FLEXIBLE ACCELERATOR FOR SPARSE TENSORS IN CONVOLUTIONAL NEURAL NETWORKS

FLEXIBLE ACCELERATOR FOR SPARSE TENSORS IN CONVOLUTIONAL NEURAL NETWORKS

A system with a multiplication circuit having a plurality of multipliers is disclosed. Each of the plurality of multipliers is configured to receive a data value and a weight value to generate a product value in a convolution operation of a machine learning application. The system also includes an a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: GUNNAM, Kiran, BANDIC, Zvonimir, KULKARNI, Anand
Format: Patent
Sprache:eng ; fre ; ger
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 GUNNAM, Kiran
BANDIC, Zvonimir
KULKARNI, Anand
description A system with a multiplication circuit having a plurality of multipliers is disclosed. Each of the plurality of multipliers is configured to receive a data value and a weight value to generate a product value in a convolution operation of a machine learning application. The system also includes an accumulator configured to receive the product value from each of the plurality of multipliers and a register bank configured to store an output of the convolution operation. The accumulator is further configured to receive a portion of values stored in the register bank and combine the received portion of values with the product values to generate combined values. The register bank is further configured to replace the portion of values with the combined values.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4128063A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4128063A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4128063A13</originalsourceid><addsrcrecordid>eNrjZPBw83GN8HTycVVwdHZ29XENcgzxD1JwA-LgAMegYFeFEFe_YP-gYAVPPwVnf78wf5_QEE9_P0cfBT_X0CAwFRLuH-QdzMPAmpaYU5zKC6W5GRTcXEOcPXRTC_LjU4sLEpNT81JL4l0DTAyNLAzMjB0NjYlQAgDdTCzi</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>FLEXIBLE ACCELERATOR FOR SPARSE TENSORS IN CONVOLUTIONAL NEURAL NETWORKS</title><source>esp@cenet</source><creator>GUNNAM, Kiran ; BANDIC, Zvonimir ; KULKARNI, Anand</creator><creatorcontrib>GUNNAM, Kiran ; BANDIC, Zvonimir ; KULKARNI, Anand</creatorcontrib><description>A system with a multiplication circuit having a plurality of multipliers is disclosed. Each of the plurality of multipliers is configured to receive a data value and a weight value to generate a product value in a convolution operation of a machine learning application. The system also includes an accumulator configured to receive the product value from each of the plurality of multipliers and a register bank configured to store an output of the convolution operation. The accumulator is further configured to receive a portion of values stored in the register bank and combine the received portion of values with the product values to generate combined values. The register bank is further configured to replace the portion of values with the combined values.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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=20230208&amp;DB=EPODOC&amp;CC=EP&amp;NR=4128063A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25568,76551</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230208&amp;DB=EPODOC&amp;CC=EP&amp;NR=4128063A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>GUNNAM, Kiran</creatorcontrib><creatorcontrib>BANDIC, Zvonimir</creatorcontrib><creatorcontrib>KULKARNI, Anand</creatorcontrib><title>FLEXIBLE ACCELERATOR FOR SPARSE TENSORS IN CONVOLUTIONAL NEURAL NETWORKS</title><description>A system with a multiplication circuit having a plurality of multipliers is disclosed. Each of the plurality of multipliers is configured to receive a data value and a weight value to generate a product value in a convolution operation of a machine learning application. The system also includes an accumulator configured to receive the product value from each of the plurality of multipliers and a register bank configured to store an output of the convolution operation. The accumulator is further configured to receive a portion of values stored in the register bank and combine the received portion of values with the product values to generate combined values. The register bank is further configured to replace the portion of values with the combined values.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPBw83GN8HTycVVwdHZ29XENcgzxD1JwA-LgAMegYFeFEFe_YP-gYAVPPwVnf78wf5_QEE9_P0cfBT_X0CAwFRLuH-QdzMPAmpaYU5zKC6W5GRTcXEOcPXRTC_LjU4sLEpNT81JL4l0DTAyNLAzMjB0NjYlQAgDdTCzi</recordid><startdate>20230208</startdate><enddate>20230208</enddate><creator>GUNNAM, Kiran</creator><creator>BANDIC, Zvonimir</creator><creator>KULKARNI, Anand</creator><scope>EVB</scope></search><sort><creationdate>20230208</creationdate><title>FLEXIBLE ACCELERATOR FOR SPARSE TENSORS IN CONVOLUTIONAL NEURAL NETWORKS</title><author>GUNNAM, Kiran ; BANDIC, Zvonimir ; KULKARNI, Anand</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4128063A13</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>GUNNAM, Kiran</creatorcontrib><creatorcontrib>BANDIC, Zvonimir</creatorcontrib><creatorcontrib>KULKARNI, Anand</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>GUNNAM, Kiran</au><au>BANDIC, Zvonimir</au><au>KULKARNI, Anand</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>FLEXIBLE ACCELERATOR FOR SPARSE TENSORS IN CONVOLUTIONAL NEURAL NETWORKS</title><date>2023-02-08</date><risdate>2023</risdate><abstract>A system with a multiplication circuit having a plurality of multipliers is disclosed. Each of the plurality of multipliers is configured to receive a data value and a weight value to generate a product value in a convolution operation of a machine learning application. The system also includes an accumulator configured to receive the product value from each of the plurality of multipliers and a register bank configured to store an output of the convolution operation. The accumulator is further configured to receive a portion of values stored in the register bank and combine the received portion of values with the product values to generate combined values. The register bank is further configured to replace the portion of values with the combined values.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4128063A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title FLEXIBLE ACCELERATOR FOR SPARSE TENSORS IN CONVOLUTIONAL NEURAL NETWORKS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T05%3A09%3A03IST&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=GUNNAM,%20Kiran&rft.date=2023-02-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4128063A1%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