Issued Patents All Time
Showing 25 most recent of 189 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12423102 | Instructions to convert from FP16 to BF8 | Alexander Heinecke, Naveen Mellempudi, Robert Valentine, Mark J. Charney, Evangelos Georganas +3 more | 2025-09-23 |
| 12417100 | Instructions for structured-sparse tile matrix FMA | Menachem Adelman, Amit Gradstein, Alexander Heinecke, Naveen Mellempudi, Shahar Mizrahi +7 more | 2025-09-16 |
| 12405770 | Matrix transpose and multiply | Menachem Adelman, Robert Valentine, Barukh Ziv, Amit Gradstein, Simon Rubanovich +5 more | 2025-09-02 |
| 12379927 | BFLOAT16 scale and/or reduce instructions | Menachem Adelman, Alexander Heinecke, Robert Valentine, Zeev Sperber, Amit Gradstein +4 more | 2025-08-05 |
| 12367045 | Instructions to convert from FP16 to BF8 | Alexander Heinecke, Naveen Mellempudi, Robert Valentine, Mark J. Charney, Evangelos Georganas +3 more | 2025-07-22 |
| 12360774 | Coalescing adjacent gather/scatter operations | Andrew T. Forsyth, Brian J. Hickmann, Jonathan C. Hall | 2025-07-15 |
| 12353878 | Apparatuses, methods, and systems for instructions for matrix multiplication instructions | Menachem Adelman, Robert Valentine, Zeev Sperber, Amit Gradstein, Simon Rubanovich +4 more | 2025-07-08 |
| 12332796 | Dynamic cache coherence protocol based on runtime interconnect utilization | Keqiang Wu, Lingxiang Xiang, Heidi Pan, Zhe Wang | 2025-06-17 |
| 12287843 | Systems and methods of instructions to accelerate multiplication of sparse matrices using bitmasks that identify non-zero elements | Dan Baum, Chen Koren, Elmoustapha Ould-Ahmed-Vall, Michael Espig, Raanan Sade +3 more | 2025-04-29 |
| 12277419 | Apparatuses, methods, and systems for instructions to convert 16-bit floating-point formats | Alexander Heinecke, Robert Valentine, Mark J. Charney, Menachem Adelman, Evangelos Georganas +3 more | 2025-04-15 |
| 12265826 | Systems for performing instructions to quickly convert and use tiles as 1D vectors | Bret L. Toll, Dan Baum, Elmoustapha Ould-Ahmed-Vall, Raanan Sade, Robert Valentine +2 more | 2025-04-01 |
| 12229554 | BFLOAT16 fused multiply instructions | Alexander Heinecke, Menachem Adelman, Robert Valentine, Zeev Sperber, Amit Gradstein +4 more | 2025-02-18 |
| 12216579 | Adaptive remote atomics | Carl J. Beckmann, Samantika S. Sury, Lingxiang Xiang, Rahul Agrawal | 2025-02-04 |
| 12210446 | Inter-cluster shared data management in sub-NUMA cluster | Zhe Wang, Lingxiang Xiang | 2025-01-28 |
| 12190118 | Data locality enhancement for graphics processing units | Prasoonkumar Surti, Guei-Yuan Lueh, Adam T. Lake, Jill MacDonald Boyce, Subramaniam Maiyuran +6 more | 2025-01-07 |
| 12175246 | Systems and methods for performing matrix compress and decompress instructions | Dan Baum, Michael Espig, James D. Guilford, Wajdi K. Feghali, Raanan Sade +7 more | 2024-12-24 |
| 12135968 | Instructions to convert from FP16 to BF8 | Alexander Heinecke, Naveen Mellempudi, Robert Valentine, Mark J. Charney, Evangelos Georganas +3 more | 2024-11-05 |
| 12130740 | Apparatuses and methods for a processor architecture | Jason W. Brandt, Robert S. Chappell, Jesus Corbal, Edward T. Grochowski, Stephen H. Gunther +9 more | 2024-10-29 |
| 12112167 | Matrix data scatter and gather between rows and irregularly spaced memory locations | Alexander Heinecke, Robert Valentine, Menachem Adelman, Evangelos Georganas, Mark J. Charney +2 more | 2024-10-08 |
| 12106104 | Processor instructions for data compression and decompression | Zhe Wang, Alaa R. Alameldeen | 2024-10-01 |
| 12056489 | Apparatuses, methods, and systems for 8-bit floating-point matrix dot product instructions | Naveen Mellempudi, Alexander Heinecke, Robert Valentine, Mark J. Charney, Evangelos Georganas +3 more | 2024-08-06 |
| 12020028 | Apparatuses, methods, and systems for 8-bit floating-point matrix dot product instructions | Naveen Mellempudi, Alexander Heinecke, Robert Valentine, Mark J. Charney, Evangelos Georganas +3 more | 2024-06-25 |
| 11989555 | Instructions for remote atomic operations | Doddaballapur N. Jayasimha, Jonas Svennebring, Samantika S. Sury, Jong Soo Park, Lingxiang Xiang | 2024-05-21 |
| 11972230 | Matrix transpose and multiply | Menachem Adelman, Robert Valentine, Barukh Ziv, Amit Gradstein, Simon Rubanovich +5 more | 2024-04-30 |
| 11954489 | Systems for performing instructions to quickly convert and use tiles as 1D vectors | Bret L. Toll, Dan Baum, Elmoustapha Ould-Ahmed-Vall, Raanan Sade, Robert Valentine +2 more | 2024-04-09 |