Task execution in a SIMD processing unit with parallel groups of processing lanes

A SIMD processing unit processes a plurality of tasks which each include up to a predetermined maximum number of work items. The work items of a task are arranged for executing a common sequence of instructions on respective data items. The data items are arranged into blocks, with some of the block...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Foo, Yoong Chert, Howson, John, Redshaw, Jonathan
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 Foo, Yoong Chert
Howson, John
Redshaw, Jonathan
description A SIMD processing unit processes a plurality of tasks which each include up to a predetermined maximum number of work items. The work items of a task are arranged for executing a common sequence of instructions on respective data items. The data items are arranged into blocks, with some of the blocks including at least one invalid data item. Work items which relate to invalid data items are invalid work items. The SIMD processing unit comprises a group of processing lanes configured to execute instructions of work items of a particular task over a plurality of processing cycles. A control module assembles work items into the tasks based on the validity of the work items, so that invalid work items of the particular task are temporally aligned across the processing lanes. In this way the number of wasted processing slots due to invalid work items may be reduced.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11734788B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11734788B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11734788B23</originalsourceid><addsrcrecordid>eNrjZAgMSSzOVkitSE0uLcnMz1PIzFNIVAj29HVRKCjKT04tLs7MS1cozcssUSjPLMlQKEgsSszJSc1RSC_KLy0oVshPQ1aXk5iXWszDwJqWmFOcyguluRkU3VxDnD10Uwvy41OLCxKTU_NSS-JDgw0NzY1NzC0snIyMiVEDAJuhN5E</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Task execution in a SIMD processing unit with parallel groups of processing lanes</title><source>esp@cenet</source><creator>Foo, Yoong Chert ; Howson, John ; Redshaw, Jonathan</creator><creatorcontrib>Foo, Yoong Chert ; Howson, John ; Redshaw, Jonathan</creatorcontrib><description>A SIMD processing unit processes a plurality of tasks which each include up to a predetermined maximum number of work items. The work items of a task are arranged for executing a common sequence of instructions on respective data items. The data items are arranged into blocks, with some of the blocks including at least one invalid data item. Work items which relate to invalid data items are invalid work items. The SIMD processing unit comprises a group of processing lanes configured to execute instructions of work items of a particular task over a plurality of processing cycles. A control module assembles work items into the tasks based on the validity of the work items, so that invalid work items of the particular task are temporally aligned across the processing lanes. In this way the number of wasted processing slots due to invalid work items may be reduced.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; 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&amp;date=20230822&amp;DB=EPODOC&amp;CC=US&amp;NR=11734788B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230822&amp;DB=EPODOC&amp;CC=US&amp;NR=11734788B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Foo, Yoong Chert</creatorcontrib><creatorcontrib>Howson, John</creatorcontrib><creatorcontrib>Redshaw, Jonathan</creatorcontrib><title>Task execution in a SIMD processing unit with parallel groups of processing lanes</title><description>A SIMD processing unit processes a plurality of tasks which each include up to a predetermined maximum number of work items. The work items of a task are arranged for executing a common sequence of instructions on respective data items. The data items are arranged into blocks, with some of the blocks including at least one invalid data item. Work items which relate to invalid data items are invalid work items. The SIMD processing unit comprises a group of processing lanes configured to execute instructions of work items of a particular task over a plurality of processing cycles. A control module assembles work items into the tasks based on the validity of the work items, so that invalid work items of the particular task are temporally aligned across the processing lanes. In this way the number of wasted processing slots due to invalid work items may be reduced.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZAgMSSzOVkitSE0uLcnMz1PIzFNIVAj29HVRKCjKT04tLs7MS1cozcssUSjPLMlQKEgsSszJSc1RSC_KLy0oVshPQ1aXk5iXWszDwJqWmFOcyguluRkU3VxDnD10Uwvy41OLCxKTU_NSS-JDgw0NzY1NzC0snIyMiVEDAJuhN5E</recordid><startdate>20230822</startdate><enddate>20230822</enddate><creator>Foo, Yoong Chert</creator><creator>Howson, John</creator><creator>Redshaw, Jonathan</creator><scope>EVB</scope></search><sort><creationdate>20230822</creationdate><title>Task execution in a SIMD processing unit with parallel groups of processing lanes</title><author>Foo, Yoong Chert ; Howson, John ; Redshaw, Jonathan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11734788B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Foo, Yoong Chert</creatorcontrib><creatorcontrib>Howson, John</creatorcontrib><creatorcontrib>Redshaw, Jonathan</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Foo, Yoong Chert</au><au>Howson, John</au><au>Redshaw, Jonathan</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Task execution in a SIMD processing unit with parallel groups of processing lanes</title><date>2023-08-22</date><risdate>2023</risdate><abstract>A SIMD processing unit processes a plurality of tasks which each include up to a predetermined maximum number of work items. The work items of a task are arranged for executing a common sequence of instructions on respective data items. The data items are arranged into blocks, with some of the blocks including at least one invalid data item. Work items which relate to invalid data items are invalid work items. The SIMD processing unit comprises a group of processing lanes configured to execute instructions of work items of a particular task over a plurality of processing cycles. A control module assembles work items into the tasks based on the validity of the work items, so that invalid work items of the particular task are temporally aligned across the processing lanes. In this way the number of wasted processing slots due to invalid work items may be reduced.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US11734788B2
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Task execution in a SIMD processing unit with parallel groups of processing lanes
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T02%3A21%3A50IST&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=Foo,%20Yoong%20Chert&rft.date=2023-08-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11734788B2%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