ARTIFICIAL INTELLIGENCE ACCELERATOR DEVICE

An artificial intelligence (AI) accelerator device may include a plurality of on-chip mini buffers that are associated with a processing element (PE) array. Each mini buffer is associated with a subset of rows or a subset of columns of the PE array. Partitioning an on-chip buffer of the AI accelerat...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	SUN, Xiaoyu, AKARVARDAR, Murat Kerem, PENG, Xiaochen
Format:	Patent
Sprache:	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	SUN, Xiaoyu AKARVARDAR, Murat Kerem PENG, Xiaochen
description	An artificial intelligence (AI) accelerator device may include a plurality of on-chip mini buffers that are associated with a processing element (PE) array. Each mini buffer is associated with a subset of rows or a subset of columns of the PE array. Partitioning an on-chip buffer of the AI accelerator device into the mini buffers described herein may reduce the size and complexity of the on-chip buffer. The reduced size of the on-chip buffer may reduce the wire routing complexity of the on-chip buffer, which may reduce latency and may reduce access energy for the AI accelerator device. This may increase the operating efficiency and/or may increase the performance of the AI accelerator device. Moreover, the mini buffers may increase the overall bandwidth that is available for the mini buffers to transfer data to and from the PE array.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024069971A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024069971A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024069971A13</originalsourceid><addsrcrecordid>eNrjZNByDArxdPN09nT0UfD0C3H18fF0d_VzdlVwdHZ29XENcgzxD1JwcQ3zdHblYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkYmBmaWluaGjobGxKkCAN_UJZU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ARTIFICIAL INTELLIGENCE ACCELERATOR DEVICE</title><source>esp@cenet</source><creator>SUN, Xiaoyu ; AKARVARDAR, Murat Kerem ; PENG, Xiaochen</creator><creatorcontrib>SUN, Xiaoyu ; AKARVARDAR, Murat Kerem ; PENG, Xiaochen</creatorcontrib><description>An artificial intelligence (AI) accelerator device may include a plurality of on-chip mini buffers that are associated with a processing element (PE) array. Each mini buffer is associated with a subset of rows or a subset of columns of the PE array. Partitioning an on-chip buffer of the AI accelerator device into the mini buffers described herein may reduce the size and complexity of the on-chip buffer. The reduced size of the on-chip buffer may reduce the wire routing complexity of the on-chip buffer, which may reduce latency and may reduce access energy for the AI accelerator device. This may increase the operating efficiency and/or may increase the performance of the AI accelerator device. Moreover, the mini buffers may increase the overall bandwidth that is available for the mini buffers to transfer data to and from the PE array.</description><language>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=20240229&DB=EPODOC&CC=US&NR=2024069971A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240229&DB=EPODOC&CC=US&NR=2024069971A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SUN, Xiaoyu</creatorcontrib><creatorcontrib>AKARVARDAR, Murat Kerem</creatorcontrib><creatorcontrib>PENG, Xiaochen</creatorcontrib><title>ARTIFICIAL INTELLIGENCE ACCELERATOR DEVICE</title><description>An artificial intelligence (AI) accelerator device may include a plurality of on-chip mini buffers that are associated with a processing element (PE) array. Each mini buffer is associated with a subset of rows or a subset of columns of the PE array. Partitioning an on-chip buffer of the AI accelerator device into the mini buffers described herein may reduce the size and complexity of the on-chip buffer. The reduced size of the on-chip buffer may reduce the wire routing complexity of the on-chip buffer, which may reduce latency and may reduce access energy for the AI accelerator device. This may increase the operating efficiency and/or may increase the performance of the AI accelerator device. Moreover, the mini buffers may increase the overall bandwidth that is available for the mini buffers to transfer data to and from the PE array.</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>eNrjZNByDArxdPN09nT0UfD0C3H18fF0d_VzdlVwdHZ29XENcgzxD1JwcQ3zdHblYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkYmBmaWluaGjobGxKkCAN_UJZU</recordid><startdate>20240229</startdate><enddate>20240229</enddate><creator>SUN, Xiaoyu</creator><creator>AKARVARDAR, Murat Kerem</creator><creator>PENG, Xiaochen</creator><scope>EVB</scope></search><sort><creationdate>20240229</creationdate><title>ARTIFICIAL INTELLIGENCE ACCELERATOR DEVICE</title><author>SUN, Xiaoyu ; AKARVARDAR, Murat Kerem ; PENG, Xiaochen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024069971A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>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>SUN, Xiaoyu</creatorcontrib><creatorcontrib>AKARVARDAR, Murat Kerem</creatorcontrib><creatorcontrib>PENG, Xiaochen</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SUN, Xiaoyu</au><au>AKARVARDAR, Murat Kerem</au><au>PENG, Xiaochen</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ARTIFICIAL INTELLIGENCE ACCELERATOR DEVICE</title><date>2024-02-29</date><risdate>2024</risdate><abstract>An artificial intelligence (AI) accelerator device may include a plurality of on-chip mini buffers that are associated with a processing element (PE) array. Each mini buffer is associated with a subset of rows or a subset of columns of the PE array. Partitioning an on-chip buffer of the AI accelerator device into the mini buffers described herein may reduce the size and complexity of the on-chip buffer. The reduced size of the on-chip buffer may reduce the wire routing complexity of the on-chip buffer, which may reduce latency and may reduce access energy for the AI accelerator device. This may increase the operating efficiency and/or may increase the performance of the AI accelerator device. Moreover, the mini buffers may increase the overall bandwidth that is available for the mini buffers to transfer data to and from the PE array.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2024069971A1
source	esp@cenet
subjects	CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
title	ARTIFICIAL INTELLIGENCE ACCELERATOR DEVICE
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A30%3A17IST&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=SUN,%20Xiaoyu&rft.date=2024-02-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024069971A1%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