neural networks202411,803,935Machine learning sparse computation mechanism202311,748,606Dynamic precision for neural network compute operations202311,727,527Programmable coarse grained and sparse matrix compute hardware with advanced scheduling202311,720,355Instructions and logic to perform floating point and integer operations for machine learning202311,693,658Compute optimizations for neural networks using ternary weight202311,609,856Extend GPU/CPU coherency to multi-GPU cores202311,593,910Compute optimization mechanism for deep neural networks202311,580,361Neural network training mechanism202311,562,461Compute optimization mechanism for deep neural networks202311,488,005Smart autonomous machines utilizing cloud, error corrections, and predictions202211,475,286Specialized fixed function hardware for efficient convolution202211,430,083Machine learning sparse computation mechanism202211,410,024Tool for facilitating efficiency in machine learning202211,360,808Efficient thread group scheduling202211,360,767Instructions and logic to perform floating point and integer operations for machine learning202211,348,198Compute optimization mechanism for deep neural networks202211,334,962Compute optimization mechanism for deep neural networks202211,222,392Compute optimization mechanism for deep neural networks202211,210,760Programmable coarse grained and sparse matrix compute hardware with advanced scheduling202111,138,048Work stealing in heterogeneous computing systems2021Career & activity timeline
Assembled from patent assignee/location history and declaration credentials.
2021–2025Patents assigned to INTEL CORP (34)· patent assignee history
2021–2025Based in US· patent location history
Inventor activity
Assignee and location history derived from the patent record.
Assignees
| Assignee | Patents | Span |
|---|---|---|
| INTEL CORP | 34 | 2021–2025 |
Locations
| Location | Patents | Span |
|---|---|---|
| US | 34 | 2021–2025 |