Platform for concurrent execution of GPU operations
Computing resources may be optimally allocated for a multipath neural network using a multipath neural network analyzer that includes an interface and a processing device. The interface receives a multipath neural network. The processing device generates the multipath neural network to include one o...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| 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 | Ki, Yang Seok Pourghassemi Najafabadi, Behnam Lee, Joo Hwan |
| description | Computing resources may be optimally allocated for a multipath neural network using a multipath neural network analyzer that includes an interface and a processing device. The interface receives a multipath neural network. The processing device generates the multipath neural network to include one or more layers of a critical path through the multipath neural network that are allocated a first allocation of computing resources that are available to execute the multipath neural network. The critical path limits throughput of the multipath neural network. The first allocation of computing resources reduces an execution time of the multipath neural network to be less than a baseline execution time of a second allocation of computing resources for the multipath neural network. The first allocation of computing resources for a first layer of the critical path is different than the second allocation of computing resources for the first layer of the critical path. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11620510B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11620510B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11620510B23</originalsourceid><addsrcrecordid>eNrjZDAOyEksScsvylUAEgrJ-XnJpUVFqXklCqkVqcmlJZn5eQr5aQruAaEK-QWpRYkggWIeBta0xJziVF4ozc2g6OYa4uyhm1qQH59aXJCYnJqXWhIfGmxoaGZkYGpo4GRkTIwaAA3RLJY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Platform for concurrent execution of GPU operations</title><source>esp@cenet</source><creator>Ki, Yang Seok ; Pourghassemi Najafabadi, Behnam ; Lee, Joo Hwan</creator><creatorcontrib>Ki, Yang Seok ; Pourghassemi Najafabadi, Behnam ; Lee, Joo Hwan</creatorcontrib><description>Computing resources may be optimally allocated for a multipath neural network using a multipath neural network analyzer that includes an interface and a processing device. The interface receives a multipath neural network. The processing device generates the multipath neural network to include one or more layers of a critical path through the multipath neural network that are allocated a first allocation of computing resources that are available to execute the multipath neural network. The critical path limits throughput of the multipath neural network. The first allocation of computing resources reduces an execution time of the multipath neural network to be less than a baseline execution time of a second allocation of computing resources for the multipath neural network. The first allocation of computing resources for a first layer of the critical path is different than the second allocation of computing resources for the first layer of the critical path.</description><language>eng</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&date=20230404&DB=EPODOC&CC=US&NR=11620510B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230404&DB=EPODOC&CC=US&NR=11620510B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Ki, Yang Seok</creatorcontrib><creatorcontrib>Pourghassemi Najafabadi, Behnam</creatorcontrib><creatorcontrib>Lee, Joo Hwan</creatorcontrib><title>Platform for concurrent execution of GPU operations</title><description>Computing resources may be optimally allocated for a multipath neural network using a multipath neural network analyzer that includes an interface and a processing device. The interface receives a multipath neural network. The processing device generates the multipath neural network to include one or more layers of a critical path through the multipath neural network that are allocated a first allocation of computing resources that are available to execute the multipath neural network. The critical path limits throughput of the multipath neural network. The first allocation of computing resources reduces an execution time of the multipath neural network to be less than a baseline execution time of a second allocation of computing resources for the multipath neural network. The first allocation of computing resources for a first layer of the critical path is different than the second allocation of computing resources for the first layer of the critical path.</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>eNrjZDAOyEksScsvylUAEgrJ-XnJpUVFqXklCqkVqcmlJZn5eQr5aQruAaEK-QWpRYkggWIeBta0xJziVF4ozc2g6OYa4uyhm1qQH59aXJCYnJqXWhIfGmxoaGZkYGpo4GRkTIwaAA3RLJY</recordid><startdate>20230404</startdate><enddate>20230404</enddate><creator>Ki, Yang Seok</creator><creator>Pourghassemi Najafabadi, Behnam</creator><creator>Lee, Joo Hwan</creator><scope>EVB</scope></search><sort><creationdate>20230404</creationdate><title>Platform for concurrent execution of GPU operations</title><author>Ki, Yang Seok ; Pourghassemi Najafabadi, Behnam ; Lee, Joo Hwan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11620510B23</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Ki, Yang Seok</creatorcontrib><creatorcontrib>Pourghassemi Najafabadi, Behnam</creatorcontrib><creatorcontrib>Lee, Joo Hwan</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ki, Yang Seok</au><au>Pourghassemi Najafabadi, Behnam</au><au>Lee, Joo Hwan</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Platform for concurrent execution of GPU operations</title><date>2023-04-04</date><risdate>2023</risdate><abstract>Computing resources may be optimally allocated for a multipath neural network using a multipath neural network analyzer that includes an interface and a processing device. The interface receives a multipath neural network. The processing device generates the multipath neural network to include one or more layers of a critical path through the multipath neural network that are allocated a first allocation of computing resources that are available to execute the multipath neural network. The critical path limits throughput of the multipath neural network. The first allocation of computing resources reduces an execution time of the multipath neural network to be less than a baseline execution time of a second allocation of computing resources for the multipath neural network. The first allocation of computing resources for a first layer of the critical path is different than the second allocation of computing resources for the first layer of the critical path.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US11620510B2 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Platform for concurrent execution of GPU operations |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T03%3A34%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=Ki,%20Yang%20Seok&rft.date=2023-04-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11620510B2%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 |