INSTRUCTION LEVEL EXECUTION PREEMPTION
One embodiment of the present invention sets forth a technique instruction level and compute thread array granularity execution preemption. Preempting at the instruction level does not require any draining of the processing pipeline. No new instructions are issued and the context state is unloaded f...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , , |
---|---|
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 | SCHAUFLER GERNOT LAMB CHRISTOPHER PURCELL TIMOTHY JOHN CUADRA PHILIP ALEXANDER JOHNSON PHILIP BROWNING GADRE SHIRISH WANG NICHOLAS SHAH LACKY V OHANNESSIAN ROBERT DUNCAN SAMUEL H PALMER GREGORY SCOTT |
description | One embodiment of the present invention sets forth a technique instruction level and compute thread array granularity execution preemption. Preempting at the instruction level does not require any draining of the processing pipeline. No new instructions are issued and the context state is unloaded from the processing pipeline. When preemption is performed at a compute thread array boundary, the amount of context state to be stored is reduced because execution units within the processing pipeline complete execution of in-flight instructions and become idle. If, the amount of time needed to complete execution of the in-flight instructions exceeds a threshold, then the preemption may dynamically change to be performed at the instruction level instead of at compute thread array granularity. |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2013124838A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2013124838A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2013124838A13</originalsourceid><addsrcrecordid>eNrjZFDz9AsOCQp1DvH091PwcQ1z9VFwjXB1DgXzA4JcXX0DQEweBta0xJziVF4ozc2g7OYa4uyhm1qQH59aXJCYnJqXWhIfGmxkYGhsaGRiYWzhaGhMnCoAhTck8g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>INSTRUCTION LEVEL EXECUTION PREEMPTION</title><source>esp@cenet</source><creator>SCHAUFLER GERNOT ; LAMB CHRISTOPHER ; PURCELL TIMOTHY JOHN ; CUADRA PHILIP ALEXANDER ; JOHNSON PHILIP BROWNING ; GADRE SHIRISH ; WANG NICHOLAS ; SHAH LACKY V ; OHANNESSIAN ROBERT ; DUNCAN SAMUEL H ; PALMER GREGORY SCOTT</creator><creatorcontrib>SCHAUFLER GERNOT ; LAMB CHRISTOPHER ; PURCELL TIMOTHY JOHN ; CUADRA PHILIP ALEXANDER ; JOHNSON PHILIP BROWNING ; GADRE SHIRISH ; WANG NICHOLAS ; SHAH LACKY V ; OHANNESSIAN ROBERT ; DUNCAN SAMUEL H ; PALMER GREGORY SCOTT</creatorcontrib><description>One embodiment of the present invention sets forth a technique instruction level and compute thread array granularity execution preemption. Preempting at the instruction level does not require any draining of the processing pipeline. No new instructions are issued and the context state is unloaded from the processing pipeline. When preemption is performed at a compute thread array boundary, the amount of context state to be stored is reduced because execution units within the processing pipeline complete execution of in-flight instructions and become idle. If, the amount of time needed to complete execution of the in-flight instructions exceeds a threshold, then the preemption may dynamically change to be performed at the instruction level instead of at compute thread array granularity.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2013</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=20130516&DB=EPODOC&CC=US&NR=2013124838A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20130516&DB=EPODOC&CC=US&NR=2013124838A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SCHAUFLER GERNOT</creatorcontrib><creatorcontrib>LAMB CHRISTOPHER</creatorcontrib><creatorcontrib>PURCELL TIMOTHY JOHN</creatorcontrib><creatorcontrib>CUADRA PHILIP ALEXANDER</creatorcontrib><creatorcontrib>JOHNSON PHILIP BROWNING</creatorcontrib><creatorcontrib>GADRE SHIRISH</creatorcontrib><creatorcontrib>WANG NICHOLAS</creatorcontrib><creatorcontrib>SHAH LACKY V</creatorcontrib><creatorcontrib>OHANNESSIAN ROBERT</creatorcontrib><creatorcontrib>DUNCAN SAMUEL H</creatorcontrib><creatorcontrib>PALMER GREGORY SCOTT</creatorcontrib><title>INSTRUCTION LEVEL EXECUTION PREEMPTION</title><description>One embodiment of the present invention sets forth a technique instruction level and compute thread array granularity execution preemption. Preempting at the instruction level does not require any draining of the processing pipeline. No new instructions are issued and the context state is unloaded from the processing pipeline. When preemption is performed at a compute thread array boundary, the amount of context state to be stored is reduced because execution units within the processing pipeline complete execution of in-flight instructions and become idle. If, the amount of time needed to complete execution of the in-flight instructions exceeds a threshold, then the preemption may dynamically change to be performed at the instruction level instead of at compute thread array granularity.</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>2013</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFDz9AsOCQp1DvH091PwcQ1z9VFwjXB1DgXzA4JcXX0DQEweBta0xJziVF4ozc2g7OYa4uyhm1qQH59aXJCYnJqXWhIfGmxkYGhsaGRiYWzhaGhMnCoAhTck8g</recordid><startdate>20130516</startdate><enddate>20130516</enddate><creator>SCHAUFLER GERNOT</creator><creator>LAMB CHRISTOPHER</creator><creator>PURCELL TIMOTHY JOHN</creator><creator>CUADRA PHILIP ALEXANDER</creator><creator>JOHNSON PHILIP BROWNING</creator><creator>GADRE SHIRISH</creator><creator>WANG NICHOLAS</creator><creator>SHAH LACKY V</creator><creator>OHANNESSIAN ROBERT</creator><creator>DUNCAN SAMUEL H</creator><creator>PALMER GREGORY SCOTT</creator><scope>EVB</scope></search><sort><creationdate>20130516</creationdate><title>INSTRUCTION LEVEL EXECUTION PREEMPTION</title><author>SCHAUFLER GERNOT ; LAMB CHRISTOPHER ; PURCELL TIMOTHY JOHN ; CUADRA PHILIP ALEXANDER ; JOHNSON PHILIP BROWNING ; GADRE SHIRISH ; WANG NICHOLAS ; SHAH LACKY V ; OHANNESSIAN ROBERT ; DUNCAN SAMUEL H ; PALMER GREGORY SCOTT</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2013124838A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2013</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>SCHAUFLER GERNOT</creatorcontrib><creatorcontrib>LAMB CHRISTOPHER</creatorcontrib><creatorcontrib>PURCELL TIMOTHY JOHN</creatorcontrib><creatorcontrib>CUADRA PHILIP ALEXANDER</creatorcontrib><creatorcontrib>JOHNSON PHILIP BROWNING</creatorcontrib><creatorcontrib>GADRE SHIRISH</creatorcontrib><creatorcontrib>WANG NICHOLAS</creatorcontrib><creatorcontrib>SHAH LACKY V</creatorcontrib><creatorcontrib>OHANNESSIAN ROBERT</creatorcontrib><creatorcontrib>DUNCAN SAMUEL H</creatorcontrib><creatorcontrib>PALMER GREGORY SCOTT</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SCHAUFLER GERNOT</au><au>LAMB CHRISTOPHER</au><au>PURCELL TIMOTHY JOHN</au><au>CUADRA PHILIP ALEXANDER</au><au>JOHNSON PHILIP BROWNING</au><au>GADRE SHIRISH</au><au>WANG NICHOLAS</au><au>SHAH LACKY V</au><au>OHANNESSIAN ROBERT</au><au>DUNCAN SAMUEL H</au><au>PALMER GREGORY SCOTT</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>INSTRUCTION LEVEL EXECUTION PREEMPTION</title><date>2013-05-16</date><risdate>2013</risdate><abstract>One embodiment of the present invention sets forth a technique instruction level and compute thread array granularity execution preemption. Preempting at the instruction level does not require any draining of the processing pipeline. No new instructions are issued and the context state is unloaded from the processing pipeline. When preemption is performed at a compute thread array boundary, the amount of context state to be stored is reduced because execution units within the processing pipeline complete execution of in-flight instructions and become idle. If, the amount of time needed to complete execution of the in-flight instructions exceeds a threshold, then the preemption may dynamically change to be performed at the instruction level instead of at compute thread array granularity.</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | eng |
recordid | cdi_epo_espacenet_US2013124838A1 |
source | esp@cenet |
subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
title | INSTRUCTION LEVEL EXECUTION PREEMPTION |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T05%3A16%3A15IST&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=SCHAUFLER%20GERNOT&rft.date=2013-05-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2013124838A1%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 |