BROADCASTING MODE OF PLANAR ENGINE FOR NEURAL PROCESSOR
Embodiments relate to a neural processor that includes one or more neural engine circuits and planar engine circuits. The neural engine circuits can perform convolution operations of input data with one or more kernels to generate outputs. The planar engine circuit is coupled to the plurality of neu...
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 | Kim, Youchang Mills, Christopher L Waters, Kenneth W |
| description | Embodiments relate to a neural processor that includes one or more neural engine circuits and planar engine circuits. The neural engine circuits can perform convolution operations of input data with one or more kernels to generate outputs. The planar engine circuit is coupled to the plurality of neural engine circuits. A planar engine circuit can be configured to multiple modes. In an elementwise mode, the planar engine circuit may combine two tensors by performing operations element by element. The planar engine circuit may support elementwise operation for two tensors that are in different sizes and ranks. The planar engine circuit may perform a broadcasting operation to duplicate one or more values across one or more channels to make a smaller tensor matching the size of the larger tensor. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2023206051A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2023206051A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2023206051A13</originalsourceid><addsrcrecordid>eNrjZDB3CvJ3dHF2DA7x9HNX8PV3cVXwd1MI8HH0cwxScPVz9_RzVXDzD1Lwcw0NcvRRCAjyd3YNDvYP4mFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGxkYGZgamho6GxsSpAgDGYSjp</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>BROADCASTING MODE OF PLANAR ENGINE FOR NEURAL PROCESSOR</title><source>esp@cenet</source><creator>Kim, Youchang ; Mills, Christopher L ; Waters, Kenneth W</creator><creatorcontrib>Kim, Youchang ; Mills, Christopher L ; Waters, Kenneth W</creatorcontrib><description>Embodiments relate to a neural processor that includes one or more neural engine circuits and planar engine circuits. The neural engine circuits can perform convolution operations of input data with one or more kernels to generate outputs. The planar engine circuit is coupled to the plurality of neural engine circuits. A planar engine circuit can be configured to multiple modes. In an elementwise mode, the planar engine circuit may combine two tensors by performing operations element by element. The planar engine circuit may support elementwise operation for two tensors that are in different sizes and ranks. The planar engine circuit may perform a broadcasting operation to duplicate one or more values across one or more channels to make a smaller tensor matching the size of the larger tensor.</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=20230629&DB=EPODOC&CC=US&NR=2023206051A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230629&DB=EPODOC&CC=US&NR=2023206051A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Kim, Youchang</creatorcontrib><creatorcontrib>Mills, Christopher L</creatorcontrib><creatorcontrib>Waters, Kenneth W</creatorcontrib><title>BROADCASTING MODE OF PLANAR ENGINE FOR NEURAL PROCESSOR</title><description>Embodiments relate to a neural processor that includes one or more neural engine circuits and planar engine circuits. The neural engine circuits can perform convolution operations of input data with one or more kernels to generate outputs. The planar engine circuit is coupled to the plurality of neural engine circuits. A planar engine circuit can be configured to multiple modes. In an elementwise mode, the planar engine circuit may combine two tensors by performing operations element by element. The planar engine circuit may support elementwise operation for two tensors that are in different sizes and ranks. The planar engine circuit may perform a broadcasting operation to duplicate one or more values across one or more channels to make a smaller tensor matching the size of the larger tensor.</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>eNrjZDB3CvJ3dHF2DA7x9HNX8PV3cVXwd1MI8HH0cwxScPVz9_RzVXDzD1Lwcw0NcvRRCAjyd3YNDvYP4mFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGxkYGZgamho6GxsSpAgDGYSjp</recordid><startdate>20230629</startdate><enddate>20230629</enddate><creator>Kim, Youchang</creator><creator>Mills, Christopher L</creator><creator>Waters, Kenneth W</creator><scope>EVB</scope></search><sort><creationdate>20230629</creationdate><title>BROADCASTING MODE OF PLANAR ENGINE FOR NEURAL PROCESSOR</title><author>Kim, Youchang ; Mills, Christopher L ; Waters, Kenneth W</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2023206051A13</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>Kim, Youchang</creatorcontrib><creatorcontrib>Mills, Christopher L</creatorcontrib><creatorcontrib>Waters, Kenneth W</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kim, Youchang</au><au>Mills, Christopher L</au><au>Waters, Kenneth W</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>BROADCASTING MODE OF PLANAR ENGINE FOR NEURAL PROCESSOR</title><date>2023-06-29</date><risdate>2023</risdate><abstract>Embodiments relate to a neural processor that includes one or more neural engine circuits and planar engine circuits. The neural engine circuits can perform convolution operations of input data with one or more kernels to generate outputs. The planar engine circuit is coupled to the plurality of neural engine circuits. A planar engine circuit can be configured to multiple modes. In an elementwise mode, the planar engine circuit may combine two tensors by performing operations element by element. The planar engine circuit may support elementwise operation for two tensors that are in different sizes and ranks. The planar engine circuit may perform a broadcasting operation to duplicate one or more values across one or more channels to make a smaller tensor matching the size of the larger tensor.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2023206051A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | BROADCASTING MODE OF PLANAR ENGINE FOR NEURAL PROCESSOR |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T00%3A56%3A18IST&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=Kim,%20Youchang&rft.date=2023-06-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2023206051A1%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 |