Deep learning inference efficiency technology with early exit and speculative execution
US-2024104916-A1 · Mar 28, 2024 · US
US2016335381A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2016335381-A1 |
| Application number | US-201615224165-A |
| Country | US |
| Kind code | A1 |
| Filing date | Jul 29, 2016 |
| Priority date | Sep 26, 2013 |
| Publication date | Nov 17, 2016 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Electronic design automation modules include a first tool and a second tool. The first tool includes ab initio simulation procedures configured to use input parameters to produce information about a band structure of a simulated material on a first simulation scale specified at least in part by the input parameters. The second tool includes a simulation procedure configured to used information about the band structure of the simulated material produced by the first tool to extract parameters on a second simulation scale larger than the first simulation scale.
Opening claim text (preview).
1 . An electronic design automation system, comprising: a data processor; storage accessible by the processor, and storing computer program instructions executable by the processor, the instructions including: a first tool including an ab initio simulation procedure configured to use input parameters to produce information about a band structure of a simulated material on a first simulation scale specified at least in part by the input parameters; and a second tool including a simulation procedure configured to use information about the band structure of the simulated material produced by the first tool to extract parameters on a second simulation scale larger than the first simulation scale. 2 . The system of claim 1 , the instructions including control procedures to iterate between the first tool and the second tool. 3 . The system of claim 1 , wherein the second tool comprises a drift-diffusion simulation procedure. 4 . The system of claim 1 , wherein the second tool comprises a wave function formalism quantum transport simulation procedure. 5 . The system of claim 1 , wherein the second tool comprises a Wigner function quantum transport simulation procedure. 6 . The system of claim 1 , wherein the second tool comprises a Boltzmann transport simulation procedure. 7 . The system of claim 1 , wherein said parameters on a second simulation scale include a device performance metric. 8 . The system of claim 1 , wherein said parameters on a second simulation scale include parameters of a charge distribution. 9 . The system of claim 1 , wherein said parameters on a second simulation scale include parameters of a current-voltage curve. 10 . A computer-implemented method comprising: executing an ab initio simulation procedure using input parameters to produce information about a band structure of a simulated material on a first simulation scale, the simulated material specified at least in part by the input parameters; and executing a second simulation procedure using information about the band structure of the simulated material produced in the ab initio simulation procedure to extract parameters on a second simulation scale larger than the first simulation scale. 11 . The method of claim 10 , including iterating between the ab initio simulation procedure and the second simulation procedure. 12 . The method of claim 10 , wherein the second simulation procedure comprises a drift-diffusion simulation procedure. 13 . The method of claim 10 , wherein the second simulation procedure comprises a wave function formalism quantum transport simulation procedure. 14 . The method of claim 10 , wherein the second simulation procedure comprises a Wigner function quantum transport simulation procedure. 15 . The method of claim 10 , wherein the second simulation procedure comprises a Boltzmann transport simulation procedure. 16 . The method of claim 10 , wherein said parameters on a second simulation scale include a device performance metric. 17 . The method of claim 10 , wherein said parameters on a second simulation scale include parameters of a charge distribution. 18 . The method of claim 10 , wherein said parameters on a second simulation scale include parameters of a current-voltage curve. 19 . An electronic design automation system, comprising: a data processor; and storage accessible by the processor, and storing computer program instructions executable by the processor, the instructions including: a first tool including a procedure configured to use input parameters to produce information about a band structure of a simulated material on a first simulation scale specified at least in part by the input parameters by solving Schrodinger's equation based on positions and types of atoms; and a second tool including a simulation procedure configured to use information about the band structure of the simulated material produced by the first tool to extract parameters on a second simulation scale larger than the first simulation scale. 20 . The system of claim 19 , wherein the second tool comprises a drift-diffusion simulation procedure. 21 . The system of claim 19 , wherein the second tool comprises a wave function formalism quantum transport simulation procedure. 22 . The system of claim 19 , wherein the second tool comprises a Wigner function quantum transport simulation procedure. 23 . The system of claim 19 , wherein the second tool comprises a Boltzmann transport simulation procedure. 24 . The system of claim 19 , wherein said parameters on a second simulation scale include a device performance metric. 25 . The system of claim 19 , wherein said parameters on a second simulation scale include parameters of a charge distribution. 26 . The system of claim 19 , wherein said parameters on a second simulation scale include parameters of a current-voltage curve. 27 . A computer-implemented method comprising: executing a first simulation procedure using input parameters to produce information about a band structure of a simulated material on a first simulation scale specified at least in part by the input parameters, by solving a Schrodinger's equation based on positions and types of atoms; and executing a second simulation procedure using information about the band structure of the simulated material produced in the first simulation procedure to extract parameters on a second simulation scale larger than the first simulation scale. 28 . The method of claim 27 , wherein the second simulation procedure comprises a drift-diffusion simulation procedure. 29 . The method of claim 27 , wherein the second simulation procedure comprises a wave function formalism quantum transport simulation procedure. 30 . The method of claim 27 , wherein the second simulation procedure comprises a Wigner function quantum transport simulation procedure. 31 . The method of claim 27 , wherein the second simulation procedure comprises a Boltzmann transport simulation procedure. 32 . The method of claim 27 , wherein said parameters on a second simulation scale include a device performance metric. 33 . The method of claim 27 , wherein said parameters on a second simulation scale include parameters of a charge distribution. 34 . The method of claim 27 , wherein said parameters on a second simulation scale include parameters of a current-voltage curve.
Logic synthesis; Behaviour synthesis, e.g. mapping logic, HDL to netlist, high-level language to RTL or netlist · CPC title
Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title
Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods · CPC title
Design verification, e.g. functional simulation or model checking · CPC title
using finite element methods [FEM] or finite difference methods [FDM] · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.