Compute optimization mechanism for deep neural networks

Embodiments provide mechanisms to facilitate compute operations for deep neural networks. One embodiment comprises a graphics processing unit comprising one or more multiprocessors, at least one of the one or more multiprocessors including a register file to store a plurality of different types of o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Satish, Nadathur Rajagopalan, Ashbaugh, Ben J, Galoppo Von Borries, Nicolas C, Akhbari, Farshad, Ray, Joydeep, Srinivasa, Narayan, Maiyuran, Subramaniam, Schluessler, Travis T, Feit, John H, Gottschlich, Justin E, Boles, Jeffery S, Vaidyanathan, Karthik, Surti, Prasoonkumar, Nurvitadhi, Eriko, Burke, Devan, Hurd, Linda L, Appu, Abhishek R, Chen, Feng, Baghsorkhi, Sara S, Lake, Adam T, Lin, Tsung-Han, Fu, Wenyin, Koker, Altug, Kim, Dukhwan, Sinha, Kamal, Vembu, Balaji, Barik, Rajkishore, Mastronarde, Josh B
Format: Patent
Sprache:eng
Schlagworte:
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 Satish, Nadathur Rajagopalan
Ashbaugh, Ben J
Galoppo Von Borries, Nicolas C
Akhbari, Farshad
Ray, Joydeep
Srinivasa, Narayan
Maiyuran, Subramaniam
Schluessler, Travis T
Feit, John H
Gottschlich, Justin E
Boles, Jeffery S
Vaidyanathan, Karthik
Surti, Prasoonkumar
Nurvitadhi, Eriko
Burke, Devan
Hurd, Linda L
Appu, Abhishek R
Chen, Feng
Baghsorkhi, Sara S
Lake, Adam T
Lin, Tsung-Han
Fu, Wenyin
Koker, Altug
Kim, Dukhwan
Sinha, Kamal
Vembu, Balaji
Barik, Rajkishore
Mastronarde, Josh B
description Embodiments provide mechanisms to facilitate compute operations for deep neural networks. One embodiment comprises a graphics processing unit comprising one or more multiprocessors, at least one of the one or more multiprocessors including a register file to store a plurality of different types of operands and a plurality of processing cores. The plurality of processing cores includes a first set of processing cores of a first type and a second set of processing cores of a second type. The first set of processing cores are associated with a first memory channel and the second set of processing cores are associated with a second memory channel.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11593910B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11593910B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11593910B23</originalsourceid><addsrcrecordid>eNrjZDB3zs8tKC1JVcgvKMnMzaxKLMnMz1PITU3OSMzLLM5VSMsvUkhJTS1QyEstLUrMAVIl5flF2cU8DKxpiTnFqbxQmptB0c01xNlDN7UgPz61uCAxORWoND402NDQ1NLY0tDAyciYGDUAHsourg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Compute optimization mechanism for deep neural networks</title><source>esp@cenet</source><creator>Satish, Nadathur Rajagopalan ; Ashbaugh, Ben J ; Galoppo Von Borries, Nicolas C ; Akhbari, Farshad ; Ray, Joydeep ; Srinivasa, Narayan ; Maiyuran, Subramaniam ; Schluessler, Travis T ; Feit, John H ; Gottschlich, Justin E ; Boles, Jeffery S ; Vaidyanathan, Karthik ; Surti, Prasoonkumar ; Nurvitadhi, Eriko ; Burke, Devan ; Hurd, Linda L ; Appu, Abhishek R ; Chen, Feng ; Baghsorkhi, Sara S ; Lake, Adam T ; Lin, Tsung-Han ; Fu, Wenyin ; Koker, Altug ; Kim, Dukhwan ; Sinha, Kamal ; Vembu, Balaji ; Barik, Rajkishore ; Mastronarde, Josh B</creator><creatorcontrib>Satish, Nadathur Rajagopalan ; Ashbaugh, Ben J ; Galoppo Von Borries, Nicolas C ; Akhbari, Farshad ; Ray, Joydeep ; Srinivasa, Narayan ; Maiyuran, Subramaniam ; Schluessler, Travis T ; Feit, John H ; Gottschlich, Justin E ; Boles, Jeffery S ; Vaidyanathan, Karthik ; Surti, Prasoonkumar ; Nurvitadhi, Eriko ; Burke, Devan ; Hurd, Linda L ; Appu, Abhishek R ; Chen, Feng ; Baghsorkhi, Sara S ; Lake, Adam T ; Lin, Tsung-Han ; Fu, Wenyin ; Koker, Altug ; Kim, Dukhwan ; Sinha, Kamal ; Vembu, Balaji ; Barik, Rajkishore ; Mastronarde, Josh B</creatorcontrib><description>Embodiments provide mechanisms to facilitate compute operations for deep neural networks. One embodiment comprises a graphics processing unit comprising one or more multiprocessors, at least one of the one or more multiprocessors including a register file to store a plurality of different types of operands and a plurality of processing cores. The plurality of processing cores includes a first set of processing cores of a first type and a second set of processing cores of a second type. The first set of processing cores are associated with a first memory channel and the second set of processing cores are associated with a second memory channel.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; 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=20230228&amp;DB=EPODOC&amp;CC=US&amp;NR=11593910B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230228&amp;DB=EPODOC&amp;CC=US&amp;NR=11593910B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Satish, Nadathur Rajagopalan</creatorcontrib><creatorcontrib>Ashbaugh, Ben J</creatorcontrib><creatorcontrib>Galoppo Von Borries, Nicolas C</creatorcontrib><creatorcontrib>Akhbari, Farshad</creatorcontrib><creatorcontrib>Ray, Joydeep</creatorcontrib><creatorcontrib>Srinivasa, Narayan</creatorcontrib><creatorcontrib>Maiyuran, Subramaniam</creatorcontrib><creatorcontrib>Schluessler, Travis T</creatorcontrib><creatorcontrib>Feit, John H</creatorcontrib><creatorcontrib>Gottschlich, Justin E</creatorcontrib><creatorcontrib>Boles, Jeffery S</creatorcontrib><creatorcontrib>Vaidyanathan, Karthik</creatorcontrib><creatorcontrib>Surti, Prasoonkumar</creatorcontrib><creatorcontrib>Nurvitadhi, Eriko</creatorcontrib><creatorcontrib>Burke, Devan</creatorcontrib><creatorcontrib>Hurd, Linda L</creatorcontrib><creatorcontrib>Appu, Abhishek R</creatorcontrib><creatorcontrib>Chen, Feng</creatorcontrib><creatorcontrib>Baghsorkhi, Sara S</creatorcontrib><creatorcontrib>Lake, Adam T</creatorcontrib><creatorcontrib>Lin, Tsung-Han</creatorcontrib><creatorcontrib>Fu, Wenyin</creatorcontrib><creatorcontrib>Koker, Altug</creatorcontrib><creatorcontrib>Kim, Dukhwan</creatorcontrib><creatorcontrib>Sinha, Kamal</creatorcontrib><creatorcontrib>Vembu, Balaji</creatorcontrib><creatorcontrib>Barik, Rajkishore</creatorcontrib><creatorcontrib>Mastronarde, Josh B</creatorcontrib><title>Compute optimization mechanism for deep neural networks</title><description>Embodiments provide mechanisms to facilitate compute operations for deep neural networks. One embodiment comprises a graphics processing unit comprising one or more multiprocessors, at least one of the one or more multiprocessors including a register file to store a plurality of different types of operands and a plurality of processing cores. The plurality of processing cores includes a first set of processing cores of a first type and a second set of processing cores of a second type. The first set of processing cores are associated with a first memory channel and the second set of processing cores are associated with a second memory channel.</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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDB3zs8tKC1JVcgvKMnMzaxKLMnMz1PITU3OSMzLLM5VSMsvUkhJTS1QyEstLUrMAVIl5flF2cU8DKxpiTnFqbxQmptB0c01xNlDN7UgPz61uCAxORWoND402NDQ1NLY0tDAyciYGDUAHsourg</recordid><startdate>20230228</startdate><enddate>20230228</enddate><creator>Satish, Nadathur Rajagopalan</creator><creator>Ashbaugh, Ben J</creator><creator>Galoppo Von Borries, Nicolas C</creator><creator>Akhbari, Farshad</creator><creator>Ray, Joydeep</creator><creator>Srinivasa, Narayan</creator><creator>Maiyuran, Subramaniam</creator><creator>Schluessler, Travis T</creator><creator>Feit, John H</creator><creator>Gottschlich, Justin E</creator><creator>Boles, Jeffery S</creator><creator>Vaidyanathan, Karthik</creator><creator>Surti, Prasoonkumar</creator><creator>Nurvitadhi, Eriko</creator><creator>Burke, Devan</creator><creator>Hurd, Linda L</creator><creator>Appu, Abhishek R</creator><creator>Chen, Feng</creator><creator>Baghsorkhi, Sara S</creator><creator>Lake, Adam T</creator><creator>Lin, Tsung-Han</creator><creator>Fu, Wenyin</creator><creator>Koker, Altug</creator><creator>Kim, Dukhwan</creator><creator>Sinha, Kamal</creator><creator>Vembu, Balaji</creator><creator>Barik, Rajkishore</creator><creator>Mastronarde, Josh B</creator><scope>EVB</scope></search><sort><creationdate>20230228</creationdate><title>Compute optimization mechanism for deep neural networks</title><author>Satish, Nadathur Rajagopalan ; Ashbaugh, Ben J ; Galoppo Von Borries, Nicolas C ; Akhbari, Farshad ; Ray, Joydeep ; Srinivasa, Narayan ; Maiyuran, Subramaniam ; Schluessler, Travis T ; Feit, John H ; Gottschlich, Justin E ; Boles, Jeffery S ; Vaidyanathan, Karthik ; Surti, Prasoonkumar ; Nurvitadhi, Eriko ; Burke, Devan ; Hurd, Linda L ; Appu, Abhishek R ; Chen, Feng ; Baghsorkhi, Sara S ; Lake, Adam T ; Lin, Tsung-Han ; Fu, Wenyin ; Koker, Altug ; Kim, Dukhwan ; Sinha, Kamal ; Vembu, Balaji ; Barik, Rajkishore ; Mastronarde, Josh B</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11593910B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Satish, Nadathur Rajagopalan</creatorcontrib><creatorcontrib>Ashbaugh, Ben J</creatorcontrib><creatorcontrib>Galoppo Von Borries, Nicolas C</creatorcontrib><creatorcontrib>Akhbari, Farshad</creatorcontrib><creatorcontrib>Ray, Joydeep</creatorcontrib><creatorcontrib>Srinivasa, Narayan</creatorcontrib><creatorcontrib>Maiyuran, Subramaniam</creatorcontrib><creatorcontrib>Schluessler, Travis T</creatorcontrib><creatorcontrib>Feit, John H</creatorcontrib><creatorcontrib>Gottschlich, Justin E</creatorcontrib><creatorcontrib>Boles, Jeffery S</creatorcontrib><creatorcontrib>Vaidyanathan, Karthik</creatorcontrib><creatorcontrib>Surti, Prasoonkumar</creatorcontrib><creatorcontrib>Nurvitadhi, Eriko</creatorcontrib><creatorcontrib>Burke, Devan</creatorcontrib><creatorcontrib>Hurd, Linda L</creatorcontrib><creatorcontrib>Appu, Abhishek R</creatorcontrib><creatorcontrib>Chen, Feng</creatorcontrib><creatorcontrib>Baghsorkhi, Sara S</creatorcontrib><creatorcontrib>Lake, Adam T</creatorcontrib><creatorcontrib>Lin, Tsung-Han</creatorcontrib><creatorcontrib>Fu, Wenyin</creatorcontrib><creatorcontrib>Koker, Altug</creatorcontrib><creatorcontrib>Kim, Dukhwan</creatorcontrib><creatorcontrib>Sinha, Kamal</creatorcontrib><creatorcontrib>Vembu, Balaji</creatorcontrib><creatorcontrib>Barik, Rajkishore</creatorcontrib><creatorcontrib>Mastronarde, Josh B</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Satish, Nadathur Rajagopalan</au><au>Ashbaugh, Ben J</au><au>Galoppo Von Borries, Nicolas C</au><au>Akhbari, Farshad</au><au>Ray, Joydeep</au><au>Srinivasa, Narayan</au><au>Maiyuran, Subramaniam</au><au>Schluessler, Travis T</au><au>Feit, John H</au><au>Gottschlich, Justin E</au><au>Boles, Jeffery S</au><au>Vaidyanathan, Karthik</au><au>Surti, Prasoonkumar</au><au>Nurvitadhi, Eriko</au><au>Burke, Devan</au><au>Hurd, Linda L</au><au>Appu, Abhishek R</au><au>Chen, Feng</au><au>Baghsorkhi, Sara S</au><au>Lake, Adam T</au><au>Lin, Tsung-Han</au><au>Fu, Wenyin</au><au>Koker, Altug</au><au>Kim, Dukhwan</au><au>Sinha, Kamal</au><au>Vembu, Balaji</au><au>Barik, Rajkishore</au><au>Mastronarde, Josh B</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Compute optimization mechanism for deep neural networks</title><date>2023-02-28</date><risdate>2023</risdate><abstract>Embodiments provide mechanisms to facilitate compute operations for deep neural networks. One embodiment comprises a graphics processing unit comprising one or more multiprocessors, at least one of the one or more multiprocessors including a register file to store a plurality of different types of operands and a plurality of processing cores. The plurality of processing cores includes a first set of processing cores of a first type and a second set of processing cores of a second type. The first set of processing cores are associated with a first memory channel and the second set of processing cores are associated with a second memory channel.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US11593910B2
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Compute optimization mechanism for deep neural networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T14%3A23%3A28IST&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=Satish,%20Nadathur%20Rajagopalan&rft.date=2023-02-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11593910B2%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