Inventor · disambiguated record
Evangelos Georganas
Also filed as: GEORGANAS EVANGELOS
18 granted patents·25 pending applications·29 citations·filing 2018–2025
89Inventor score
Top patents by PatentIndex Score
43 records- 0197US12020028B2Apparatuses, methods, and systems for 8-bit floating-point matrix dot product instructionsINTEL CORP·Filed 2020·Granted Jun 25, 2024·7 cites·24 claims
- 0297US11972230B2Matrix transpose and multiplyINTEL CORP·Filed 2020·Granted Apr 30, 2024·9 cites·20 claims
- 0397US11941395B2Apparatuses, methods, and systems for instructions for 16-bit floating-point matrix dot product instructionsINTEL CORP·Filed 2020·Granted Mar 26, 2024·7 cites·24 claims
- 0481US11354564B2Tuning of loop orders in blocked dense basic linear algebra subroutinesINTEL CORP·Filed 2019·Granted Jun 7, 2022·4 cites·30 claims
- 0579US2024241722A1Apparatuses, methods, and systems for 8-bit floating-point matrix dot product instructionsINTEL CORP·Filed 2024·Application pending·0 cites
- 0677US12056489B2Apparatuses, methods, and systems for 8-bit floating-point matrix dot product instructionsINTEL CORP·Filed 2023·Granted Aug 6, 2024·0 cites·14 claims
- 0776US10853554B2Systems and methods for determining a configuration for a microarchitectureINTEL CORP·Filed 2019·Granted Dec 1, 2020·2 cites·20 claims
- 0875US2025117218A1Instructions to convert from fp16 to bf8INTEL CORP·Filed 2024·Application pending·0 cites
- 0974US12405770B2Matrix transpose and multiplyINTEL CORP·Filed 2024·Granted Sep 2, 2025·0 cites·20 claims
- 1074US12367045B2Instructions to convert from FP16 to BF8INTEL CORP·Filed 2024·Granted Jul 22, 2025·0 cites·16 claims
- 1172US2024184585A1Bfloat16 comparison instructionsINTEL CORP·Filed 2024·Application pending·0 cites
- 1267US12229554B2BFLOAT16 fused multiply instructionsINTEL CORP·Filed 2021·Granted Feb 18, 2025·0 cites·30 claims
- 1367US2025217141A1Bfloat16 fused multiply instructionsINTEL CORP·Filed 2025·Application pending·0 cites
- 1466US12379927B2BFLOAT16 scale and/or reduce instructionsINTEL CORP·Filed 2021·Granted Aug 5, 2025·0 cites·35 claims
- 1566US11386256B2Systems and methods for determining a configuration for a microarchitectureINTEL CORP·Filed 2020·Granted Jul 12, 2022·0 cites·25 claims
- 1664US2025053454A1Methods and apparatus for a machine learning model decompression acceleratorINTEL CORP·Filed 2024·Application pending·0 cites
- 1763US12417100B2Instructions for structured-sparse tile matrix FMAINTEL CORP·Filed 2022·Granted Sep 16, 2025·0 cites·23 claims
- 1863US12135968B2Instructions to convert from FP16 to BF8INTEL CORP·Filed 2020·Granted Nov 5, 2024·0 cites·20 claims
- 1962US2023072105A1Bfloat16 comparison instructionsINTEL CORP·Filed 2021·Application pending·0 cites
- 2061US12423102B2Instructions to convert from FP16 to BF8INTEL CORP·Filed 2020·Granted Sep 23, 2025·0 cites·18 claims
- 2156US12353878B2Apparatuses, methods, and systems for instructions for matrix multiplication instructionsINTEL CORP·Filed 2021·Granted Jul 8, 2025·0 cites·14 claims
- 2256US12112167B2Matrix data scatter and gather between rows and irregularly spaced memory locationsINTEL CORP·Filed 2020·Granted Oct 8, 2024·0 cites·17 claims
- 2354US12277419B2Apparatuses, methods, and systems for instructions to convert 16-bit floating-point formatsINTEL CORP·Filed 2020·Granted Apr 15, 2025·0 cites·18 claims
- 2452US10970072B2Systems and methods to transpose vectors on-the-fly while loading from memoryINTEL CORP·Filed 2018·Granted Apr 6, 2021·0 cites·15 claims
- 2552US2025004768A1Vector packed matrix multiplication and accumulation processors, methods, systems, and instructionsHEINECKE ALEXANDER·Filed 2023·Application pending·0 cites
- 2652US2025004765A1Apparatus and method for a load instruction with a read-shared indicationINTEL CORP·Filed 2023·Application pending·0 cites
- 2749US2024045687A18-bit floating point classification and manipulation instructionsINTEL CORP·Filed 2022·Application pending·0 cites
- 2849US2024045681A18-bit floating point comparison instructionsINTEL CORP·Filed 2022·Application pending·0 cites
- 2949US2024045688A18-bit floating point fused multiply instructionsINTEL CORP·Filed 2022·Application pending·0 cites
- 3049US2024045654A18-bit floating point source arithmetic instructionsINTEL CORP·Filed 2022·Application pending·0 cites
- 3149US2024045691A1Apparatuses, methods, and systems for 8-bit floating-point matrix dot product instructionsINTEL CORP·Filed 2022·Application pending·0 cites
- 3249US2024045677A1Instructions to convert from fp16 to fp8INTEL CORP·Filed 2022·Application pending·0 cites
- 3349US2024045682A18-bit floating point scale and/or reduce instructionsINTEL CORP·Filed 2022·Application pending·0 cites
- 3449US2024045686A1Instructions to convert from fp8INTEL CORP·Filed 2022·Application pending·0 cites
- 3549US2024045684A1Instructions to convert from fp16 to fp8INTEL CORP·Filed 2022·Application pending·0 cites
- 3646US2023069000A1Bfloat16 arithmetic instructionsINTEL CORP·Filed 2021·Application pending·0 cites
- 3746US2023060146A1Bfloat16 classification and manipulation instructionsINTEL CORP·Filed 2021·Application pending·0 cites
- 3846US2023409326A1Device, method and system for executing a tile load and expand instructionINTEL CORP·Filed 2022·Application pending·0 cites
- 3945US2023102279A1Apparatuses, methods, and systems for instructions for structured-sparse tile matrix fmaINTEL CORP·Filed 2021·Application pending·0 cites
- 4045US2023101512A1Shared prefetch instruction and supportINTEL CORP·Filed 2021·Application pending·0 cites
- 4144US2022100513A1Apparatuses, methods, and systems for instructions for loading data and padding into a tile of a matrix operations acceleratorINTEL CORP·Filed 2020·Application pending·0 cites
- 4243US2021406012A1Loading and storing matrix data with datatype conversionINTEL CORP·Filed 2020·Application pending·0 cites
- 4337US2019220278A1Apparatus and method for down-converting and interleaving multiple floating point valuesADELMAN MENACHEM·Filed 2019·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when Evangelos Georganas 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 →