Inventor · disambiguated record
Olivier Temam
Also filed as: TEMAM OLIVIER
45 granted patents·9 pending applications·609 citations·filing 2016–2025
98Inventor score
Top patents by PatentIndex Score
54 records- 0199US9836691B1Neural network instruction set architectureGOOGLE INC·Filed 2017·Granted Dec 5, 2017·108 cites·17 claims
- 0299US9710265B1Neural network compute tileGOOGLE INC·Filed 2017·Granted Jul 18, 2017·201 cites·17 claims
- 0398US10175980B2Neural network compute tileGOOGLE LLC·Filed 2016·Granted Jan 8, 2019·38 cites·20 claims
- 0497US9959247B1Permuting in a matrix-vector processorGOOGLE LLC·Filed 2017·Granted May 1, 2018·27 cites·15 claims
- 0597US9928460B1Neural network accelerator tile architecture with three-dimensional stackingGOOGLE INC·Filed 2017·Granted Mar 27, 2018·45 cites·18 claims
- 0696US10504022B2Neural network accelerator with parameters resident on chipGOOGLE LLC·Filed 2018·Granted Dec 10, 2019·22 cites·20 claims
- 0796US9959498B1Neural network instruction set architectureGOOGLE LLC·Filed 2016·Granted May 1, 2018·21 cites·16 claims
- 0895US10963780B2Yield improvements for three-dimensionally stacked neural network acceleratorsGOOGLE LLC·Filed 2017·Granted Mar 30, 2021·11 cites·18 claims
- 0995US10127494B1Neural network crossbar stackGOOGLE LLC·Filed 2017·Granted Nov 13, 2018·45 cites·22 claims
- 1094US10956537B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2020·Granted Mar 23, 2021·3 cites·16 claims
- 1194US10936942B2Apparatus 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
- 1294US10496326B2Hardware double buffering using a special purpose computational unitGOOGLE LLC·Filed 2019·Granted Dec 3, 2019·9 cites·17 claims
- 1394US9946539B1Accessing data in multi-dimensional tensors using addersGOOGLE LLC·Filed 2017·Granted Apr 17, 2018·19 cites·20 claims
- 1493US10534607B2Accessing data in multi-dimensional tensors using addersGOOGLE LLC·Filed 2018·Granted Jan 14, 2020·10 cites·12 claims
- 1593US10248908B2Alternative loop limits for accessing data in multi-dimensional tensorsGOOGLE LLC·Filed 2017·Granted Apr 2, 2019·10 cites·19 claims
- 1691US12061968B2Neural network instruction set architectureGOOGLE LLC·Filed 2022·Granted Aug 13, 2024·1 cites·21 claims
- 1791US10108538B1Accessing prologue and epilogue dataGOOGLE LLC·Filed 2017·Granted Oct 23, 2018·7 cites·20 claims
- 1890US10802956B2Accessing prologue and epilogue dataGOOGLE LLC·Filed 2018·Granted Oct 13, 2020·8 cites·20 claims
- 1986US12292473B2Yield improvements for three-dimensionally stacked neural network acceleratorsGOOGLE LLC·Filed 2023·Granted May 6, 2025·0 cites·17 claims
- 2086US10614151B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2019·Granted Apr 7, 2020·2 cites·15 claims
- 2186US10592583B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2019·Granted Mar 17, 2020·2 cites·12 claims
- 2285US2025045559A1Neural network instruction set architectureGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2384US12339923B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2023·Granted Jun 24, 2025·0 cites·15 claims
- 2484US10706007B2Vector reduction processorGOOGLE LLC·Filed 2018·Granted Jul 7, 2020·2 cites·10 claims
- 2583US12499081B2Vector reduction processorGOOGLE LLC·Filed 2024·Granted Dec 16, 2025·0 cites·18 claims
- 2683US12455737B2Neural network compute tileGOOGLE LLC·Filed 2023·Granted Oct 28, 2025·0 cites·16 claims
- 2783US2025068897A1Apparatus and mechanism for processing neural network tasks using a single chip package with multiple identical diesGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2881US11422801B2Neural network compute tileGOOGLE LLC·Filed 2019·Granted Aug 23, 2022·2 cites·20 claims
- 2980US10175912B1Hardware double buffering using a special purpose computational unitGOOGLE LLC·Filed 2017·Granted Jan 8, 2019·2 cites·17 claims
- 3080US2024078417A1Neural network accelerator with parameters resident on chipGOOGLE LLC·Filed 2023·Application pending·0 cites
- 3179US11816480B2Neural network compute tileGOOGLE LLC·Filed 2022·Granted Nov 14, 2023·0 cites·16 claims
- 3279US11727259B2Neural network accelerator with parameters resident on chipGOOGLE LLC·Filed 2022·Granted Aug 15, 2023·0 cites·11 claims
- 3378US2025231765A1Neural network compute tileGOOGLE LLC·Filed 2025·Application pending·0 cites
- 3478US2025265444A1Neural network instruction set architectureGOOGLE LLC·Filed 2025·Application pending·0 cites
- 3577US2025232164A1Neural network accelerator with parameters resident on chipGOOGLE LLC·Filed 2025·Application pending·0 cites
- 3676US2025238668A1Apparatus and mechanism for processing neural network tasks using a single chip package with multiple identical diesGOOGLE LLC·Filed 2025·Application pending·0 cites
- 3775US11275992B2Special purpose neural network training chipGOOGLE LLC·Filed 2018·Granted Mar 15, 2022·2 cites·11 claims
- 3874US11836598B2Yield improvements for three-dimensionally stacked neural network acceleratorsGOOGLE LLC·Filed 2021·Granted Dec 5, 2023·0 cites·10 claims
- 3974US11748443B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2021·Granted Sep 5, 2023·0 cites·20 claims
- 4074US10216705B2Permuting in a matrix-vector processorGOOGLE LLC·Filed 2018·Granted Feb 26, 2019·1 cites·16 claims
- 4173US11379707B2Neural network instruction set architectureGOOGLE LLC·Filed 2017·Granted Jul 5, 2022·1 cites·20 claims
- 4272US12165048B2Neural network crossbar stackGOOGLE LLC·Filed 2022·Granted Dec 10, 2024·0 cites·38 claims
- 4372US12079711B2Apparatus and mechanism for processing neural network tasks using a single chip package with multiple identical diesGOOGLE LLC·Filed 2021·Granted Sep 3, 2024·0 cites·20 claims
- 4472US11948060B2Neural network accelerator tile architecture with three-dimensional stackingGOOGLE LLC·Filed 2022·Granted Apr 2, 2024·0 cites·18 claims
- 4572US11940946B2Vector reduction processorGOOGLE LLC·Filed 2021·Granted Mar 26, 2024·0 cites·20 claims
- 4671US2025165766A1Accelerating neural networks in hardware using interconnected crossbarsGOOGLE LLC·Filed 2025·Application pending·0 cites
- 4770US11061854B2Vector reduction processorGOOGLE LLC·Filed 2020·Granted Jul 13, 2021·0 cites·20 claims
- 4869US10885434B2Alternative loop limits for accessing data in multi-dimensional tensorsGOOGLE LLC·Filed 2019·Granted Jan 5, 2021·1 cites·20 claims
- 4963US11501144B2Neural network accelerator with parameters resident on chipGOOGLE LLC·Filed 2019·Granted Nov 15, 2022·0 cites·8 claims
- 5062US11099772B2Hardware double buffering using a special purpose computational unitGOOGLE LLC·Filed 2019·Granted Aug 24, 2021·0 cites·14 claims
Showing the top 50 of 54 patent records by PatentIndex Score.
Join the waitlist — get patent alerts
Get an alert when Olivier Temam 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 →