SEQUENTIAL PREFETCH METHOD FOR 1, 2 OR 3 WORD INSTRUCTIONS

A sequential prefetch method is provided for a pipelined data processor (10) having a sequential instruction prefetch unit (IPU) (34). An instruction queue (50) in the IPU (34) is coupled to a pipelined instruction unit (32) and an instruction cache (14) of the data processor (10). A prefetch contro...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: REININGER, RUSSELL, LEDBETTER, WILLIA B., JR
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 REININGER, RUSSELL
LEDBETTER, WILLIA B., JR
description A sequential prefetch method is provided for a pipelined data processor (10) having a sequential instruction prefetch unit (IPU) (34). An instruction queue (50) in the IPU (34) is coupled to a pipelined instruction unit (32) and an instruction cache (14) of the data processor (10). A prefetch controller (56) in the IPU (34) keeps the instruction stream prefetched so that the instruction queue (50) may load any combination of one, two, or three word instructions into the pipelined instruction unit (32) every clock cycle. The pipelined instruction unit (32) receives instruction words from the instruction queue (50), and decodes the instruction for execution operations, and for the instruction length/pipeline movement. A queue filling method is provided for maintaining the requisite number of instruction words in the instruction queue (50) to avoid pipeline stalls. The queue filling method is based upon the movement of the instruction pipeline (32) attributable to the usage by an instruction sequencer (32) of the instruction words received from the instruction queue. (50)
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP0436341A3</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP0436341A3</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP0436341A33</originalsourceid><addsrcrecordid>eNrjZLAKdg0MdfUL8XT0UQgIcnVzDXH2UPB1DfHwd1Fw8w9SMNRRMFIA0sYK4f5BLgqefsEhQaHOIZ7-fsE8DKxpiTnFqbxQmptBAaxdN7UgPz61uCAxOTUvtSTeNcDAxNjM2MTQ0diYCCUAMDMoHw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SEQUENTIAL PREFETCH METHOD FOR 1, 2 OR 3 WORD INSTRUCTIONS</title><source>esp@cenet</source><creator>REININGER, RUSSELL ; LEDBETTER, WILLIA B., JR</creator><creatorcontrib>REININGER, RUSSELL ; LEDBETTER, WILLIA B., JR</creatorcontrib><description>A sequential prefetch method is provided for a pipelined data processor (10) having a sequential instruction prefetch unit (IPU) (34). An instruction queue (50) in the IPU (34) is coupled to a pipelined instruction unit (32) and an instruction cache (14) of the data processor (10). A prefetch controller (56) in the IPU (34) keeps the instruction stream prefetched so that the instruction queue (50) may load any combination of one, two, or three word instructions into the pipelined instruction unit (32) every clock cycle. The pipelined instruction unit (32) receives instruction words from the instruction queue (50), and decodes the instruction for execution operations, and for the instruction length/pipeline movement. A queue filling method is provided for maintaining the requisite number of instruction words in the instruction queue (50) to avoid pipeline stalls. The queue filling method is based upon the movement of the instruction pipeline (32) attributable to the usage by an instruction sequencer (32) of the instruction words received from the instruction queue. (50)</description><edition>5</edition><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>1993</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=19930317&amp;DB=EPODOC&amp;CC=EP&amp;NR=0436341A3$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=19930317&amp;DB=EPODOC&amp;CC=EP&amp;NR=0436341A3$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>REININGER, RUSSELL</creatorcontrib><creatorcontrib>LEDBETTER, WILLIA B., JR</creatorcontrib><title>SEQUENTIAL PREFETCH METHOD FOR 1, 2 OR 3 WORD INSTRUCTIONS</title><description>A sequential prefetch method is provided for a pipelined data processor (10) having a sequential instruction prefetch unit (IPU) (34). An instruction queue (50) in the IPU (34) is coupled to a pipelined instruction unit (32) and an instruction cache (14) of the data processor (10). A prefetch controller (56) in the IPU (34) keeps the instruction stream prefetched so that the instruction queue (50) may load any combination of one, two, or three word instructions into the pipelined instruction unit (32) every clock cycle. The pipelined instruction unit (32) receives instruction words from the instruction queue (50), and decodes the instruction for execution operations, and for the instruction length/pipeline movement. A queue filling method is provided for maintaining the requisite number of instruction words in the instruction queue (50) to avoid pipeline stalls. The queue filling method is based upon the movement of the instruction pipeline (32) attributable to the usage by an instruction sequencer (32) of the instruction words received from the instruction queue. (50)</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>1993</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAKdg0MdfUL8XT0UQgIcnVzDXH2UPB1DfHwd1Fw8w9SMNRRMFIA0sYK4f5BLgqefsEhQaHOIZ7-fsE8DKxpiTnFqbxQmptBAaxdN7UgPz61uCAxOTUvtSTeNcDAxNjM2MTQ0diYCCUAMDMoHw</recordid><startdate>19930317</startdate><enddate>19930317</enddate><creator>REININGER, RUSSELL</creator><creator>LEDBETTER, WILLIA B., JR</creator><scope>EVB</scope></search><sort><creationdate>19930317</creationdate><title>SEQUENTIAL PREFETCH METHOD FOR 1, 2 OR 3 WORD INSTRUCTIONS</title><author>REININGER, RUSSELL ; LEDBETTER, WILLIA B., JR</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP0436341A33</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>1993</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>REININGER, RUSSELL</creatorcontrib><creatorcontrib>LEDBETTER, WILLIA B., JR</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>REININGER, RUSSELL</au><au>LEDBETTER, WILLIA B., JR</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SEQUENTIAL PREFETCH METHOD FOR 1, 2 OR 3 WORD INSTRUCTIONS</title><date>1993-03-17</date><risdate>1993</risdate><abstract>A sequential prefetch method is provided for a pipelined data processor (10) having a sequential instruction prefetch unit (IPU) (34). An instruction queue (50) in the IPU (34) is coupled to a pipelined instruction unit (32) and an instruction cache (14) of the data processor (10). A prefetch controller (56) in the IPU (34) keeps the instruction stream prefetched so that the instruction queue (50) may load any combination of one, two, or three word instructions into the pipelined instruction unit (32) every clock cycle. The pipelined instruction unit (32) receives instruction words from the instruction queue (50), and decodes the instruction for execution operations, and for the instruction length/pipeline movement. A queue filling method is provided for maintaining the requisite number of instruction words in the instruction queue (50) to avoid pipeline stalls. The queue filling method is based upon the movement of the instruction pipeline (32) attributable to the usage by an instruction sequencer (32) of the instruction words received from the instruction queue. (50)</abstract><edition>5</edition><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_EP0436341A3
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title SEQUENTIAL PREFETCH METHOD FOR 1, 2 OR 3 WORD INSTRUCTIONS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T04%3A22%3A44IST&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=REININGER,%20RUSSELL&rft.date=1993-03-17&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP0436341A3%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