Michael Espig
24Patents
6h-index
42Co-inventors
65Inventor score
Filing activity: Sep 30, 2008 → Nov 6, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US10719323B2 | Systems and methods for performing matrix compress and decompress instructions | Physics | 46 | Active |
| US10896043B2 | Systems for performing instructions for fast element unpacking into 2-dimensional registers | Physics | 28 | Active |
| US10942985B2 | Apparatuses, methods, and systems for fast fourier transform configuration and computation instructions | Physics | 21 | Active |
| US10922077B2 | Apparatuses, methods, and systems for stencil configuration and computation instructions | Physics | 20 | Active |
| US11507376B2 | Systems for performing instructions for fast element unpacking into 2-dimensional registers | Physics | 6 | Active |
| US11748103B2 | Systems and methods for performing matrix compress and decompress instructions | Physics | 6 | Active |
| US11294671B2 | Systems and methods for performing duplicate detection instructions on 2D data | Physics | 6 | Active |
| US11249761B2 | Systems and methods for performing matrix compress and decompress instructions | Physics | 6 | Active |
| US11886875B2 | Systems and methods for performing nibble-sized operations on matrix elements | Physics | 5 | Active |
| US11847185B2 | Systems and methods of instructions to accelerate multiplication of sparse matrices using bitmasks that identify non-zero elements | Physics | 5 | Active |
| US8762599B2 | Delegating a poll operation to another device | Physics | 2 | Active |
| US8495464B2 | Reliability support in memory systems without error correcting code support | Electricity | 1 | Active |
| US8553693B2 | Network controller circuitry to issue at least one portion of packet payload to device in manner that by-passes communication protocol stack involvement | Electricity | 1 | Active |
| US12175246B2 | Systems and methods for performing matrix compress and decompress instructions | Physics | 0 | Active |
| US12321714B2 | Compressed wallace trees in FMA circuits | Physics | 0 | Active |
| US11836464B2 | Method and apparatus for efficient binary and ternary support in fused multiply-add (FMA) circuits | Physics | 0 | Active |
| US8649262B2 | Dynamic configuration of potential links between processing elements | Electricity | 0 | Active |
| US8364862B2 | Delegating a poll operation to another device | Physics | 0 | Active |
| US12182570B2 | Apparatuses, methods, and systems for a packed data convolution instruction with shift control and width control | Physics | 0 | Active |
| US12287843B2 | Systems and methods of instructions to accelerate multiplication of sparse matrices using bitmasks that identify non-zero elements | Physics | 0 | Active |
| US12099838B2 | Instruction and logic for sum of square differences | Physics | 0 | Active |
| US10713012B2 | Method and apparatus for efficient binary and ternary support in fused multiply-add (FMA) circuits | Physics | 0 | Active |
| US11366636B2 | Method and apparatus for efficient binary and ternary support in fused multiply-add (FMA) circuits | Physics | 0 | Active |
| US11327754B2 | Method and apparatus for approximation using polynomials | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.