Multi-variate strided read operations for accessing matrix operands

In one embodiment, a matrix processor comprises a memory to store a matrix operand and a strided read sequence, wherein: the matrix operand is stored out of order in the memory; and the strided read sequence comprises a sequence of read operations to read the matrix operand in a correct order from t...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	DELCHIARO, JEFF, SAJJANAR, UJWAL BASAVARAJ, WERNER, TONY L, RHOADES, ROBERT T, YE, ANNE Q, GAREGRAT, NITIN N, ROTZIN, MICHAEL
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
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	DELCHIARO, JEFF SAJJANAR, UJWAL BASAVARAJ WERNER, TONY L RHOADES, ROBERT T YE, ANNE Q GAREGRAT, NITIN N ROTZIN, MICHAEL
description	In one embodiment, a matrix processor comprises a memory to store a matrix operand and a strided read sequence, wherein: the matrix operand is stored out of order in the memory; and the strided read sequence comprises a sequence of read operations to read the matrix operand in a correct order from the memory. The matrix processor further comprises circuitry to: receive a first instruction to be executed by the matrix processor, wherein the first instruction is to instruct the matrix processor to perform a first operation on the matrix operand; read the matrix operand from the memory based on the strided read sequence; and execute the first instruction by performing the first operation on the matrix operand.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_TWI842911BB</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>TWI842911BB</sourcerecordid><originalsourceid>FETCH-epo_espacenet_TWI842911BB3</originalsourceid><addsrcrecordid>eNrjZHD2Lc0pydQtSyzKTCxJVSguKcpMSU1RKEpNTFHIL0gtSizJzM8rVkjLL1JITE5OLS7OzEtXyE0EKquAyOelFPMwsKYl5hSn8kJpbgYFN9cQZw_d1IL8-NTigsTk1LzUkviQcE8LEyNLQ0MnJ2MilAAAW44zAQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Multi-variate strided read operations for accessing matrix operands</title><source>esp@cenet</source><creator>DELCHIARO, JEFF ; SAJJANAR, UJWAL BASAVARAJ ; WERNER, TONY L ; RHOADES, ROBERT T ; YE, ANNE Q ; GAREGRAT, NITIN N ; ROTZIN, MICHAEL</creator><creatorcontrib>DELCHIARO, JEFF ; SAJJANAR, UJWAL BASAVARAJ ; WERNER, TONY L ; RHOADES, ROBERT T ; YE, ANNE Q ; GAREGRAT, NITIN N ; ROTZIN, MICHAEL</creatorcontrib><description>In one embodiment, a matrix processor comprises a memory to store a matrix operand and a strided read sequence, wherein: the matrix operand is stored out of order in the memory; and the strided read sequence comprises a sequence of read operations to read the matrix operand in a correct order from the memory. The matrix processor further comprises circuitry to: receive a first instruction to be executed by the matrix processor, wherein the first instruction is to instruct the matrix processor to perform a first operation on the matrix operand; read the matrix operand from the memory based on the strided read sequence; and execute the first instruction by performing the first operation on the matrix operand.</description><language>chi ; eng</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&date=20240521&DB=EPODOC&CC=TW&NR=I842911B$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240521&DB=EPODOC&CC=TW&NR=I842911B$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DELCHIARO, JEFF</creatorcontrib><creatorcontrib>SAJJANAR, UJWAL BASAVARAJ</creatorcontrib><creatorcontrib>WERNER, TONY L</creatorcontrib><creatorcontrib>RHOADES, ROBERT T</creatorcontrib><creatorcontrib>YE, ANNE Q</creatorcontrib><creatorcontrib>GAREGRAT, NITIN N</creatorcontrib><creatorcontrib>ROTZIN, MICHAEL</creatorcontrib><title>Multi-variate strided read operations for accessing matrix operands</title><description>In one embodiment, a matrix processor comprises a memory to store a matrix operand and a strided read sequence, wherein: the matrix operand is stored out of order in the memory; and the strided read sequence comprises a sequence of read operations to read the matrix operand in a correct order from the memory. The matrix processor further comprises circuitry to: receive a first instruction to be executed by the matrix processor, wherein the first instruction is to instruct the matrix processor to perform a first operation on the matrix operand; read the matrix operand from the memory based on the strided read sequence; and execute the first instruction by performing the first operation on the matrix operand.</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>eNrjZHD2Lc0pydQtSyzKTCxJVSguKcpMSU1RKEpNTFHIL0gtSizJzM8rVkjLL1JITE5OLS7OzEtXyE0EKquAyOelFPMwsKYl5hSn8kJpbgYFN9cQZw_d1IL8-NTigsTk1LzUkviQcE8LEyNLQ0MnJ2MilAAAW44zAQ</recordid><startdate>20240521</startdate><enddate>20240521</enddate><creator>DELCHIARO, JEFF</creator><creator>SAJJANAR, UJWAL BASAVARAJ</creator><creator>WERNER, TONY L</creator><creator>RHOADES, ROBERT T</creator><creator>YE, ANNE Q</creator><creator>GAREGRAT, NITIN N</creator><creator>ROTZIN, MICHAEL</creator><scope>EVB</scope></search><sort><creationdate>20240521</creationdate><title>Multi-variate strided read operations for accessing matrix operands</title><author>DELCHIARO, JEFF ; SAJJANAR, UJWAL BASAVARAJ ; WERNER, TONY L ; RHOADES, ROBERT T ; YE, ANNE Q ; GAREGRAT, NITIN N ; ROTZIN, MICHAEL</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_TWI842911BB3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</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>DELCHIARO, JEFF</creatorcontrib><creatorcontrib>SAJJANAR, UJWAL BASAVARAJ</creatorcontrib><creatorcontrib>WERNER, TONY L</creatorcontrib><creatorcontrib>RHOADES, ROBERT T</creatorcontrib><creatorcontrib>YE, ANNE Q</creatorcontrib><creatorcontrib>GAREGRAT, NITIN N</creatorcontrib><creatorcontrib>ROTZIN, MICHAEL</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DELCHIARO, JEFF</au><au>SAJJANAR, UJWAL BASAVARAJ</au><au>WERNER, TONY L</au><au>RHOADES, ROBERT T</au><au>YE, ANNE Q</au><au>GAREGRAT, NITIN N</au><au>ROTZIN, MICHAEL</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Multi-variate strided read operations for accessing matrix operands</title><date>2024-05-21</date><risdate>2024</risdate><abstract>In one embodiment, a matrix processor comprises a memory to store a matrix operand and a strided read sequence, wherein: the matrix operand is stored out of order in the memory; and the strided read sequence comprises a sequence of read operations to read the matrix operand in a correct order from the memory. The matrix processor further comprises circuitry to: receive a first instruction to be executed by the matrix processor, wherein the first instruction is to instruct the matrix processor to perform a first operation on the matrix operand; read the matrix operand from the memory based on the strided read sequence; and execute the first instruction by performing the first operation on the matrix operand.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	chi ; eng
recordid	cdi_epo_espacenet_TWI842911BB
source	esp@cenet
subjects	CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
title	Multi-variate strided read operations for accessing matrix operands
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T05%3A58%3A33IST&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=DELCHIARO,%20JEFF&rft.date=2024-05-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ETWI842911BB%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