Sparsity-aware neural processing unit for performing constant probability index matching and processing method of the same

Sparsity-aware neural processing unit for performing constant probability index matching and processing method of the same

A method of processing of a sparsity-aware neural processing unit includes receiving a plurality of input activations (IA); obtaining a weight having a non-zero value in each weight output channel; storing the weight and the IA in a memory, and obtaining an input channel index comprising a memory ad...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Oh, Youngtaek, Kim, Jae-Joon, Ryu, Sungju
Format: Patent
Sprache:eng
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 Oh, Youngtaek
Kim, Jae-Joon
Ryu, Sungju
description A method of processing of a sparsity-aware neural processing unit includes receiving a plurality of input activations (IA); obtaining a weight having a non-zero value in each weight output channel; storing the weight and the IA in a memory, and obtaining an input channel index comprising a memory address location in which the weight and the IA are stored; and arranging the non-zero weight of each weight output channel according to a row size of an index matching unit (IMU) and matching the IA to the weight in the IMU comprising a buffer memory storing the input channel index.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11928578B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11928578B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11928578B23</originalsourceid><addsrcrecordid>eNqNjLsKwkAQANNYiPoP6wekSESMraLYR-uwuWzMQW7vuN3g4-tNwMLSamAYZp68y4BRrL5SfGAkYBoi9hCiNyRi-Q4DW4XWRwgUR7jJGc-iyDp1Nda2HwdguaEnOFTTTQ1y87txpJ1vwLegHYGgo2Uya7EXWn25SNbn0_V4SSn4iiSgISatbmWW7fNiuysO-eaf5gMRG0hC</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Sparsity-aware neural processing unit for performing constant probability index matching and processing method of the same</title><source>esp@cenet</source><creator>Oh, Youngtaek ; Kim, Jae-Joon ; Ryu, Sungju</creator><creatorcontrib>Oh, Youngtaek ; Kim, Jae-Joon ; Ryu, Sungju</creatorcontrib><description>A method of processing of a sparsity-aware neural processing unit includes receiving a plurality of input activations (IA); obtaining a weight having a non-zero value in each weight output channel; storing the weight and the IA in a memory, and obtaining an input channel index comprising a memory address location in which the weight and the IA are stored; and arranging the non-zero weight of each weight output channel according to a row size of an index matching unit (IMU) and matching the IA to the weight in the IMU comprising a buffer memory storing the input channel index.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2024</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=20240312&amp;DB=EPODOC&amp;CC=US&amp;NR=11928578B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240312&amp;DB=EPODOC&amp;CC=US&amp;NR=11928578B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Oh, Youngtaek</creatorcontrib><creatorcontrib>Kim, Jae-Joon</creatorcontrib><creatorcontrib>Ryu, Sungju</creatorcontrib><title>Sparsity-aware neural processing unit for performing constant probability index matching and processing method of the same</title><description>A method of processing of a sparsity-aware neural processing unit includes receiving a plurality of input activations (IA); obtaining a weight having a non-zero value in each weight output channel; storing the weight and the IA in a memory, and obtaining an input channel index comprising a memory address location in which the weight and the IA are stored; and arranging the non-zero weight of each weight output channel according to a row size of an index matching unit (IMU) and matching the IA to the weight in the IMU comprising a buffer memory storing the input channel index.</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjLsKwkAQANNYiPoP6wekSESMraLYR-uwuWzMQW7vuN3g4-tNwMLSamAYZp68y4BRrL5SfGAkYBoi9hCiNyRi-Q4DW4XWRwgUR7jJGc-iyDp1Nda2HwdguaEnOFTTTQ1y87txpJ1vwLegHYGgo2Uya7EXWn25SNbn0_V4SSn4iiSgISatbmWW7fNiuysO-eaf5gMRG0hC</recordid><startdate>20240312</startdate><enddate>20240312</enddate><creator>Oh, Youngtaek</creator><creator>Kim, Jae-Joon</creator><creator>Ryu, Sungju</creator><scope>EVB</scope></search><sort><creationdate>20240312</creationdate><title>Sparsity-aware neural processing unit for performing constant probability index matching and processing method of the same</title><author>Oh, Youngtaek ; Kim, Jae-Joon ; Ryu, Sungju</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11928578B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</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>Oh, Youngtaek</creatorcontrib><creatorcontrib>Kim, Jae-Joon</creatorcontrib><creatorcontrib>Ryu, Sungju</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Oh, Youngtaek</au><au>Kim, Jae-Joon</au><au>Ryu, Sungju</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Sparsity-aware neural processing unit for performing constant probability index matching and processing method of the same</title><date>2024-03-12</date><risdate>2024</risdate><abstract>A method of processing of a sparsity-aware neural processing unit includes receiving a plurality of input activations (IA); obtaining a weight having a non-zero value in each weight output channel; storing the weight and the IA in a memory, and obtaining an input channel index comprising a memory address location in which the weight and the IA are stored; and arranging the non-zero weight of each weight output channel according to a row size of an index matching unit (IMU) and matching the IA to the weight in the IMU comprising a buffer memory storing the input channel index.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US11928578B2
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Sparsity-aware neural processing unit for performing constant probability index matching and processing method of the same
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T14%3A04%3A44IST&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=Oh,%20Youngtaek&rft.date=2024-03-12&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11928578B2%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