PROGRAMMABLE MATRIX PROCESSING ENGINE

In one embodiment, an integrated circuit (IC) chip is provided. The IC chip comprises: a plurality of processing units to collectively execute a matrix multiplication operation with matrix data by performing matrix processing at least partially in parallel, each processing unit of the plurality of p...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: KORTHIKANTI, Vijay, WERNER, Tony L, LAU, Horace, KALAIAH, Aravind
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 KORTHIKANTI, Vijay
WERNER, Tony L
LAU, Horace
KALAIAH, Aravind
description In one embodiment, an integrated circuit (IC) chip is provided. The IC chip comprises: a plurality of processing units to collectively execute a matrix multiplication operation with matrix data by performing matrix processing at least partially in parallel, each processing unit of the plurality of processing units to process a portion of the matrix data to perform a corresponding partial matrix operation; a plurality of memories, each memory to store the portion of the matrix data to be processed by a corresponding processing unit of the plurality of processing units; a plurality of interconnects to couple the plurality of processing units, a processing unit of the plurality of processing units to send partial matrix data to a neighboring processing unit of the plurality of processing units or to receive partial matrix data from the neighboring processing unit over a corresponding interconnect; a first controller, wherein responsive to the first controller, the plurality of processing units are to collectively execute the matrix multiplication operation in accordance with at least one matrix multiplication command or instruction specifying a first input matrix and a second input matrix, the plurality of processing units to produce an output matrix by multiplying the first input matrix and the second input matrix; and a plurality of second controllers, each second controller associated with a processing unit of the plurality of processing units, the second controller to retrieve the portion of the matrix data to be processed by a corresponding processing unit of the plurality of processing units from a system memory and to store the portion of the matrix data to a corresponding memory of the plurality of memories.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4120071B1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4120071B1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4120071B13</originalsourceid><addsrcrecordid>eNrjZFANCPJ3D3L09XV08nFV8HUMCfKMUACKObsGB3v6uSu4-rl7-rnyMLCmJeYUp_JCaW4GBTfXEGcP3dSC_PjU4oLE5NS81JJ41wATQyMDA3NDJ0NjIpQAAG3xIvU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>PROGRAMMABLE MATRIX PROCESSING ENGINE</title><source>esp@cenet</source><creator>KORTHIKANTI, Vijay ; WERNER, Tony L ; LAU, Horace ; KALAIAH, Aravind</creator><creatorcontrib>KORTHIKANTI, Vijay ; WERNER, Tony L ; LAU, Horace ; KALAIAH, Aravind</creatorcontrib><description>In one embodiment, an integrated circuit (IC) chip is provided. The IC chip comprises: a plurality of processing units to collectively execute a matrix multiplication operation with matrix data by performing matrix processing at least partially in parallel, each processing unit of the plurality of processing units to process a portion of the matrix data to perform a corresponding partial matrix operation; a plurality of memories, each memory to store the portion of the matrix data to be processed by a corresponding processing unit of the plurality of processing units; a plurality of interconnects to couple the plurality of processing units, a processing unit of the plurality of processing units to send partial matrix data to a neighboring processing unit of the plurality of processing units or to receive partial matrix data from the neighboring processing unit over a corresponding interconnect; a first controller, wherein responsive to the first controller, the plurality of processing units are to collectively execute the matrix multiplication operation in accordance with at least one matrix multiplication command or instruction specifying a first input matrix and a second input matrix, the plurality of processing units to produce an output matrix by multiplying the first input matrix and the second input matrix; and a plurality of second controllers, each second controller associated with a processing unit of the plurality of processing units, the second controller to retrieve the portion of the matrix data to be processed by a corresponding processing unit of the plurality of processing units from a system memory and to store the portion of the matrix data to a corresponding memory of the plurality of memories.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2024</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=20241106&amp;DB=EPODOC&amp;CC=EP&amp;NR=4120071B1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20241106&amp;DB=EPODOC&amp;CC=EP&amp;NR=4120071B1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KORTHIKANTI, Vijay</creatorcontrib><creatorcontrib>WERNER, Tony L</creatorcontrib><creatorcontrib>LAU, Horace</creatorcontrib><creatorcontrib>KALAIAH, Aravind</creatorcontrib><title>PROGRAMMABLE MATRIX PROCESSING ENGINE</title><description>In one embodiment, an integrated circuit (IC) chip is provided. The IC chip comprises: a plurality of processing units to collectively execute a matrix multiplication operation with matrix data by performing matrix processing at least partially in parallel, each processing unit of the plurality of processing units to process a portion of the matrix data to perform a corresponding partial matrix operation; a plurality of memories, each memory to store the portion of the matrix data to be processed by a corresponding processing unit of the plurality of processing units; a plurality of interconnects to couple the plurality of processing units, a processing unit of the plurality of processing units to send partial matrix data to a neighboring processing unit of the plurality of processing units or to receive partial matrix data from the neighboring processing unit over a corresponding interconnect; a first controller, wherein responsive to the first controller, the plurality of processing units are to collectively execute the matrix multiplication operation in accordance with at least one matrix multiplication command or instruction specifying a first input matrix and a second input matrix, the plurality of processing units to produce an output matrix by multiplying the first input matrix and the second input matrix; and a plurality of second controllers, each second controller associated with a processing unit of the plurality of processing units, the second controller to retrieve the portion of the matrix data to be processed by a corresponding processing unit of the plurality of processing units from a system memory and to store the portion of the matrix data to a corresponding memory of the plurality of memories.</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFANCPJ3D3L09XV08nFV8HUMCfKMUACKObsGB3v6uSu4-rl7-rnyMLCmJeYUp_JCaW4GBTfXEGcP3dSC_PjU4oLE5NS81JJ41wATQyMDA3NDJ0NjIpQAAG3xIvU</recordid><startdate>20241106</startdate><enddate>20241106</enddate><creator>KORTHIKANTI, Vijay</creator><creator>WERNER, Tony L</creator><creator>LAU, Horace</creator><creator>KALAIAH, Aravind</creator><scope>EVB</scope></search><sort><creationdate>20241106</creationdate><title>PROGRAMMABLE MATRIX PROCESSING ENGINE</title><author>KORTHIKANTI, Vijay ; WERNER, Tony L ; LAU, Horace ; KALAIAH, Aravind</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4120071B13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>KORTHIKANTI, Vijay</creatorcontrib><creatorcontrib>WERNER, Tony L</creatorcontrib><creatorcontrib>LAU, Horace</creatorcontrib><creatorcontrib>KALAIAH, Aravind</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KORTHIKANTI, Vijay</au><au>WERNER, Tony L</au><au>LAU, Horace</au><au>KALAIAH, Aravind</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>PROGRAMMABLE MATRIX PROCESSING ENGINE</title><date>2024-11-06</date><risdate>2024</risdate><abstract>In one embodiment, an integrated circuit (IC) chip is provided. The IC chip comprises: a plurality of processing units to collectively execute a matrix multiplication operation with matrix data by performing matrix processing at least partially in parallel, each processing unit of the plurality of processing units to process a portion of the matrix data to perform a corresponding partial matrix operation; a plurality of memories, each memory to store the portion of the matrix data to be processed by a corresponding processing unit of the plurality of processing units; a plurality of interconnects to couple the plurality of processing units, a processing unit of the plurality of processing units to send partial matrix data to a neighboring processing unit of the plurality of processing units or to receive partial matrix data from the neighboring processing unit over a corresponding interconnect; a first controller, wherein responsive to the first controller, the plurality of processing units are to collectively execute the matrix multiplication operation in accordance with at least one matrix multiplication command or instruction specifying a first input matrix and a second input matrix, the plurality of processing units to produce an output matrix by multiplying the first input matrix and the second input matrix; and a plurality of second controllers, each second controller associated with a processing unit of the plurality of processing units, the second controller to retrieve the portion of the matrix data to be processed by a corresponding processing unit of the plurality of processing units from a system memory and to store the portion of the matrix data to a corresponding memory of the plurality of memories.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4120071B1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title PROGRAMMABLE MATRIX PROCESSING ENGINE
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T15%3A09%3A12IST&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=KORTHIKANTI,%20Vijay&rft.date=2024-11-06&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4120071B1%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