ATTACHED ACCELERATOR BASED INFERENCE SERVICE
Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a m...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; fre ; ger |
| 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 | SIVASUBRAMANIAN, Swaminathan DIRAC, Leo Parker SENGUPTA, Sudipta WOOD, Matthew James PERUMALLA, Poorna Chand Srinivas DIVAKARUNI, Dominic Rajeev OLGIATI, Andrea SAHA, Bratin BSHARA, Nafea |
| description | Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a machine learning model and the application instance configuration including: an indication of the central processing unit (CPU) capability to be used, an arithmetic precision of the machine learning model to be used, an indication of the accelerator capability to be used, a storage location of the application, and an indication of an amount of random access memory to use. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP3814899A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP3814899A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP3814899A13</originalsourceid><addsrcrecordid>eNrjZNBxDAlxdPZwdVFwdHZ29XENcgzxD1JwcgwGinj6ubkGufo5uyoEuwaFeTq78jCwpiXmFKfyQmluBgU31xBnD93Ugvz41OKCxOTUvNSSeNcAYwtDEwtLS0dDYyKUAAA8DCSx</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ATTACHED ACCELERATOR BASED INFERENCE SERVICE</title><source>esp@cenet</source><creator>SIVASUBRAMANIAN, Swaminathan ; DIRAC, Leo Parker ; SENGUPTA, Sudipta ; WOOD, Matthew James ; PERUMALLA, Poorna Chand Srinivas ; DIVAKARUNI, Dominic Rajeev ; OLGIATI, Andrea ; SAHA, Bratin ; BSHARA, Nafea</creator><creatorcontrib>SIVASUBRAMANIAN, Swaminathan ; DIRAC, Leo Parker ; SENGUPTA, Sudipta ; WOOD, Matthew James ; PERUMALLA, Poorna Chand Srinivas ; DIVAKARUNI, Dominic Rajeev ; OLGIATI, Andrea ; SAHA, Bratin ; BSHARA, Nafea</creatorcontrib><description>Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a machine learning model and the application instance configuration including: an indication of the central processing unit (CPU) capability to be used, an arithmetic precision of the machine learning model to be used, an indication of the accelerator capability to be used, a storage location of the application, and an indication of an amount of random access memory to use.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2021</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=20210505&DB=EPODOC&CC=EP&NR=3814899A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210505&DB=EPODOC&CC=EP&NR=3814899A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SIVASUBRAMANIAN, Swaminathan</creatorcontrib><creatorcontrib>DIRAC, Leo Parker</creatorcontrib><creatorcontrib>SENGUPTA, Sudipta</creatorcontrib><creatorcontrib>WOOD, Matthew James</creatorcontrib><creatorcontrib>PERUMALLA, Poorna Chand Srinivas</creatorcontrib><creatorcontrib>DIVAKARUNI, Dominic Rajeev</creatorcontrib><creatorcontrib>OLGIATI, Andrea</creatorcontrib><creatorcontrib>SAHA, Bratin</creatorcontrib><creatorcontrib>BSHARA, Nafea</creatorcontrib><title>ATTACHED ACCELERATOR BASED INFERENCE SERVICE</title><description>Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a machine learning model and the application instance configuration including: an indication of the central processing unit (CPU) capability to be used, an arithmetic precision of the machine learning model to be used, an indication of the accelerator capability to be used, a storage location of the application, and an indication of an amount of random access memory to use.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNBxDAlxdPZwdVFwdHZ29XENcgzxD1JwcgwGinj6ubkGufo5uyoEuwaFeTq78jCwpiXmFKfyQmluBgU31xBnD93Ugvz41OKCxOTUvNSSeNcAYwtDEwtLS0dDYyKUAAA8DCSx</recordid><startdate>20210505</startdate><enddate>20210505</enddate><creator>SIVASUBRAMANIAN, Swaminathan</creator><creator>DIRAC, Leo Parker</creator><creator>SENGUPTA, Sudipta</creator><creator>WOOD, Matthew James</creator><creator>PERUMALLA, Poorna Chand Srinivas</creator><creator>DIVAKARUNI, Dominic Rajeev</creator><creator>OLGIATI, Andrea</creator><creator>SAHA, Bratin</creator><creator>BSHARA, Nafea</creator><scope>EVB</scope></search><sort><creationdate>20210505</creationdate><title>ATTACHED ACCELERATOR BASED INFERENCE SERVICE</title><author>SIVASUBRAMANIAN, Swaminathan ; DIRAC, Leo Parker ; SENGUPTA, Sudipta ; WOOD, Matthew James ; PERUMALLA, Poorna Chand Srinivas ; DIVAKARUNI, Dominic Rajeev ; OLGIATI, Andrea ; SAHA, Bratin ; BSHARA, Nafea</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP3814899A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>SIVASUBRAMANIAN, Swaminathan</creatorcontrib><creatorcontrib>DIRAC, Leo Parker</creatorcontrib><creatorcontrib>SENGUPTA, Sudipta</creatorcontrib><creatorcontrib>WOOD, Matthew James</creatorcontrib><creatorcontrib>PERUMALLA, Poorna Chand Srinivas</creatorcontrib><creatorcontrib>DIVAKARUNI, Dominic Rajeev</creatorcontrib><creatorcontrib>OLGIATI, Andrea</creatorcontrib><creatorcontrib>SAHA, Bratin</creatorcontrib><creatorcontrib>BSHARA, Nafea</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SIVASUBRAMANIAN, Swaminathan</au><au>DIRAC, Leo Parker</au><au>SENGUPTA, Sudipta</au><au>WOOD, Matthew James</au><au>PERUMALLA, Poorna Chand Srinivas</au><au>DIVAKARUNI, Dominic Rajeev</au><au>OLGIATI, Andrea</au><au>SAHA, Bratin</au><au>BSHARA, Nafea</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ATTACHED ACCELERATOR BASED INFERENCE SERVICE</title><date>2021-05-05</date><risdate>2021</risdate><abstract>Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a machine learning model and the application instance configuration including: an indication of the central processing unit (CPU) capability to be used, an arithmetic precision of the machine learning model to be used, an indication of the accelerator capability to be used, a storage location of the application, and an indication of an amount of random access memory to use.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; fre ; ger |
| recordid | cdi_epo_espacenet_EP3814899A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | ATTACHED ACCELERATOR BASED INFERENCE SERVICE |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T10%3A03%3A40IST&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=SIVASUBRAMANIAN,%20Swaminathan&rft.date=2021-05-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP3814899A1%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 |