NEURAL NETWORK SCHEDULING METHOD AND APPARATUS

NEURAL NETWORK SCHEDULING METHOD AND APPARATUS

A neural network scheduling method and apparatus are provided, so that utilization of an on-chip storage capacity can be improved, and running performance of hardware can be improved. The method includes: determining a first batch size corresponding to each layer in a neural network (S701); forming,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: YUAN, Honghui, LI, Shucheng, XIONG, Lejin, NIKITA, Chernega
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
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 YUAN, Honghui
LI, Shucheng
XIONG, Lejin
NIKITA, Chernega
description A neural network scheduling method and apparatus are provided, so that utilization of an on-chip storage capacity can be improved, and running performance of hardware can be improved. The method includes: determining a first batch size corresponding to each layer in a neural network (S701); forming, through grouping based on the first batch size, the neural network into a neural network including at least one first layer group (S702); forming, through grouping based on a grouping result of the first layer group, the neural network into a neural network including at least one second layer group (S703); and scheduling the neural network based on a grouping result of the second layer group (S704).
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4148627A4</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4148627A4</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4148627A43</originalsourceid><addsrcrecordid>eNrjZNDzcw0NcvRR8HMNCfcP8lYIdvZwdQn18fRzV_B1DfHwd1Fw9APigADHIMeQ0GAeBta0xJziVF4ozc2g4OYa4uyhm1qQH59aXJCYnJqXWhLvGmBiaGJhZmTuaGJMhBIAp8Alfw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>NEURAL NETWORK SCHEDULING METHOD AND APPARATUS</title><source>esp@cenet</source><creator>YUAN, Honghui ; LI, Shucheng ; XIONG, Lejin ; NIKITA, Chernega</creator><creatorcontrib>YUAN, Honghui ; LI, Shucheng ; XIONG, Lejin ; NIKITA, Chernega</creatorcontrib><description>A neural network scheduling method and apparatus are provided, so that utilization of an on-chip storage capacity can be improved, and running performance of hardware can be improved. The method includes: determining a first batch size corresponding to each layer in a neural network (S701); forming, through grouping based on the first batch size, the neural network into a neural network including at least one first layer group (S702); forming, through grouping based on a grouping result of the first layer group, the neural network into a neural network including at least one second layer group (S703); and scheduling the neural network based on a grouping result of the second layer group (S704).</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</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=20230628&amp;DB=EPODOC&amp;CC=EP&amp;NR=4148627A4$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230628&amp;DB=EPODOC&amp;CC=EP&amp;NR=4148627A4$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YUAN, Honghui</creatorcontrib><creatorcontrib>LI, Shucheng</creatorcontrib><creatorcontrib>XIONG, Lejin</creatorcontrib><creatorcontrib>NIKITA, Chernega</creatorcontrib><title>NEURAL NETWORK SCHEDULING METHOD AND APPARATUS</title><description>A neural network scheduling method and apparatus are provided, so that utilization of an on-chip storage capacity can be improved, and running performance of hardware can be improved. The method includes: determining a first batch size corresponding to each layer in a neural network (S701); forming, through grouping based on the first batch size, the neural network into a neural network including at least one first layer group (S702); forming, through grouping based on a grouping result of the first layer group, the neural network into a neural network including at least one second layer group (S703); and scheduling the neural network based on a grouping result of the second layer group (S704).</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNDzcw0NcvRR8HMNCfcP8lYIdvZwdQn18fRzV_B1DfHwd1Fw9APigADHIMeQ0GAeBta0xJziVF4ozc2g4OYa4uyhm1qQH59aXJCYnJqXWhLvGmBiaGJhZmTuaGJMhBIAp8Alfw</recordid><startdate>20230628</startdate><enddate>20230628</enddate><creator>YUAN, Honghui</creator><creator>LI, Shucheng</creator><creator>XIONG, Lejin</creator><creator>NIKITA, Chernega</creator><scope>EVB</scope></search><sort><creationdate>20230628</creationdate><title>NEURAL NETWORK SCHEDULING METHOD AND APPARATUS</title><author>YUAN, Honghui ; LI, Shucheng ; XIONG, Lejin ; NIKITA, Chernega</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4148627A43</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>YUAN, Honghui</creatorcontrib><creatorcontrib>LI, Shucheng</creatorcontrib><creatorcontrib>XIONG, Lejin</creatorcontrib><creatorcontrib>NIKITA, Chernega</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YUAN, Honghui</au><au>LI, Shucheng</au><au>XIONG, Lejin</au><au>NIKITA, Chernega</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>NEURAL NETWORK SCHEDULING METHOD AND APPARATUS</title><date>2023-06-28</date><risdate>2023</risdate><abstract>A neural network scheduling method and apparatus are provided, so that utilization of an on-chip storage capacity can be improved, and running performance of hardware can be improved. The method includes: determining a first batch size corresponding to each layer in a neural network (S701); forming, through grouping based on the first batch size, the neural network into a neural network including at least one first layer group (S702); forming, through grouping based on a grouping result of the first layer group, the neural network into a neural network including at least one second layer group (S703); and scheduling the neural network based on a grouping result of the second layer group (S704).</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4148627A4
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title NEURAL NETWORK SCHEDULING METHOD AND APPARATUS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T10%3A33%3A01IST&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=YUAN,%20Honghui&rft.date=2023-06-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4148627A4%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