Deep neural network model compiling optimization method based on SW processor
The invention relates to a deep neural network model compilation optimization method based on an SW processor, and the method comprises the steps: carrying out the corresponding packaging of an automatically generated AOT (Ahead-of-Time) code according to the code specification of the SW processor,...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; 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 | ZHENG XUEGUI LIAO JIANJIN YANG HAILONG LUAN ZHONGZHI QIAN DEPEI LI MINGZHEN |
| description | The invention relates to a deep neural network model compilation optimization method based on an SW processor, and the method comprises the steps: carrying out the corresponding packaging of an automatically generated AOT (Ahead-of-Time) code according to the code specification of the SW processor, and carrying out the correct initialization and calling in a main function, a local data storage management (LDM) method is used for transmitting data related to partial calculation to a local data cache in batches so as to improve the transmission rate, and a direct memory access (DMA) code insertion method is used for realizing efficient data transmission of a main memory and the LDM. The method disclosed by the invention is suitable for a hardware system structure of the SW processor, high-performance codes can be quickly generated, and the development efficiency of programmers is improved.
本发明涉及一种基于申威处理器的深度神经网络模型编译优化方法，其方法依照申威处理器的代码规范，对自动生成的AOT(Ahead-of-Time)代码进行相应的封装，并在主函数中进行正确的初始化和调用，并利用局部数据存储管理(LDM)方法将部分计算涉及 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115576561A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115576561A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115576561A3</originalsourceid><addsrcrecordid>eNrjZPB1SU0tUMhLLS1KzAFSJeX5RdkKufkpqTkKyfm5BZk5mXnpCvkFJZm5mVWJJZn5eQq5qSUZ-SkKSYnFqSkKQH5wuEJBUX5yanFxfhEPA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTgXaEe_sZ2hoampuZmpm6GhMjBoA-Ig2bg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Deep neural network model compiling optimization method based on SW processor</title><source>esp@cenet</source><creator>ZHENG XUEGUI ; LIAO JIANJIN ; YANG HAILONG ; LUAN ZHONGZHI ; QIAN DEPEI ; LI MINGZHEN</creator><creatorcontrib>ZHENG XUEGUI ; LIAO JIANJIN ; YANG HAILONG ; LUAN ZHONGZHI ; QIAN DEPEI ; LI MINGZHEN</creatorcontrib><description>The invention relates to a deep neural network model compilation optimization method based on an SW processor, and the method comprises the steps: carrying out the corresponding packaging of an automatically generated AOT (Ahead-of-Time) code according to the code specification of the SW processor, and carrying out the correct initialization and calling in a main function, a local data storage management (LDM) method is used for transmitting data related to partial calculation to a local data cache in batches so as to improve the transmission rate, and a direct memory access (DMA) code insertion method is used for realizing efficient data transmission of a main memory and the LDM. The method disclosed by the invention is suitable for a hardware system structure of the SW processor, high-performance codes can be quickly generated, and the development efficiency of programmers is improved.
本发明涉及一种基于申威处理器的深度神经网络模型编译优化方法，其方法依照申威处理器的代码规范，对自动生成的AOT(Ahead-of-Time)代码进行相应的封装，并在主函数中进行正确的初始化和调用，并利用局部数据存储管理(LDM)方法将部分计算涉及</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; 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&date=20230106&DB=EPODOC&CC=CN&NR=115576561A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230106&DB=EPODOC&CC=CN&NR=115576561A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHENG XUEGUI</creatorcontrib><creatorcontrib>LIAO JIANJIN</creatorcontrib><creatorcontrib>YANG HAILONG</creatorcontrib><creatorcontrib>LUAN ZHONGZHI</creatorcontrib><creatorcontrib>QIAN DEPEI</creatorcontrib><creatorcontrib>LI MINGZHEN</creatorcontrib><title>Deep neural network model compiling optimization method based on SW processor</title><description>The invention relates to a deep neural network model compilation optimization method based on an SW processor, and the method comprises the steps: carrying out the corresponding packaging of an automatically generated AOT (Ahead-of-Time) code according to the code specification of the SW processor, and carrying out the correct initialization and calling in a main function, a local data storage management (LDM) method is used for transmitting data related to partial calculation to a local data cache in batches so as to improve the transmission rate, and a direct memory access (DMA) code insertion method is used for realizing efficient data transmission of a main memory and the LDM. The method disclosed by the invention is suitable for a hardware system structure of the SW processor, high-performance codes can be quickly generated, and the development efficiency of programmers is improved.
本发明涉及一种基于申威处理器的深度神经网络模型编译优化方法，其方法依照申威处理器的代码规范，对自动生成的AOT(Ahead-of-Time)代码进行相应的封装，并在主函数中进行正确的初始化和调用，并利用局部数据存储管理(LDM)方法将部分计算涉及</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPB1SU0tUMhLLS1KzAFSJeX5RdkKufkpqTkKyfm5BZk5mXnpCvkFJZm5mVWJJZn5eQq5qSUZ-SkKSYnFqSkKQH5wuEJBUX5yanFxfhEPA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTgXaEe_sZ2hoampuZmpm6GhMjBoA-Ig2bg</recordid><startdate>20230106</startdate><enddate>20230106</enddate><creator>ZHENG XUEGUI</creator><creator>LIAO JIANJIN</creator><creator>YANG HAILONG</creator><creator>LUAN ZHONGZHI</creator><creator>QIAN DEPEI</creator><creator>LI MINGZHEN</creator><scope>EVB</scope></search><sort><creationdate>20230106</creationdate><title>Deep neural network model compiling optimization method based on SW processor</title><author>ZHENG XUEGUI ; LIAO JIANJIN ; YANG HAILONG ; LUAN ZHONGZHI ; QIAN DEPEI ; LI MINGZHEN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115576561A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHENG XUEGUI</creatorcontrib><creatorcontrib>LIAO JIANJIN</creatorcontrib><creatorcontrib>YANG HAILONG</creatorcontrib><creatorcontrib>LUAN ZHONGZHI</creatorcontrib><creatorcontrib>QIAN DEPEI</creatorcontrib><creatorcontrib>LI MINGZHEN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHENG XUEGUI</au><au>LIAO JIANJIN</au><au>YANG HAILONG</au><au>LUAN ZHONGZHI</au><au>QIAN DEPEI</au><au>LI MINGZHEN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Deep neural network model compiling optimization method based on SW processor</title><date>2023-01-06</date><risdate>2023</risdate><abstract>The invention relates to a deep neural network model compilation optimization method based on an SW processor, and the method comprises the steps: carrying out the corresponding packaging of an automatically generated AOT (Ahead-of-Time) code according to the code specification of the SW processor, and carrying out the correct initialization and calling in a main function, a local data storage management (LDM) method is used for transmitting data related to partial calculation to a local data cache in batches so as to improve the transmission rate, and a direct memory access (DMA) code insertion method is used for realizing efficient data transmission of a main memory and the LDM. The method disclosed by the invention is suitable for a hardware system structure of the SW processor, high-performance codes can be quickly generated, and the development efficiency of programmers is improved.
本发明涉及一种基于申威处理器的深度神经网络模型编译优化方法，其方法依照申威处理器的代码规范，对自动生成的AOT(Ahead-of-Time)代码进行相应的封装，并在主函数中进行正确的初始化和调用，并利用局部数据存储管理(LDM)方法将部分计算涉及</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115576561A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Deep neural network model compiling optimization method based on SW processor |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T02%3A25%3A08IST&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=ZHENG%20XUEGUI&rft.date=2023-01-06&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115576561A%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 |