G06F 15/825
Dataflow computers
Official title: {Dataflow computers}
G06F15/825 (Dataflow computers) appears on 119 US grants and 163 published applications in this corpus.
Search patents in G06F- Granted patents
- 119
- Published applications
- 163
- Assignees
- 66
- Inventors
- 263
- Latest grant
- 6 Oct 2026
Filings by year
| Year | Granted patents | Published applications |
|---|---|---|
| 1993 | 1 | 0 |
| 1994 | 0 | 0 |
| 1995 | 0 | 0 |
| 1996 | 2 | 0 |
| 1997 | 0 | 0 |
| 1998 | 0 | 0 |
| 1999 | 0 | 0 |
| 2000 | 0 | 0 |
| 2001 | 0 | 0 |
| 2002 | 0 | 0 |
| 2003 | 0 | 0 |
| 2004 | 0 | 0 |
| 2005 | 0 | 1 |
| 2006 | 0 | 0 |
| 2007 | 0 | 0 |
| 2008 | 0 | 1 |
| 2009 | 0 | 1 |
| 2010 | 0 | 1 |
| 2011 | 2 | 4 |
| 2012 | 1 | 2 |
| 2013 | 2 | 3 |
| 2014 | 1 | 2 |
| 2015 | 3 | 5 |
| 2016 | 6 | 5 |
| 2017 | 3 | 8 |
| 2018 | 3 | 5 |
| 2019 | 12 | 17 |
| 2020 | 6 | 9 |
| 2021 | 8 | 10 |
| 2022 | 9 | 8 |
| 2023 | 12 | 29 |
| 2024 | 16 | 17 |
| 2025 | 18 | 21 |
| 2026 | 14 | 14 |
By publication year. Applications have been published since 2001. 2026 runs to 8 Oct.
Recent patents
- Dataflow-based general-purpose processor architectures with feedforward register lanes6 Oct 2026US 12,754,739 B2The Board of Trustees of the University of Illinois
- Dependency-aware server processing of dataflow applications21 Jul 2026US 12,688,062 B2SambaNova Systems, Inc.
- System and method for optimizing data-transfer among multiple compute units in a data-parallel computing system21 Jul 2026US 12,688,148 B2SambaNova Systems, Inc.
- Method to reset configurable units in a reconfigurable processor14 Jul 2026US 12,681,806 B2SambaNova Systems, Inc.
- Hardware accelerator with configurable tensor operation pipeline30 Jun 2026US 12,670,123 B2Microsoft Technology Licensing, LLC
- Runtime counter-based tracking and communication of variable-length output size in a data processing system24 Sep 2026US 2026/0288674 A1SambaNova Systems, Inc.
- Ultra-low power coarse-grained reconfigurable arrays with programmable on-chip network20 Aug 2026US 2026/0244418 A1Carnegie Mellon University
- Systems and methods for implementing directional operand broadcast and multiply-accumulate execution using a configurable patch mesh in a multi-core processing array of an integrated circuit2 Jul 2026US 2026/0187028 A1quadric.io, Inc.
- Processor for configurable parallel computations14 May 2026US 2026/0133932 A1Star Ally International Limited
- Array processing entity array placement and routing14 May 2026US 2026/0133933 A1Mobileye Vision Technologies Ltd.
Most cited
By later US patents
- Tagged token data processing system with operand matching in activation frames123US 5,241,635 AMassachusetts Institute of Technology · 1993
- Document distribution recommender system and method65US 7,996,456 B2John Nicholas and Kristin Gross Trust · 2011
- Wavelet representation for accelerated deep learning52US 10,515,303 B2Cerebras Systems Inc. · 2019
- Dataflow triggered tasks for accelerated deep learning34US 10,614,357 B2Cerebras Systems Inc. · 2020
- Multithreaded processor array with heterogeneous function blocks communicating tokens via self-routing switch fabrics34US 9,158,575 B22015