HARDWARE ACCELERATED NEURAL NETWORK SUBGRAPHS

HARDWARE ACCELERATED NEURAL NETWORK SUBGRAPHS

Technology related to hardware accelerated neural network subgraphs is disclosed. In one example of the disclosed technology, a method for compiling a neural network model is disclosed. The method includes identifying a subgraph of the neural network model to partition from the neural network model....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: El Husseini, Ahmad Mahdi, Reinhardt, Steven K, Rapsang, Amanda Grace, van Megen, Friedel, Boehn, Christian
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator El Husseini, Ahmad Mahdi
Reinhardt, Steven K
Rapsang, Amanda Grace
van Megen, Friedel
Boehn, Christian
description Technology related to hardware accelerated neural network subgraphs is disclosed. In one example of the disclosed technology, a method for compiling a neural network model is disclosed. The method includes identifying a subgraph of the neural network model to partition from the neural network model. An interface can be inserted between the neural network model and a partitioned version of the identified subgraph. The partitioned version can be adapted to be evaluated with a neural network accelerator. The identified subgraph can be compiled to the neural network accelerator to generate configuration information for the neural network accelerator. The neural network accelerator can be configured with the configuration information to provide an accelerated version of the subgraph.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2019286972A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2019286972A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2019286972A13</originalsourceid><addsrcrecordid>eNrjZND1cAxyCXcMclVwdHZ29XENcgxxdVHwcw0NcvQBUiHh_kHeCsGhTu5BjgEewTwMrGmJOcWpvFCam0HZzTXE2UM3tSA_PrW4IDE5NS-1JD402MjA0NLIwszS3MjR0Jg4VQBgPyaf</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>HARDWARE ACCELERATED NEURAL NETWORK SUBGRAPHS</title><source>esp@cenet</source><creator>El Husseini, Ahmad Mahdi ; Reinhardt, Steven K ; Rapsang, Amanda Grace ; van Megen, Friedel ; Boehn, Christian</creator><creatorcontrib>El Husseini, Ahmad Mahdi ; Reinhardt, Steven K ; Rapsang, Amanda Grace ; van Megen, Friedel ; Boehn, Christian</creatorcontrib><description>Technology related to hardware accelerated neural network subgraphs is disclosed. In one example of the disclosed technology, a method for compiling a neural network model is disclosed. The method includes identifying a subgraph of the neural network model to partition from the neural network model. An interface can be inserted between the neural network model and a partitioned version of the identified subgraph. The partitioned version can be adapted to be evaluated with a neural network accelerator. The identified subgraph can be compiled to the neural network accelerator to generate configuration information for the neural network accelerator. The neural network accelerator can be configured with the configuration information to provide an accelerated version of the subgraph.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2019</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20190919&amp;DB=EPODOC&amp;CC=US&amp;NR=2019286972A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20190919&amp;DB=EPODOC&amp;CC=US&amp;NR=2019286972A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>El Husseini, Ahmad Mahdi</creatorcontrib><creatorcontrib>Reinhardt, Steven K</creatorcontrib><creatorcontrib>Rapsang, Amanda Grace</creatorcontrib><creatorcontrib>van Megen, Friedel</creatorcontrib><creatorcontrib>Boehn, Christian</creatorcontrib><title>HARDWARE ACCELERATED NEURAL NETWORK SUBGRAPHS</title><description>Technology related to hardware accelerated neural network subgraphs is disclosed. In one example of the disclosed technology, a method for compiling a neural network model is disclosed. The method includes identifying a subgraph of the neural network model to partition from the neural network model. An interface can be inserted between the neural network model and a partitioned version of the identified subgraph. The partitioned version can be adapted to be evaluated with a neural network accelerator. The identified subgraph can be compiled to the neural network accelerator to generate configuration information for the neural network accelerator. The neural network accelerator can be configured with the configuration information to provide an accelerated version of the subgraph.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZND1cAxyCXcMclVwdHZ29XENcgxxdVHwcw0NcvQBUiHh_kHeCsGhTu5BjgEewTwMrGmJOcWpvFCam0HZzTXE2UM3tSA_PrW4IDE5NS-1JD402MjA0NLIwszS3MjR0Jg4VQBgPyaf</recordid><startdate>20190919</startdate><enddate>20190919</enddate><creator>El Husseini, Ahmad Mahdi</creator><creator>Reinhardt, Steven K</creator><creator>Rapsang, Amanda Grace</creator><creator>van Megen, Friedel</creator><creator>Boehn, Christian</creator><scope>EVB</scope></search><sort><creationdate>20190919</creationdate><title>HARDWARE ACCELERATED NEURAL NETWORK SUBGRAPHS</title><author>El Husseini, Ahmad Mahdi ; Reinhardt, Steven K ; Rapsang, Amanda Grace ; van Megen, Friedel ; Boehn, Christian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2019286972A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>El Husseini, Ahmad Mahdi</creatorcontrib><creatorcontrib>Reinhardt, Steven K</creatorcontrib><creatorcontrib>Rapsang, Amanda Grace</creatorcontrib><creatorcontrib>van Megen, Friedel</creatorcontrib><creatorcontrib>Boehn, Christian</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>El Husseini, Ahmad Mahdi</au><au>Reinhardt, Steven K</au><au>Rapsang, Amanda Grace</au><au>van Megen, Friedel</au><au>Boehn, Christian</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>HARDWARE ACCELERATED NEURAL NETWORK SUBGRAPHS</title><date>2019-09-19</date><risdate>2019</risdate><abstract>Technology related to hardware accelerated neural network subgraphs is disclosed. In one example of the disclosed technology, a method for compiling a neural network model is disclosed. The method includes identifying a subgraph of the neural network model to partition from the neural network model. An interface can be inserted between the neural network model and a partitioned version of the identified subgraph. The partitioned version can be adapted to be evaluated with a neural network accelerator. The identified subgraph can be compiled to the neural network accelerator to generate configuration information for the neural network accelerator. The neural network accelerator can be configured with the configuration information to provide an accelerated version of the subgraph.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2019286972A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title HARDWARE ACCELERATED NEURAL NETWORK SUBGRAPHS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-15T11%3A09%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=El%20Husseini,%20Ahmad%20Mahdi&rft.date=2019-09-19&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2019286972A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true