Periodical
Patent Issued for Runtime optimization of computations of an artificial neural network compiled for execution on a deep learning accelerator (USPTO 12725026).
| Τίτλος: | Patent Issued for Runtime optimization of computations of an artificial neural network compiled for execution on a deep learning accelerator (USPTO 12725026). |
|---|---|
| Πηγή: | Pharma Business Week. 9/21/2026, p5631-5631. 1p. |
| Θεματικοί όροι: | *Artificial neural networks, *Integrated circuits, *Mathematical optimization, Compilers (Computer programs), Neural computers, Adaptive computing systems, Semiconductor devices |
| Εταιρία/Οντότητα: | Micron Technology Inc. 093120871 MU |
| Περίληψη: | This article focuses on a patent assigned to Micron Technology Inc. for a compiler designed to optimize the execution of Artificial Neural Networks (ANNs) on integrated circuits with Deep Learning Accelerators (DLAs). The patented technology involves a runtime library embedding a secondary ANN that dynamically predicts and selects optimal execution options based on the data patterns processed by the primary ANN, thereby improving energy efficiency and computation speed. The compiler converts ANN descriptions into executable instructions stored in random access memory, with the embedded ANN continuously learning from performance data to refine execution strategies. This approach supports various hardware configurations and adapts compiler optimizations in real time to enhance the performance of deep learning computations on specialized semiconductor devices. [Extracted from the article] |
| Copyright of Pharma Business Week is the property of NewsRx and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Βάση Δεδομένων: | Business Source Index |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: bsx DbLabel: Business Source Index An: 197130615 RelevancyScore: 1350 AccessLevel: 6 PubType: Periodical PubTypeId: serialPeriodical PreciseRelevancyScore: 1350 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Patent Issued for Runtime optimization of computations of an artificial neural network compiled for execution on a deep learning accelerator (USPTO 12725026). – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Pharma+Business+Week%22">Pharma Business Week</searchLink>. 9/21/2026, p5631-5631. 1p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Integrated+circuits%22">Integrated circuits</searchLink><br />*<searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Compilers+%28Computer+programs%29%22">Compilers (Computer programs)</searchLink><br /><searchLink fieldCode="DE" term="%22Neural+computers%22">Neural computers</searchLink><br /><searchLink fieldCode="DE" term="%22Adaptive+computing+systems%22">Adaptive computing systems</searchLink><br /><searchLink fieldCode="DE" term="%22Semiconductor+devices%22">Semiconductor devices</searchLink> – Name: SubjectCompany Label: Company/Entity Group: Su Data: <searchLink fieldCode="DE" term="%22Micron+Technology+Inc%2E%22">Micron Technology Inc.</searchLink> <searchLink fieldCode="DN" term="%22093120871%22">093120871</searchLink> <searchLink fieldCode="TK" term="%22MU%22">MU</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This article focuses on a patent assigned to Micron Technology Inc. for a compiler designed to optimize the execution of Artificial Neural Networks (ANNs) on integrated circuits with Deep Learning Accelerators (DLAs). The patented technology involves a runtime library embedding a secondary ANN that dynamically predicts and selects optimal execution options based on the data patterns processed by the primary ANN, thereby improving energy efficiency and computation speed. The compiler converts ANN descriptions into executable instructions stored in random access memory, with the embedded ANN continuously learning from performance data to refine execution strategies. This approach supports various hardware configurations and adapts compiler optimizations in real time to enhance the performance of deep learning computations on specialized semiconductor devices. [Extracted from the article] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Pharma Business Week is the property of NewsRx and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=bsx&AN=197130615 |
| RecordInfo | BibRecord: BibEntity: Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 1 StartPage: 5631 Subjects: – SubjectFull: Artificial neural networks Type: general – SubjectFull: Integrated circuits Type: general – SubjectFull: Mathematical optimization Type: general – SubjectFull: Compilers (Computer programs) Type: general – SubjectFull: Neural computers Type: general – SubjectFull: Adaptive computing systems Type: general – SubjectFull: Semiconductor devices Type: general – SubjectFull: Micron Technology Inc. Type: general Titles: – TitleFull: Patent Issued for Runtime optimization of computations of an artificial neural network compiled for execution on a deep learning accelerator (USPTO 12725026). Type: main BibRelationships: IsPartOfRelationships: – BibEntity: Dates: – D: 21 M: 09 Text: 9/21/2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 15436675 Titles: – TitleFull: Pharma Business Week Type: main |
| ResultId | 1 |