Patent | Date |
---|
Using a low-bit-width dot product engine to sum high-bit-width numbers Grant 11,455,143 - Ulrich , et al. September 27, 2 | 2022-09-27 |
Pipelined pointwise convolution using per-channel convolution operations Grant 11,443,013 - Komuravelli , et al. September 13, 2 | 2022-09-13 |
High throughput matrix processor with support for concurrently processing multiple matrices Grant 11,409,838 - Nair , et al. August 9, 2 | 2022-08-09 |
Device and method for flexibly summing matrix values Grant 11,379,557 - Nair , et al. July 5, 2 | 2022-07-05 |
Matrix processing instruction with optional up/down sampling of matrix Grant 11,372,644 - Ulrich , et al. June 28, 2 | 2022-06-28 |
Floating Point Multiply Hardware Using Decomposed Component Numbers App 20220107782 - Nair; Krishnakumar Narayanan ;   et al. | 2022-04-07 |
Hardware for floating-point arithmetic in multiple formats Grant 11,275,560 - Ulrich , et al. March 15, 2 | 2022-03-15 |
Floating point multiply hardware using decomposed component numbers Grant 11,188,303 - Nair , et al. November 30, 2 | 2021-11-30 |
Device And Method For Flexibly Summing Matrix Values App 20210349965 - Nair; Krishnakumar Narayanan ;   et al. | 2021-11-11 |
Using A Low-bit-width Dot Product Engine To Sum High-bit-width Numbers App 20210349690 - Ulrich; Thomas Mark ;   et al. | 2021-11-11 |
Mapping Convolution To Connected Processing Elements Using Distributed Pipelined Separable Convolution Operations App 20210334072 - Komuravelli; Rakesh ;   et al. | 2021-10-28 |
High Bandwidth Memory System With Distributed Request Broadcasting Masters App 20210326051 - Diril; Abdulkadir Utku ;   et al. | 2021-10-21 |
Grouped Convolution Using Point-to-point Connected Channel Convolution Engines App 20210319076 - Komuravelli; Rakesh ;   et al. | 2021-10-14 |
Pipelined Pointwise Convolution Using Per-channel Convolution Operations App 20210294875 - Komuravelli; Rakesh ;   et al. | 2021-09-23 |
Systems and methods for reducing power consumption of convolution operations for artificial neural networks Grant 11,120,328 - Nair September 14, 2 | 2021-09-14 |
Mapping Convolution To A Partition Channel Convolution Engine App 20210271451 - Nair; Krishnakumar Narayanan ;   et al. | 2021-09-02 |
Mapping Convolution To A Channel Convolution Engine App 20210256363 - Nair; Krishnakumar Narayanan ;   et al. | 2021-08-19 |
Hardware For Floating-point Arithmetic In Multiple Formats App 20210255830 - Ulrich; Thomas Mark ;   et al. | 2021-08-19 |
High bandwidth memory system with distributed request broadcasting masters Grant 11,054,998 - Diril , et al. July 6, 2 | 2021-07-06 |
Systems And Methods For Reducing Data Movement During Convolution Operations In Artificial Neural Networks App 20210192359 - Khish Ardestani Zadeh; Ehsan ;   et al. | 2021-06-24 |
High Bandwidth Memory System With Crossbar Switch For Dynamically Programmable Distribution Scheme App 20210182196 - Wu; Olivia ;   et al. | 2021-06-17 |
High Bandwidth Memory System With Distributed Request Broadcasting Masters App 20210181957 - Diril; Abdulkadir Utku ;   et al. | 2021-06-17 |
Hardware Accelerated Matrix Manipulation Operations Using Processor Instructions App 20210173646 - Ulrich; Thomas Mark ;   et al. | 2021-06-10 |
High Bandwidth Memory System With Dynamically Programmable Distribution Scheme App 20210165691 - Diril; Abdulkadir Utku ;   et al. | 2021-06-03 |
High Throughput Matrix Processor With Support For Concurrently Processing Multiple Matrices App 20210124794 - Nair; Krishnakumar Narayanan ;   et al. | 2021-04-29 |
Support For Different Matrix Multiplications By Selecting Adder Tree Intermediate Results App 20210125044 - Hao; Yuchen ;   et al. | 2021-04-29 |
Floating Point Multiply Hardware Using Decomposed Component Numbers App 20210103429 - Nair; Krishnakumar Narayanan ;   et al. | 2021-04-08 |
Memory organization for matrix processing Grant 10,872,038 - Nair , et al. December 22, 2 | 2020-12-22 |