VECTOR FRIENDLY INSTRUCTION FORMAT AND EXECUTION THEREOF

A vector friendly instruction format and execution thereof. According to one embodiment of the invention, a processor is to execute an instruction set. The instruction set includes a first instruction format, wherein the first instruction format includes a first plurality of templates, wherein the f...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHARNEY, Mark, DURAN, Santiago Galan, OULD-AHMED-VALL, Elmoustapha, CAVIN, Robert D, GIRKAR, Milind Baburao, SANS, Roger Espasa, ABEL, James C, WU, Lisa, VALENTINE, Robert C, SAN ADRIAN, Jesus Corbal, SAIR, Suleyman, GROCHOWSKI, Edward Thomas, YOUNT, Charles, TOLL, Bret L, HALL, Jonathan Cannon, BRADFORD, Dennis R, ABRAHAM, Seth, WIEDEMEIER, Jeffrey G, SAMUDRALA, Sridhar, FORSYTH, Andrew Thomas
Format: Patent
Sprache:eng ; fre ; ger
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 CHARNEY, Mark
DURAN, Santiago Galan
OULD-AHMED-VALL, Elmoustapha
CAVIN, Robert D
GIRKAR, Milind Baburao
SANS, Roger Espasa
ABEL, James C
WU, Lisa
VALENTINE, Robert C
SAN ADRIAN, Jesus Corbal
SAIR, Suleyman
GROCHOWSKI, Edward Thomas
YOUNT, Charles
TOLL, Bret L
HALL, Jonathan Cannon
BRADFORD, Dennis R
ABRAHAM, Seth
WIEDEMEIER, Jeffrey G
SAMUDRALA, Sridhar
FORSYTH, Andrew Thomas
description A vector friendly instruction format and execution thereof. According to one embodiment of the invention, a processor is to execute an instruction set. The instruction set includes a first instruction format, wherein the first instruction format includes a first plurality of templates, wherein the first instruction format has a plurality of fields including a base operation field, a data element width field, and a write mask field, wherein the first instruction format supports, through different values in the base operation field, specification of different vector operations, wherein each of the vector operations is to generate a destination vector operand including a plurality of data elements at different data element positions, wherein the first instruction format supports, through different values in the data element width field, specification of different data element widths, wherein the base operation field, the data element width field, and the write mask field may each store only one value on each occurrence of an instruction in the first instruction format in instruction streams. The processor includes a decode unit to decode the occurrences of the instructions in the first plurality of templates, including to: distinguish, for each of the occurrences, which one of the data element widths to use based on a value in the data element width field; and distinguish, for each of the occurrences, the data elements resulting from the occurrence's vector operation to be reflected in the destination vector operand's corresponding data element positions based on the write mask field's content and the data element width for the occurrence. Different values that may be stored in the write mask field distinguish different write mask registers, of a set of write mask registers, that are to store configurable write masks. The data element width for the occurrence distinguishes which of the data element positions of the destination vector operand correspond with which bits of the configurable write masks.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP3422178A3</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP3422178A3</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP3422178A33</originalsourceid><addsrcrecordid>eNrjZLAIc3UO8Q9ScAvydPVz8YlU8PQLDgkKdQ7x9PdTcPMP8nUMUXD0c1FwjXB1DgULhni4Brn6u_EwsKYl5hSn8kJpbgYFN9cQZw_d1IL8-NTigsTk1LzUknjXAGMTIyNDcwtHY2MilAAAQWEocA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>VECTOR FRIENDLY INSTRUCTION FORMAT AND EXECUTION THEREOF</title><source>esp@cenet</source><creator>CHARNEY, Mark ; DURAN, Santiago Galan ; OULD-AHMED-VALL, Elmoustapha ; CAVIN, Robert D ; GIRKAR, Milind Baburao ; SANS, Roger Espasa ; ABEL, James C ; WU, Lisa ; VALENTINE, Robert C ; SAN ADRIAN, Jesus Corbal ; SAIR, Suleyman ; GROCHOWSKI, Edward Thomas ; YOUNT, Charles ; TOLL, Bret L ; HALL, Jonathan Cannon ; BRADFORD, Dennis R ; ABRAHAM, Seth ; WIEDEMEIER, Jeffrey G ; SAMUDRALA, Sridhar ; FORSYTH, Andrew Thomas</creator><creatorcontrib>CHARNEY, Mark ; DURAN, Santiago Galan ; OULD-AHMED-VALL, Elmoustapha ; CAVIN, Robert D ; GIRKAR, Milind Baburao ; SANS, Roger Espasa ; ABEL, James C ; WU, Lisa ; VALENTINE, Robert C ; SAN ADRIAN, Jesus Corbal ; SAIR, Suleyman ; GROCHOWSKI, Edward Thomas ; YOUNT, Charles ; TOLL, Bret L ; HALL, Jonathan Cannon ; BRADFORD, Dennis R ; ABRAHAM, Seth ; WIEDEMEIER, Jeffrey G ; SAMUDRALA, Sridhar ; FORSYTH, Andrew Thomas</creatorcontrib><description>A vector friendly instruction format and execution thereof. According to one embodiment of the invention, a processor is to execute an instruction set. The instruction set includes a first instruction format, wherein the first instruction format includes a first plurality of templates, wherein the first instruction format has a plurality of fields including a base operation field, a data element width field, and a write mask field, wherein the first instruction format supports, through different values in the base operation field, specification of different vector operations, wherein each of the vector operations is to generate a destination vector operand including a plurality of data elements at different data element positions, wherein the first instruction format supports, through different values in the data element width field, specification of different data element widths, wherein the base operation field, the data element width field, and the write mask field may each store only one value on each occurrence of an instruction in the first instruction format in instruction streams. The processor includes a decode unit to decode the occurrences of the instructions in the first plurality of templates, including to: distinguish, for each of the occurrences, which one of the data element widths to use based on a value in the data element width field; and distinguish, for each of the occurrences, the data elements resulting from the occurrence's vector operation to be reflected in the destination vector operand's corresponding data element positions based on the write mask field's content and the data element width for the occurrence. Different values that may be stored in the write mask field distinguish different write mask registers, of a set of write mask registers, that are to store configurable write masks. The data element width for the occurrence distinguishes which of the data element positions of the destination vector operand correspond with which bits of the configurable write masks.</description><language>eng ; fre ; ger</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=20190410&amp;DB=EPODOC&amp;CC=EP&amp;NR=3422178A3$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20190410&amp;DB=EPODOC&amp;CC=EP&amp;NR=3422178A3$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHARNEY, Mark</creatorcontrib><creatorcontrib>DURAN, Santiago Galan</creatorcontrib><creatorcontrib>OULD-AHMED-VALL, Elmoustapha</creatorcontrib><creatorcontrib>CAVIN, Robert D</creatorcontrib><creatorcontrib>GIRKAR, Milind Baburao</creatorcontrib><creatorcontrib>SANS, Roger Espasa</creatorcontrib><creatorcontrib>ABEL, James C</creatorcontrib><creatorcontrib>WU, Lisa</creatorcontrib><creatorcontrib>VALENTINE, Robert C</creatorcontrib><creatorcontrib>SAN ADRIAN, Jesus Corbal</creatorcontrib><creatorcontrib>SAIR, Suleyman</creatorcontrib><creatorcontrib>GROCHOWSKI, Edward Thomas</creatorcontrib><creatorcontrib>YOUNT, Charles</creatorcontrib><creatorcontrib>TOLL, Bret L</creatorcontrib><creatorcontrib>HALL, Jonathan Cannon</creatorcontrib><creatorcontrib>BRADFORD, Dennis R</creatorcontrib><creatorcontrib>ABRAHAM, Seth</creatorcontrib><creatorcontrib>WIEDEMEIER, Jeffrey G</creatorcontrib><creatorcontrib>SAMUDRALA, Sridhar</creatorcontrib><creatorcontrib>FORSYTH, Andrew Thomas</creatorcontrib><title>VECTOR FRIENDLY INSTRUCTION FORMAT AND EXECUTION THEREOF</title><description>A vector friendly instruction format and execution thereof. According to one embodiment of the invention, a processor is to execute an instruction set. The instruction set includes a first instruction format, wherein the first instruction format includes a first plurality of templates, wherein the first instruction format has a plurality of fields including a base operation field, a data element width field, and a write mask field, wherein the first instruction format supports, through different values in the base operation field, specification of different vector operations, wherein each of the vector operations is to generate a destination vector operand including a plurality of data elements at different data element positions, wherein the first instruction format supports, through different values in the data element width field, specification of different data element widths, wherein the base operation field, the data element width field, and the write mask field may each store only one value on each occurrence of an instruction in the first instruction format in instruction streams. The processor includes a decode unit to decode the occurrences of the instructions in the first plurality of templates, including to: distinguish, for each of the occurrences, which one of the data element widths to use based on a value in the data element width field; and distinguish, for each of the occurrences, the data elements resulting from the occurrence's vector operation to be reflected in the destination vector operand's corresponding data element positions based on the write mask field's content and the data element width for the occurrence. Different values that may be stored in the write mask field distinguish different write mask registers, of a set of write mask registers, that are to store configurable write masks. The data element width for the occurrence distinguishes which of the data element positions of the destination vector operand correspond with which bits of the configurable write masks.</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>eNrjZLAIc3UO8Q9ScAvydPVz8YlU8PQLDgkKdQ7x9PdTcPMP8nUMUXD0c1FwjXB1DgULhni4Brn6u_EwsKYl5hSn8kJpbgYFN9cQZw_d1IL8-NTigsTk1LzUknjXAGMTIyNDcwtHY2MilAAAQWEocA</recordid><startdate>20190410</startdate><enddate>20190410</enddate><creator>CHARNEY, Mark</creator><creator>DURAN, Santiago Galan</creator><creator>OULD-AHMED-VALL, Elmoustapha</creator><creator>CAVIN, Robert D</creator><creator>GIRKAR, Milind Baburao</creator><creator>SANS, Roger Espasa</creator><creator>ABEL, James C</creator><creator>WU, Lisa</creator><creator>VALENTINE, Robert C</creator><creator>SAN ADRIAN, Jesus Corbal</creator><creator>SAIR, Suleyman</creator><creator>GROCHOWSKI, Edward Thomas</creator><creator>YOUNT, Charles</creator><creator>TOLL, Bret L</creator><creator>HALL, Jonathan Cannon</creator><creator>BRADFORD, Dennis R</creator><creator>ABRAHAM, Seth</creator><creator>WIEDEMEIER, Jeffrey G</creator><creator>SAMUDRALA, Sridhar</creator><creator>FORSYTH, Andrew Thomas</creator><scope>EVB</scope></search><sort><creationdate>20190410</creationdate><title>VECTOR FRIENDLY INSTRUCTION FORMAT AND EXECUTION THEREOF</title><author>CHARNEY, Mark ; DURAN, Santiago Galan ; OULD-AHMED-VALL, Elmoustapha ; CAVIN, Robert D ; GIRKAR, Milind Baburao ; SANS, Roger Espasa ; ABEL, James C ; WU, Lisa ; VALENTINE, Robert C ; SAN ADRIAN, Jesus Corbal ; SAIR, Suleyman ; GROCHOWSKI, Edward Thomas ; YOUNT, Charles ; TOLL, Bret L ; HALL, Jonathan Cannon ; BRADFORD, Dennis R ; ABRAHAM, Seth ; WIEDEMEIER, Jeffrey G ; SAMUDRALA, Sridhar ; FORSYTH, Andrew Thomas</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP3422178A33</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</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>CHARNEY, Mark</creatorcontrib><creatorcontrib>DURAN, Santiago Galan</creatorcontrib><creatorcontrib>OULD-AHMED-VALL, Elmoustapha</creatorcontrib><creatorcontrib>CAVIN, Robert D</creatorcontrib><creatorcontrib>GIRKAR, Milind Baburao</creatorcontrib><creatorcontrib>SANS, Roger Espasa</creatorcontrib><creatorcontrib>ABEL, James C</creatorcontrib><creatorcontrib>WU, Lisa</creatorcontrib><creatorcontrib>VALENTINE, Robert C</creatorcontrib><creatorcontrib>SAN ADRIAN, Jesus Corbal</creatorcontrib><creatorcontrib>SAIR, Suleyman</creatorcontrib><creatorcontrib>GROCHOWSKI, Edward Thomas</creatorcontrib><creatorcontrib>YOUNT, Charles</creatorcontrib><creatorcontrib>TOLL, Bret L</creatorcontrib><creatorcontrib>HALL, Jonathan Cannon</creatorcontrib><creatorcontrib>BRADFORD, Dennis R</creatorcontrib><creatorcontrib>ABRAHAM, Seth</creatorcontrib><creatorcontrib>WIEDEMEIER, Jeffrey G</creatorcontrib><creatorcontrib>SAMUDRALA, Sridhar</creatorcontrib><creatorcontrib>FORSYTH, Andrew Thomas</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHARNEY, Mark</au><au>DURAN, Santiago Galan</au><au>OULD-AHMED-VALL, Elmoustapha</au><au>CAVIN, Robert D</au><au>GIRKAR, Milind Baburao</au><au>SANS, Roger Espasa</au><au>ABEL, James C</au><au>WU, Lisa</au><au>VALENTINE, Robert C</au><au>SAN ADRIAN, Jesus Corbal</au><au>SAIR, Suleyman</au><au>GROCHOWSKI, Edward Thomas</au><au>YOUNT, Charles</au><au>TOLL, Bret L</au><au>HALL, Jonathan Cannon</au><au>BRADFORD, Dennis R</au><au>ABRAHAM, Seth</au><au>WIEDEMEIER, Jeffrey G</au><au>SAMUDRALA, Sridhar</au><au>FORSYTH, Andrew Thomas</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>VECTOR FRIENDLY INSTRUCTION FORMAT AND EXECUTION THEREOF</title><date>2019-04-10</date><risdate>2019</risdate><abstract>A vector friendly instruction format and execution thereof. According to one embodiment of the invention, a processor is to execute an instruction set. The instruction set includes a first instruction format, wherein the first instruction format includes a first plurality of templates, wherein the first instruction format has a plurality of fields including a base operation field, a data element width field, and a write mask field, wherein the first instruction format supports, through different values in the base operation field, specification of different vector operations, wherein each of the vector operations is to generate a destination vector operand including a plurality of data elements at different data element positions, wherein the first instruction format supports, through different values in the data element width field, specification of different data element widths, wherein the base operation field, the data element width field, and the write mask field may each store only one value on each occurrence of an instruction in the first instruction format in instruction streams. The processor includes a decode unit to decode the occurrences of the instructions in the first plurality of templates, including to: distinguish, for each of the occurrences, which one of the data element widths to use based on a value in the data element width field; and distinguish, for each of the occurrences, the data elements resulting from the occurrence's vector operation to be reflected in the destination vector operand's corresponding data element positions based on the write mask field's content and the data element width for the occurrence. Different values that may be stored in the write mask field distinguish different write mask registers, of a set of write mask registers, that are to store configurable write masks. The data element width for the occurrence distinguishes which of the data element positions of the destination vector operand correspond with which bits of the configurable write masks.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP3422178A3
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title VECTOR FRIENDLY INSTRUCTION FORMAT AND EXECUTION THEREOF
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T13%3A23%3A58IST&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=CHARNEY,%20Mark&rft.date=2019-04-10&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP3422178A3%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