PROGRAM, PARALLEL OPERATION METHOD, AND INFORMATION PROCESSOR
PROBLEM TO BE SOLVED: To efficiently use a storage area of a memory in a matrix operation.SOLUTION: An information processor 10 allocates operations of a partial matrix 24 in a matrix 23 including a zero element and a non-zero element to a thread 21, and allocates operations of a partial matrix 25 i...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Patent |
| Sprache: | eng ; jpn |
| 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 | USUI TETSUZO |
| description | PROBLEM TO BE SOLVED: To efficiently use a storage area of a memory in a matrix operation.SOLUTION: An information processor 10 allocates operations of a partial matrix 24 in a matrix 23 including a zero element and a non-zero element to a thread 21, and allocates operations of a partial matrix 25 in the matrix 23 to a thread 22. The information processor 10 compares a distribution of the non-zero element between rows or columns in the partial matrix 24 with a distribution of the non-zero element between rows or columns in the partial matrix 25. The information processor 10 changes allocation of storage areas storing a vector to be used in operations by the threads 21, 22 respectively according to a result of comparison.
【課題】行列演算においてメモリの記憶領域を効率的に利用する。【解決手段】情報処理装置１０は、零要素および非零要素を含む行列２３の中の部分行列２４の演算をスレッド２１に割り当て、行列２３の中の部分行列２５の演算をスレッド２２に割り当てる。情報処理装置１０は、部分行列２４における行間または列間の非零要素の分布と、部分行列２５における行間または列間の非零要素の分布とを比較する。情報処理装置１０は、比較の結果に応じて、スレッド２１，２２が演算においてそれぞれ利用するベクトルを記憶する記憶領域の割り当てを変化させる。【選択図】図１ |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_JP2014199545A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>JP2014199545A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_JP2014199545A3</originalsourceid><addsrcrecordid>eNrjZLANCPJ3D3L01VEIcAxy9PFx9VHwD3ANcgzx9PdT8HUN8fB30VFw9HNR8PRz8w_yhYgD9Ti7Bgf7B_EwsKYl5hSn8kJpbgYlN9cQZw_d1IL8-NTigsTk1LzUknivACMDQxNDS0tTE1NHY6IUAQCJhSpw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>PROGRAM, PARALLEL OPERATION METHOD, AND INFORMATION PROCESSOR</title><source>esp@cenet</source><creator>USUI TETSUZO</creator><creatorcontrib>USUI TETSUZO</creatorcontrib><description>PROBLEM TO BE SOLVED: To efficiently use a storage area of a memory in a matrix operation.SOLUTION: An information processor 10 allocates operations of a partial matrix 24 in a matrix 23 including a zero element and a non-zero element to a thread 21, and allocates operations of a partial matrix 25 in the matrix 23 to a thread 22. The information processor 10 compares a distribution of the non-zero element between rows or columns in the partial matrix 24 with a distribution of the non-zero element between rows or columns in the partial matrix 25. The information processor 10 changes allocation of storage areas storing a vector to be used in operations by the threads 21, 22 respectively according to a result of comparison.
【課題】行列演算においてメモリの記憶領域を効率的に利用する。【解決手段】情報処理装置１０は、零要素および非零要素を含む行列２３の中の部分行列２４の演算をスレッド２１に割り当て、行列２３の中の部分行列２５の演算をスレッド２２に割り当てる。情報処理装置１０は、部分行列２４における行間または列間の非零要素の分布と、部分行列２５における行間または列間の非零要素の分布とを比較する。情報処理装置１０は、比較の結果に応じて、スレッド２１，２２が演算においてそれぞれ利用するベクトルを記憶する記憶領域の割り当てを変化させる。【選択図】図１</description><language>eng ; jpn</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2014</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=20141023&DB=EPODOC&CC=JP&NR=2014199545A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20141023&DB=EPODOC&CC=JP&NR=2014199545A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>USUI TETSUZO</creatorcontrib><title>PROGRAM, PARALLEL OPERATION METHOD, AND INFORMATION PROCESSOR</title><description>PROBLEM TO BE SOLVED: To efficiently use a storage area of a memory in a matrix operation.SOLUTION: An information processor 10 allocates operations of a partial matrix 24 in a matrix 23 including a zero element and a non-zero element to a thread 21, and allocates operations of a partial matrix 25 in the matrix 23 to a thread 22. The information processor 10 compares a distribution of the non-zero element between rows or columns in the partial matrix 24 with a distribution of the non-zero element between rows or columns in the partial matrix 25. The information processor 10 changes allocation of storage areas storing a vector to be used in operations by the threads 21, 22 respectively according to a result of comparison.
【課題】行列演算においてメモリの記憶領域を効率的に利用する。【解決手段】情報処理装置１０は、零要素および非零要素を含む行列２３の中の部分行列２４の演算をスレッド２１に割り当て、行列２３の中の部分行列２５の演算をスレッド２２に割り当てる。情報処理装置１０は、部分行列２４における行間または列間の非零要素の分布と、部分行列２５における行間または列間の非零要素の分布とを比較する。情報処理装置１０は、比較の結果に応じて、スレッド２１，２２が演算においてそれぞれ利用するベクトルを記憶する記憶領域の割り当てを変化させる。【選択図】図１</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>2014</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLANCPJ3D3L01VEIcAxy9PFx9VHwD3ANcgzx9PdT8HUN8fB30VFw9HNR8PRz8w_yhYgD9Ti7Bgf7B_EwsKYl5hSn8kJpbgYlN9cQZw_d1IL8-NTigsTk1LzUknivACMDQxNDS0tTE1NHY6IUAQCJhSpw</recordid><startdate>20141023</startdate><enddate>20141023</enddate><creator>USUI TETSUZO</creator><scope>EVB</scope></search><sort><creationdate>20141023</creationdate><title>PROGRAM, PARALLEL OPERATION METHOD, AND INFORMATION PROCESSOR</title><author>USUI TETSUZO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_JP2014199545A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; jpn</language><creationdate>2014</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>USUI TETSUZO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>USUI TETSUZO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>PROGRAM, PARALLEL OPERATION METHOD, AND INFORMATION PROCESSOR</title><date>2014-10-23</date><risdate>2014</risdate><abstract>PROBLEM TO BE SOLVED: To efficiently use a storage area of a memory in a matrix operation.SOLUTION: An information processor 10 allocates operations of a partial matrix 24 in a matrix 23 including a zero element and a non-zero element to a thread 21, and allocates operations of a partial matrix 25 in the matrix 23 to a thread 22. The information processor 10 compares a distribution of the non-zero element between rows or columns in the partial matrix 24 with a distribution of the non-zero element between rows or columns in the partial matrix 25. The information processor 10 changes allocation of storage areas storing a vector to be used in operations by the threads 21, 22 respectively according to a result of comparison.
【課題】行列演算においてメモリの記憶領域を効率的に利用する。【解決手段】情報処理装置１０は、零要素および非零要素を含む行列２３の中の部分行列２４の演算をスレッド２１に割り当て、行列２３の中の部分行列２５の演算をスレッド２２に割り当てる。情報処理装置１０は、部分行列２４における行間または列間の非零要素の分布と、部分行列２５における行間または列間の非零要素の分布とを比較する。情報処理装置１０は、比較の結果に応じて、スレッド２１，２２が演算においてそれぞれ利用するベクトルを記憶する記憶領域の割り当てを変化させる。【選択図】図１</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; jpn |
| recordid | cdi_epo_espacenet_JP2014199545A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | PROGRAM, PARALLEL OPERATION METHOD, AND INFORMATION PROCESSOR |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T11%3A23%3A54IST&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=USUI%20TETSUZO&rft.date=2014-10-23&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EJP2014199545A%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 |