| 12154027 |
Increased precision neural processing element |
Amol Ashok Ambardekar, Kent D. Cedola, Chad B. McBride, George Petre, Larry Marvin Wall |
2024-11-26 |
$484,419,000 |
| 11909422 |
Neural network processor using compression and decompression of activation data to reduce memory bandwidth utilization |
Joseph L. Corkery, Benjamin Eliot LUNDELL, Larry Marvin Wall, Chad B. McBride, Amol Ashok Ambardekar +2 more |
2024-02-20 |
$456,258,000 |
| 11750212 |
Flexible hardware for high throughput vector dequantization with dynamic vector length and codebook size |
Amol Ashok Ambardekar, Aleksandar Tomic, Chad B. McBride, George Petre, Kent D. Cedola +1 more |
2023-09-05 |
$364,523,000 |
| 11722147 |
Dynamic sequencing of data partitions for optimizing memory utilization and performance of neural networks |
Kent D. Cedola, Larry Marvin Wall, George Petre, Chad B. McBride, Amol Ashok Ambardekar |
2023-08-08 |
$313,798,000 |
| 11604972 |
Increased precision neural processing element |
Amol Ashok Ambardekar, Kent D. Cedola, Chad B. McBride, George Petre, Larry Marvin Wall |
2023-03-14 |
$417,100,000 |
| 11528033 |
Neural network processor using compression and decompression of activation data to reduce memory bandwidth utilization |
Joseph L. Corkery, Benjamin Eliot LUNDELL, Larry Marvin Wall, Chad B. McBride, Amol Ashok Ambardekar +2 more |
2022-12-13 |
$224,065,000 |
| 11507349 |
Neural processing element with single instruction multiple data (SIMD) compute lanes |
Chad B. McBride, Amol Ashok Ambardekar, Kent D. Cedola, George Petre, Larry Marvin Wall |
2022-11-22 |
$216,625,000 |
| 11494237 |
Managing workloads of a deep neural network processor |
Chad B. McBride, Amol Ashok Ambardekar, Kent D. Cedola, George Petre, Larry Marvin Wall |
2022-11-08 |
$248,013,000 |
| 11476869 |
Dynamically partitioning workload in a deep neural network module to reduce power consumption |
Amol Ashok Ambardekar, Chad B. McBride, George Petre, Kent D. Cedola, Larry Marvin Wall |
2022-10-18 |
$176,053,000 |
| 11405051 |
Enhancing processing performance of artificial intelligence/machine hardware by data sharing and distribution as well as reuse of data in neuron buffer/line buffer |
Chad B. McBride, Amol Ashok Ambardekar, Kent D. Cedola, George Petre, Larry Marvin Wall |
2022-08-02 |
$223,267,000 |
| 11341399 |
Reducing power consumption in a neural network processor by skipping processing operations |
Amol Ashok Ambardekar, Chad B. McBride, George Petre, Larry Marvin Wall, Kent D. Cedola |
2022-05-24 |
$214,502,000 |
| 11256976 |
Dynamic sequencing of data partitions for optimizing memory utilization and performance of neural networks |
Kent D. Cedola, Larry Marvin Wall, George Petre, Chad B. McBride, Amol Ashok Ambardekar |
2022-02-22 |
$301,637,000 |
| 11205118 |
Power-efficient deep neural network module configured for parallel kernel and parallel input processing |
Amol Ashok Ambardekar, Chad B. McBride, George Petre, Larry Marvin Wall, Kent D. Cedola |
2021-12-21 |
$276,379,000 |
| 11182667 |
Minimizing memory reads and increasing performance by leveraging aligned blob data in a processing unit of a neural network environment |
George Petre, Chad B. McBride, Amol Ashok Ambardekar, Kent D. Cedola, Larry Marvin Wall |
2021-11-23 |
$215,686,000 |
| 11176448 |
Enhancing processing performance of a DNN module by bandwidth control of fabric interface |
Chad B. McBride, Timothy H. Heil, Amol Ashok Ambardekar, George Petre, Kent D. Cedola +1 more |
2021-11-16 |
$286,400,000 |
| 11100390 |
Power-efficient deep neural network module configured for layer and operation fencing and dependency management |
Chad B. McBride, Amol Ashok Ambardekar, Kent D. Cedola, George Petre, Larry Marvin Wall |
2021-08-24 |
$155,614,000 |
| 11100391 |
Power-efficient deep neural network module configured for executing a layer descriptor list |
Amol Ashok Ambardekar, Kent D. Cedola, Larry Marvin Wall, George Petre, Chad B. McBride |
2021-08-24 |
$155,614,000 |
| 11030131 |
Data processing performance enhancement for neural networks using a virtualized data iterator |
Chad B. McBride, George Petre, Amol Ashok Ambardekar, Kent D. Cedola, Larry Marvin Wall |
2021-06-08 |
$130,719,000 |
| 11010315 |
Flexible hardware for high throughput vector dequantization with dynamic vector length and codebook size |
Amol Ashok Ambardekar, Aleksandar Tomic, Chad B. McBride, George Petre, Kent D. Cedola +1 more |
2021-05-18 |
$149,958,000 |
| 10963403 |
Processing discontiguous memory as contiguous memory to improve performance of a neural network environment |
George Petre, Chad B. McBride, Amol Ashok Ambardekar, Kent D. Cedola, Larry Marvin Wall |
2021-03-30 |
$145,552,000 |
| 10795836 |
Data processing performance enhancement for neural networks using a virtualized data iterator |
Chad B. McBride, George Petre, Amol Ashok Ambardekar, Kent D. Cedola, Larry Marvin Wall |
2020-10-06 |
$143,945,000 |
| 10628345 |
Enhancing processing performance of a DNN module by bandwidth control of fabric interface |
Chad B. McBride, Timothy H. Heil, Amol Ashok Ambardekar, George Petre, Kent D. Cedola +1 more |
2020-04-21 |
$75,244,000 |
| 10572401 |
Direct memory access descriptor processing using timestamps |
Chad B. McBride, Jeffrey Powers Bradford, Steven Wheeler, Christopher Jon Johnson, Andras Tantos |
2020-02-25 |
$60,478,000 |
| 10540584 |
Queue management for direct memory access |
Chad B. McBride, Amol Ashok Ambardekar, Kent D. Cedola, George Petre, Larry Marvin Wall |
2020-01-21 |
$61,337,000 |
| 10528494 |
Direct memory access (“DMA”) descriptor processing using identifiers assigned to descriptors on DMA engines |
Chad B. McBride, Jeffrey Powers Bradford, Steven Wheeler, Christopher Jon Johnson, Andras Tantos |
2020-01-07 |
$59,890,000 |
