BYPASSING MEMORY ACCESS FOR A LOAD INSTRUCTION USING INSTRUCTION ADDRESS MAPPING

Systems, methods, and computer-readable media are disclosed for executing a predicted load that bypasses memory access for a load instruction. A first physical register that is predicted as storing avalue to be loaded by the load instruction is identified and the value stored in the first physical r...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: PRASKY BRIAN R, SCHROTER DAVID A, SHUM CHUNG-LUNG, STAPPENBECK COREY
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 PRASKY BRIAN R
SCHROTER DAVID A
SHUM CHUNG-LUNG
STAPPENBECK COREY
description Systems, methods, and computer-readable media are disclosed for executing a predicted load that bypasses memory access for a load instruction. A first physical register that is predicted as storing avalue to be loaded by the load instruction is identified and the value stored in the first physical register is copied to a second physical register for use by a consumer operation. A predicted storeinstruction corresponding to the load instruction is identified and a mapping table is accessed to obtain data associated with the predicted store instruction. The data is evaluated to determine whether the predicted load meets dependency constraints. As a result of execution of the predicted load, the consumer operation can utilize the data stored in the first physical register directly and bypass the cache memory access that would otherwise be required to execute the load instruction. 公开了用于执行绕过对加载指令的存储器访问的预测加载的系统、方法和计算机可读介质。被预测为存储将由加载指令加载的值的第一物理寄存器被识别,并且存储在第一物理寄存器中的值被复制到第二物理寄存器以由消费者操作使用。识别对应于加载指令的预测存储指令,并访问映射表以获得与预测的
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN110312994A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN110312994A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN110312994A3</originalsourceid><addsrcrecordid>eNrjZAhwigxwDA729HNX8HX19Q-KVHB0dnYNDlZw8w9ScFTw8Xd0UfD0Cw4JCnUO8fT3UwgFK0UWcXRxCQJp8HUMCADK8TCwpiXmFKfyQmluBkU31xBnD93Ugvz41OKCxOTUvNSSeGc_Q0MDY0MjS0sTR2Ni1AAAlI0vUg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>BYPASSING MEMORY ACCESS FOR A LOAD INSTRUCTION USING INSTRUCTION ADDRESS MAPPING</title><source>esp@cenet</source><creator>PRASKY BRIAN R ; SCHROTER DAVID A ; SHUM CHUNG-LUNG ; STAPPENBECK COREY</creator><creatorcontrib>PRASKY BRIAN R ; SCHROTER DAVID A ; SHUM CHUNG-LUNG ; STAPPENBECK COREY</creatorcontrib><description>Systems, methods, and computer-readable media are disclosed for executing a predicted load that bypasses memory access for a load instruction. A first physical register that is predicted as storing avalue to be loaded by the load instruction is identified and the value stored in the first physical register is copied to a second physical register for use by a consumer operation. A predicted storeinstruction corresponding to the load instruction is identified and a mapping table is accessed to obtain data associated with the predicted store instruction. The data is evaluated to determine whether the predicted load meets dependency constraints. As a result of execution of the predicted load, the consumer operation can utilize the data stored in the first physical register directly and bypass the cache memory access that would otherwise be required to execute the load instruction. 公开了用于执行绕过对加载指令的存储器访问的预测加载的系统、方法和计算机可读介质。被预测为存储将由加载指令加载的值的第一物理寄存器被识别,并且存储在第一物理寄存器中的值被复制到第二物理寄存器以由消费者操作使用。识别对应于加载指令的预测存储指令,并访问映射表以获得与预测的</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2019</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=20191008&amp;DB=EPODOC&amp;CC=CN&amp;NR=110312994A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20191008&amp;DB=EPODOC&amp;CC=CN&amp;NR=110312994A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>PRASKY BRIAN R</creatorcontrib><creatorcontrib>SCHROTER DAVID A</creatorcontrib><creatorcontrib>SHUM CHUNG-LUNG</creatorcontrib><creatorcontrib>STAPPENBECK COREY</creatorcontrib><title>BYPASSING MEMORY ACCESS FOR A LOAD INSTRUCTION USING INSTRUCTION ADDRESS MAPPING</title><description>Systems, methods, and computer-readable media are disclosed for executing a predicted load that bypasses memory access for a load instruction. A first physical register that is predicted as storing avalue to be loaded by the load instruction is identified and the value stored in the first physical register is copied to a second physical register for use by a consumer operation. A predicted storeinstruction corresponding to the load instruction is identified and a mapping table is accessed to obtain data associated with the predicted store instruction. The data is evaluated to determine whether the predicted load meets dependency constraints. As a result of execution of the predicted load, the consumer operation can utilize the data stored in the first physical register directly and bypass the cache memory access that would otherwise be required to execute the load instruction. 公开了用于执行绕过对加载指令的存储器访问的预测加载的系统、方法和计算机可读介质。被预测为存储将由加载指令加载的值的第一物理寄存器被识别,并且存储在第一物理寄存器中的值被复制到第二物理寄存器以由消费者操作使用。识别对应于加载指令的预测存储指令,并访问映射表以获得与预测的</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>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZAhwigxwDA729HNX8HX19Q-KVHB0dnYNDlZw8w9ScFTw8Xd0UfD0Cw4JCnUO8fT3UwgFK0UWcXRxCQJp8HUMCADK8TCwpiXmFKfyQmluBkU31xBnD93Ugvz41OKCxOTUvNSSeGc_Q0MDY0MjS0sTR2Ni1AAAlI0vUg</recordid><startdate>20191008</startdate><enddate>20191008</enddate><creator>PRASKY BRIAN R</creator><creator>SCHROTER DAVID A</creator><creator>SHUM CHUNG-LUNG</creator><creator>STAPPENBECK COREY</creator><scope>EVB</scope></search><sort><creationdate>20191008</creationdate><title>BYPASSING MEMORY ACCESS FOR A LOAD INSTRUCTION USING INSTRUCTION ADDRESS MAPPING</title><author>PRASKY BRIAN R ; SCHROTER DAVID A ; SHUM CHUNG-LUNG ; STAPPENBECK COREY</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN110312994A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>PRASKY BRIAN R</creatorcontrib><creatorcontrib>SCHROTER DAVID A</creatorcontrib><creatorcontrib>SHUM CHUNG-LUNG</creatorcontrib><creatorcontrib>STAPPENBECK COREY</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>PRASKY BRIAN R</au><au>SCHROTER DAVID A</au><au>SHUM CHUNG-LUNG</au><au>STAPPENBECK COREY</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>BYPASSING MEMORY ACCESS FOR A LOAD INSTRUCTION USING INSTRUCTION ADDRESS MAPPING</title><date>2019-10-08</date><risdate>2019</risdate><abstract>Systems, methods, and computer-readable media are disclosed for executing a predicted load that bypasses memory access for a load instruction. A first physical register that is predicted as storing avalue to be loaded by the load instruction is identified and the value stored in the first physical register is copied to a second physical register for use by a consumer operation. A predicted storeinstruction corresponding to the load instruction is identified and a mapping table is accessed to obtain data associated with the predicted store instruction. The data is evaluated to determine whether the predicted load meets dependency constraints. As a result of execution of the predicted load, the consumer operation can utilize the data stored in the first physical register directly and bypass the cache memory access that would otherwise be required to execute the load instruction. 公开了用于执行绕过对加载指令的存储器访问的预测加载的系统、方法和计算机可读介质。被预测为存储将由加载指令加载的值的第一物理寄存器被识别,并且存储在第一物理寄存器中的值被复制到第二物理寄存器以由消费者操作使用。识别对应于加载指令的预测存储指令,并访问映射表以获得与预测的</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN110312994A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title BYPASSING MEMORY ACCESS FOR A LOAD INSTRUCTION USING INSTRUCTION ADDRESS MAPPING
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T06%3A58%3A11IST&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=PRASKY%20BRIAN%20R&rft.date=2019-10-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN110312994A%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