Inventor · disambiguated record
Dong Hyuk Woo
Also filed as: WOO DONG HYUK
56 granted patents·22 pending applications·802 citations·filing 2012–2025
99Inventor score
Top patents by PatentIndex Score
78 records- 0199US10019668B1Scheduling neural network processingGOOGLE LLC·Filed 2017·Granted Jul 10, 2018·77 cites·18 claims
- 0299US9836691B1Neural network instruction set architectureGOOGLE INC·Filed 2017·Granted Dec 5, 2017·108 cites·17 claims
- 0399US9818059B1Exploiting input data sparsity in neural network compute unitsGOOGLE INC·Filed 2017·Granted Nov 14, 2017·89 cites·20 claims
- 0499US9710265B1Neural network compute tileGOOGLE INC·Filed 2017·Granted Jul 18, 2017·201 cites·17 claims
- 0598US10175980B2Neural network compute tileGOOGLE LLC·Filed 2016·Granted Jan 8, 2019·38 cites·20 claims
- 0697US9959247B1Permuting in a matrix-vector processorGOOGLE LLC·Filed 2017·Granted May 1, 2018·27 cites·15 claims
- 0796US10504022B2Neural network accelerator with parameters resident on chipGOOGLE LLC·Filed 2018·Granted Dec 10, 2019·22 cites·20 claims
- 0896US9959498B1Neural network instruction set architectureGOOGLE LLC·Filed 2016·Granted May 1, 2018·21 cites·16 claims
- 0996US9875104B2Accessing data in multi-dimensional tensorsGOOGLE INC·Filed 2016·Granted Jan 23, 2018·18 cites·20 claims
- 1095US9798701B2Matrix processing apparatusGOOGLE INC·Filed 2016·Granted Oct 24, 2017·10 cites·15 claims
- 1194US10956537B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2020·Granted Mar 23, 2021·3 cites·16 claims
- 1294US10936942B2Apparatus and mechanism for processing neural network tasks using a single chip package with multiple identical diesGOOGLE LLC·Filed 2017·Granted Mar 2, 2021·9 cites·20 claims
- 1394US10496326B2Hardware double buffering using a special purpose computational unitGOOGLE LLC·Filed 2019·Granted Dec 3, 2019·9 cites·17 claims
- 1494US9946539B1Accessing data in multi-dimensional tensors using addersGOOGLE LLC·Filed 2017·Granted Apr 17, 2018·19 cites·20 claims
- 1594US9805001B2Matrix processing apparatusGOOGLE INC·Filed 2016·Granted Oct 31, 2017·10 cites·18 claims
- 1693US10534607B2Accessing data in multi-dimensional tensors using addersGOOGLE LLC·Filed 2018·Granted Jan 14, 2020·10 cites·12 claims
- 1793US10360163B2Exploiting input data sparsity in neural network compute unitsGOOGLE LLC·Filed 2016·Granted Jul 23, 2019·10 cites·20 claims
- 1893US10248908B2Alternative loop limits for accessing data in multi-dimensional tensorsGOOGLE LLC·Filed 2017·Granted Apr 2, 2019·10 cites·19 claims
- 1992US9875100B2Accessing data in multi-dimensional tensorsGOOGLE INC·Filed 2017·Granted Jan 23, 2018·7 cites·17 claims
- 2091US12061968B2Neural network instruction set architectureGOOGLE LLC·Filed 2022·Granted Aug 13, 2024·1 cites·21 claims
- 2191US10108538B1Accessing prologue and epilogue dataGOOGLE LLC·Filed 2017·Granted Oct 23, 2018·7 cites·20 claims
- 2290US10802956B2Accessing prologue and epilogue dataGOOGLE LLC·Filed 2018·Granted Oct 13, 2020·8 cites·20 claims
- 2390US9898441B2Matrix processing apparatusGOOGLE INC·Filed 2016·Granted Feb 20, 2018·9 cites·17 claims
- 2489US10417303B2Matrix processing apparatusGOOGLE LLC·Filed 2017·Granted Sep 17, 2019·4 cites·20 claims
- 2588US10228947B2Accessing data in multi-dimensional tensorsGOOGLE LLC·Filed 2017·Granted Mar 12, 2019·4 cites·20 claims
- 2688US9323525B2Monitoring vector lane duty cycle for dynamic optimizationINTEL CORP·Filed 2014·Granted Apr 26, 2016·11 cites·12 claims
- 2787US11816045B2Exploiting input data sparsity in neural network compute unitsGOOGLE LLC·Filed 2021·Granted Nov 14, 2023·1 cites·11 claims
- 2887US8806171B2Systems and methods providing wear leveling using dynamic randomization for non-volatile memorySEONG NAK HEE·Filed 2012·Granted Aug 12, 2014·17 cites·23 claims
- 2986US10614151B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2019·Granted Apr 7, 2020·2 cites·15 claims
- 3086US10592583B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2019·Granted Mar 17, 2020·2 cites·12 claims
- 3185US10719575B2Matrix processing apparatusGOOGLE LLC·Filed 2019·Granted Jul 21, 2020·2 cites·20 claims
- 3285US2025045559A1Neural network instruction set architectureGOOGLE LLC·Filed 2024·Application pending·0 cites
- 3384US12339923B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2023·Granted Jun 24, 2025·0 cites·15 claims
- 3484US9606797B2Compressing execution cycles for divergent execution in a single instruction multiple data (SIMD) processorINTEL CORP·Filed 2012·Granted Mar 28, 2017·12 cites·26 claims
- 3583US12455737B2Neural network compute tileGOOGLE LLC·Filed 2023·Granted Oct 28, 2025·0 cites·16 claims
- 3683US2025068897A1Apparatus and mechanism for processing neural network tasks using a single chip package with multiple identical diesGOOGLE LLC·Filed 2024·Application pending·0 cites
- 3783US2024289285A1Exploiting input data sparsity in neural network compute unitsGOOGLE LLC·Filed 2023·Application pending·0 cites
- 3881US11422801B2Neural network compute tileGOOGLE LLC·Filed 2019·Granted Aug 23, 2022·2 cites·20 claims
- 3981US9880976B2Matrix processing apparatusGOOGLE INC·Filed 2016·Granted Jan 30, 2018·4 cites·17 claims
- 4081US9477628B2Collective communications apparatus and method for parallel systemsINTEL CORP·Filed 2013·Granted Oct 25, 2016·6 cites·25 claims
- 4181US2025209302A1Scheduling neural network processingGOOGLE LLC·Filed 2025·Application pending·0 cites
- 4281US2024403621A1Processing sequential inputs using neural network acceleratorsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 4380US10175912B1Hardware double buffering using a special purpose computational unitGOOGLE LLC·Filed 2017·Granted Jan 8, 2019·2 cites·17 claims
- 4480US2024078417A1Neural network accelerator with parameters resident on chipGOOGLE LLC·Filed 2023·Application pending·0 cites
- 4579US11816480B2Neural network compute tileGOOGLE LLC·Filed 2022·Granted Nov 14, 2023·0 cites·16 claims
- 4679US11727259B2Neural network accelerator with parameters resident on chipGOOGLE LLC·Filed 2022·Granted Aug 15, 2023·0 cites·11 claims
- 4779US10373291B1Image transformation for machine learningGOOGLE LLC·Filed 2018·Granted Aug 6, 2019·3 cites·17 claims
- 4878US11157794B2Scheduling neural network processingGOOGLE LLC·Filed 2018·Granted Oct 26, 2021·2 cites·20 claims
- 4978US2025231765A1Neural network compute tileGOOGLE LLC·Filed 2025·Application pending·0 cites
- 5078US2025258784A1Exploiting input data sparsity in neural network compute unitsGOOGLE LLC·Filed 2025·Application pending·0 cites
Showing the top 50 of 78 patent records by PatentIndex Score.
Join the waitlist — get patent alerts
Get an alert when Dong Hyuk Woo files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →