Inventor · disambiguated record
George Petre
Also filed as: PETRE GEORGE
25 granted patents·2 pending applications·29 citations·filing 2017–2024
95Inventor score
Files withMICROSOFT TECHNOLOGY LICENSING LLC27
Top patents by PatentIndex Score
27 records- 0194US10628345B2Enhancing processing performance of a DNN module by bandwidth control of fabric interfaceMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted Apr 21, 2020·6 cites·22 claims
- 0293US11909422B2Neural network processor using compression and decompression of activation data to reduce memory bandwidth utilizationMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2022·Granted Feb 20, 2024·1 cites·5 claims
- 0388US11100390B2Power-efficient deep neural network module configured for layer and operation fencing and dependency managementMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted Aug 24, 2021·3 cites·20 claims
- 0487US10540584B2Queue management for direct memory accessMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2017·Granted Jan 21, 2020·3 cites·17 claims
- 0584US11476869B2Dynamically partitioning workload in a deep neural network module to reduce power consumptionMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted Oct 18, 2022·2 cites·18 claims
- 0684US11405051B2Enhancing processing performance of artificial intelligence/machine hardware by data sharing and distribution as well as reuse of data in neuron buffer/line bufferMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted Aug 2, 2022·2 cites·22 claims
- 0784US11256976B2Dynamic sequencing of data partitions for optimizing memory utilization and performance of neural networksMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2017·Granted Feb 22, 2022·2 cites·22 claims
- 0884US11182667B2Minimizing memory reads and increasing performance by leveraging aligned blob data in a processing unit of a neural network environmentMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2017·Granted Nov 23, 2021·2 cites·22 claims
- 0984US10795836B2Data processing performance enhancement for neural networks using a virtualized data iteratorMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2017·Granted Oct 6, 2020·2 cites·20 claims
- 1083US11010315B2Flexible hardware for high throughput vector dequantization with dynamic vector length and codebook sizeMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted May 18, 2021·2 cites·22 claims
- 1179US11528033B2Neural network processor using compression and decompression of activation data to reduce memory bandwidth utilizationMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted Dec 13, 2022·1 cites·20 claims
- 1279US11100391B2Power-efficient deep neural network module configured for executing a layer descriptor listMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted Aug 24, 2021·1 cites·20 claims
- 1378US11722147B2Dynamic sequencing of data partitions for optimizing memory utilization and performance of neural networksMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2022·Granted Aug 8, 2023·0 cites·20 claims
- 1475US11750212B2Flexible hardware for high throughput vector dequantization with dynamic vector length and codebook sizeMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2021·Granted Sep 5, 2023·0 cites·19 claims
- 1575US11030131B2Data processing performance enhancement for neural networks using a virtualized data iteratorMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2020·Granted Jun 8, 2021·0 cites·20 claims
- 1675US10996739B2Reducing power consumption in a neural network environment using data managementMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2017·Granted May 4, 2021·2 cites·21 claims
- 1774US12154027B2Increased precision neural processing elementMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2023·Granted Nov 26, 2024·0 cites·20 claims
- 1874US11176448B2Enhancing processing performance of a DNN module by bandwidth control of fabric interfaceMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2020·Granted Nov 16, 2021·0 cites·20 claims
- 1968US11487342B2Reducing power consumption in a neural network environment using data managementMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2021·Granted Nov 1, 2022·0 cites·20 claims
- 2065US11341399B2Reducing power consumption in a neural network processor by skipping processing operationsMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted May 24, 2022·0 cites·10 claims
- 2165US11205118B2Power-efficient deep neural network module configured for parallel kernel and parallel input processingMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2018·Granted Dec 21, 2021·0 cites·10 claims
- 2264US10963403B2Processing discontiguous memory as contiguous memory to improve performance of a neural network environmentMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2017·Granted Mar 30, 2021·0 cites·23 claims
- 2361US2018300602A1Minimizing memory reads and increasing performance of a neural network environment using a directed line bufferMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2017·Application pending·0 cites
- 2458US11604972B2Increased precision neural processing elementMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2019·Granted Mar 14, 2023·0 cites·18 claims
- 2557US2025355708A1Hardware thread allocation controllerMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2024·Application pending·0 cites
- 2655US11507349B2Neural processing element with single instruction multiple data (SIMD) compute lanesMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2019·Granted Nov 22, 2022·0 cites·20 claims
- 2747US11494237B2Managing workloads of a deep neural network processorMICROSOFT TECHNOLOGY LICENSING LLC·Filed 2019·Granted Nov 8, 2022·0 cites·7 claims
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →