Inventor · disambiguated record
Mikhail Smelyanskiy
Also filed as: SMELYANSKIY MIKHAIL
33 granted patents·12 pending applications·150 citations·filing 2005–2025
96Inventor score
Top patents by PatentIndex Score
45 records- 0194US9996350B2Hardware apparatuses and methods to prefetch a multidimensional block of elements from a multidimensional arrayINTEL CORP·Filed 2014·Granted Jun 12, 2018·20 cites·24 claims
- 0292US10776699B2Optimized compute hardware for machine learning operationsINTEL CORP·Filed 2018·Granted Sep 15, 2020·10 cites·20 claims
- 0392US10699190B1Systems and methods for efficiently updating neural networksFACEBOOK INC·Filed 2018·Granted Jun 30, 2020·15 cites·16 claims
- 0492US8688957B2Mechanism for conflict detection using SIMDSMELYANSKIY MIKHAIL·Filed 2010·Granted Apr 1, 2014·25 cites·20 claims
- 0591US11487888B1Systems and methods for protecting neural network weightsMETA PLATFORMS INC·Filed 2020·Granted Nov 1, 2022·3 cites·20 claims
- 0691US10948966B1Systems and methods for optimizing power usage for systems within quality-of-service constraintsFACEBOOK INC·Filed 2018·Granted Mar 16, 2021·11 cites·20 claims
- 0791US10817783B1Systems and methods for efficiently updating neural networksFACEBOOK INC·Filed 2020·Granted Oct 27, 2020·3 cites·20 claims
- 0890US10671147B2Dynamic power management for artificial intelligence hardware acceleratorsFACEBOOK INC·Filed 2017·Granted Jun 2, 2020·7 cites·20 claims
- 0989US11334796B2Optimized compute hardware for machine learning operationsINTEL CORP·Filed 2020·Granted May 17, 2022·2 cites·62 claims
- 1086US10579383B1Systems and methods for efficient scaling of quantized integersFACEBOOK INC·Filed 2018·Granted Mar 3, 2020·6 cites·20 claims
- 1184US11514306B1Static memory allocation in neural networksMETA PLATFORMS INC·Filed 2018·Granted Nov 29, 2022·4 cites·20 claims
- 1283US10719613B1Systems and methods for protecting neural network weightsFACEBOOK INC·Filed 2018·Granted Jul 21, 2020·5 cites·19 claims
- 1382US2025362924A1Optimized compute hardware for machine learning operationsINTEL CORP·Filed 2025·Application pending·0 cites
- 1481US11256977B2Lowering hardware for neural networksFACEBOOK INC·Filed 2017·Granted Feb 22, 2022·4 cites·20 claims
- 1581US10482156B2Sparsity-aware hardware acceleratorsFACEBOOK INC·Filed 2017·Granted Nov 19, 2019·4 cites·20 claims
- 1680US9678750B2Vector instructions to enable efficient synchronization and parallel reduction operationsINTEL CORP·Filed 2013·Granted Jun 13, 2017·5 cites·15 claims
- 1778US10474430B2Mixed-precision processing elements, systems, and methods for computational modelsFACEBOOK INC·Filed 2017·Granted Nov 12, 2019·2 cites·19 claims
- 1878US10372787B2Hardware accelerator pre-configured with coefficients for matrix-transform operationsFACEBOOK INC·Filed 2017·Granted Aug 6, 2019·3 cites·20 claims
- 1977US9513905B2Vector instructions to enable efficient synchronization and parallel reduction operationsSMELYANSKIY MIKHAIL·Filed 2008·Granted Dec 6, 2016·8 cites·22 claims
- 2076US12314727B2Optimized compute hardware for machine learning operationsINTEL CORP·Filed 2022·Granted May 27, 2025·0 cites·20 claims
- 2176US10553207B2Systems and methods for employing predication in computational modelsFACEBOOK INC·Filed 2017·Granted Feb 4, 2020·3 cites·13 claims
- 2274US9720663B2Methods, systems and apparatus to optimize sparse matrix applicationsINTEL CORP·Filed 2015·Granted Aug 1, 2017·2 cites·25 claims
- 2371US7350036B2Technique to perform concurrent updates to a shared data structureINTEL CORP·Filed 2005·Granted Mar 25, 2008·5 cites·23 claims
- 2463US10198264B2Sorting data and merging sorted data in an instruction set architectureINTEL CORP·Filed 2015·Granted Feb 5, 2019·1 cites·25 claims
- 2562US11264011B2Systems and methods for employing predication in computational modelsFACEBOOK INC·Filed 2020·Granted Mar 1, 2022·0 cites·20 claims
- 2662US10777251B1In-memory processing based on combining output currentsFACEBOOK INC·Filed 2019·Granted Sep 15, 2020·1 cites·20 claims
- 2760US11023240B1Systems and methods for efficient scaling of quantized integersFACEBOOK INC·Filed 2019·Granted Jun 1, 2021·0 cites·20 claims
- 2860US10656944B2Hardware apparatus and methods to prefetch a multidimensional block of elements from a multidimensional arrayINTEL CORP·Filed 2018·Granted May 19, 2020·0 cites·24 claims
- 2958US10768989B2Virtual vector processingINTEL CORP·Filed 2018·Granted Sep 8, 2020·0 cites·22 claims
- 3053US2011025700A1Using a Texture Unit for General Purpose ComputingLEE VICTOR W·Filed 2009·Application pending·0 cites
- 3152US9076254B2Texture unit for general purpose computingINTEL CORP·Filed 2013·Granted Jul 7, 2015·0 cites·23 claims
- 3248US8570336B2Texture unit for general purpose computingLEE VICTOR W·Filed 2009·Granted Oct 29, 2013·0 cites·21 claims
- 3348US2015228091A1Texture Unit for General Purpose ComputingINTEL CORP·Filed 2015·Application pending·0 cites
- 3447US9870267B2Virtual vector processingNGUYEN ANTHONY·Filed 2006·Granted Jan 16, 2018·0 cites·30 claims
- 3547US2016179540A1Instruction and logic for hardware support for execution of calculationsSMELYANSKIY MIKHAIL·Filed 2014·Application pending·0 cites
- 3644US9153064B2Grouping pixels to be texturedLEE VICTOR W·Filed 2009·Granted Oct 6, 2015·0 cites·19 claims
- 3744US8564601B2Parallel and vectored Gilbert-Johnson-Keerthi graphics processingBADER ALEKSEY A·Filed 2009·Granted Oct 22, 2013·1 cites·20 claims
- 3842US2009160869A1Extended texture mapping unitSMELYANSKIY MIKHAIL·Filed 2007·Application pending·0 cites
- 3941US2019190538A1Accelerator hardware for compression and decompressionFACEBOOK INC·Filed 2017·Application pending·0 cites
- 4041US2010082939A1Techniques for efficient implementation of brownian bridge algorithm on simd platformsCHONG JIKE·Filed 2008·Application pending·0 cites
- 4141US2019171927A1Layer-level quantization in neural networksFACEBOOK INC·Filed 2017·Application pending·0 cites
- 4239US2007143759A1Scheduling and partitioning tasks via architecture-aware feedback informationOZGUR AYSEL·Filed 2005·Application pending·0 cites
- 4336US2017091103A1Instruction and Logic for Indirect AccessesSMELYANSKIY MIKHAIL·Filed 2015·Application pending·0 cites
- 4436US2017177361A1Apparatus and method for accelerating graph analyticsANDERSON MICHAEL·Filed 2015·Application pending·0 cites
- 4531US2017185403A1Hardware content-associative data structure for acceleration of set operationsINTEL CORP·Filed 2015·Application pending·0 cites
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →