ROUNDING MECHANISMS IN PROCESSORS
An arithmetic unit, for example a multiply and accumulate (MAC) unit 42, for a processing engine includes a partial product reduction tree 480. The partial product reduction tree will generate carry results and provides a final output to a final adder 470 connected to the partial production reductio...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | eng |
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 | GIACALONE, JEAN-PIERRE LOMBARDOT, ANNE THEODOROU, FRANCOIS |
description | An arithmetic unit, for example a multiply and accumulate (MAC) unit
42,
for a processing engine includes a partial product reduction tree
480.
The partial product reduction tree will generate carry results and provides a final output to a final adder
470
connected to the partial production reduction tree. Unbiased rounding logic
476
is provided. A carry propagation tree is responsive to the carry results for anticipating a zero on each of N least significant bits of the final adder. When zero is anticipated on each of N least significant bits of the final adder, the carry propagation tree is operable to generate an output signal
477
which is used by the unbiased rounding stage to force the (N+1)th least significant bit of the final adder to zero. Through the use of a carry propagation tree to predict, or anticipate zeros on the N least significant bits, unbiased rounding can be effected without a time penalty in that a carry propagation tree can be configured to be at least a rapid as the carry propagation of the final adder. Where a zero anticipation function is provided, this can also be mapped onto the carry propagation tree, thus providing an efficient hardware implementation through sharing of that hardware between functions. |
format | Patent |
fullrecord | <record><control><sourceid>uspatents_EFI</sourceid><recordid>TN_cdi_uspatents_applications_20030055860</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>20030055860</sourcerecordid><originalsourceid>FETCH-uspatents_applications_200300558603</originalsourceid><addsrcrecordid>eNrjZFAM8g_1c_H0c1fwdXX2cPTzDPYNVvD0UwgI8nd2DQ72DwrmYWBNS8wpTuWF0twMmm6uIc4euqXFBYklqXklxfGJBQU5mcmJJZn5ecXxRgYGxgYGpqYWZgbGpKgFAPC1KWo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ROUNDING MECHANISMS IN PROCESSORS</title><source>USPTO Published Applications</source><creator>GIACALONE, JEAN-PIERRE ; LOMBARDOT, ANNE ; THEODOROU, FRANCOIS</creator><creatorcontrib>GIACALONE, JEAN-PIERRE ; LOMBARDOT, ANNE ; THEODOROU, FRANCOIS</creatorcontrib><description>An arithmetic unit, for example a multiply and accumulate (MAC) unit
42,
for a processing engine includes a partial product reduction tree
480.
The partial product reduction tree will generate carry results and provides a final output to a final adder
470
connected to the partial production reduction tree. Unbiased rounding logic
476
is provided. A carry propagation tree is responsive to the carry results for anticipating a zero on each of N least significant bits of the final adder. When zero is anticipated on each of N least significant bits of the final adder, the carry propagation tree is operable to generate an output signal
477
which is used by the unbiased rounding stage to force the (N+1)th least significant bit of the final adder to zero. Through the use of a carry propagation tree to predict, or anticipate zeros on the N least significant bits, unbiased rounding can be effected without a time penalty in that a carry propagation tree can be configured to be at least a rapid as the carry propagation of the final adder. Where a zero anticipation function is provided, this can also be mapped onto the carry propagation tree, thus providing an efficient hardware implementation through sharing of that hardware between functions.</description><language>eng</language><creationdate>2003</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/20030055860$$EPDF$$P50$$Guspatents$$Hfree_for_read</linktopdf><link.rule.ids>230,308,776,869,881,64032</link.rule.ids><linktorsrc>$$Uhttps://patentcenter.uspto.gov/applications/09411186$$EView_record_in_USPTO$$FView_record_in_$$GUSPTO$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>GIACALONE, JEAN-PIERRE</creatorcontrib><creatorcontrib>LOMBARDOT, ANNE</creatorcontrib><creatorcontrib>THEODOROU, FRANCOIS</creatorcontrib><title>ROUNDING MECHANISMS IN PROCESSORS</title><description>An arithmetic unit, for example a multiply and accumulate (MAC) unit
42,
for a processing engine includes a partial product reduction tree
480.
The partial product reduction tree will generate carry results and provides a final output to a final adder
470
connected to the partial production reduction tree. Unbiased rounding logic
476
is provided. A carry propagation tree is responsive to the carry results for anticipating a zero on each of N least significant bits of the final adder. When zero is anticipated on each of N least significant bits of the final adder, the carry propagation tree is operable to generate an output signal
477
which is used by the unbiased rounding stage to force the (N+1)th least significant bit of the final adder to zero. Through the use of a carry propagation tree to predict, or anticipate zeros on the N least significant bits, unbiased rounding can be effected without a time penalty in that a carry propagation tree can be configured to be at least a rapid as the carry propagation of the final adder. Where a zero anticipation function is provided, this can also be mapped onto the carry propagation tree, thus providing an efficient hardware implementation through sharing of that hardware between functions.</description><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2003</creationdate><recordtype>patent</recordtype><sourceid>EFI</sourceid><recordid>eNrjZFAM8g_1c_H0c1fwdXX2cPTzDPYNVvD0UwgI8nd2DQ72DwrmYWBNS8wpTuWF0twMmm6uIc4euqXFBYklqXklxfGJBQU5mcmJJZn5ecXxRgYGxgYGpqYWZgbGpKgFAPC1KWo</recordid><startdate>20030320</startdate><enddate>20030320</enddate><creator>GIACALONE, JEAN-PIERRE</creator><creator>LOMBARDOT, ANNE</creator><creator>THEODOROU, FRANCOIS</creator><scope>EFI</scope></search><sort><creationdate>20030320</creationdate><title>ROUNDING MECHANISMS IN PROCESSORS</title><author>GIACALONE, JEAN-PIERRE ; LOMBARDOT, ANNE ; THEODOROU, FRANCOIS</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-uspatents_applications_200300558603</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2003</creationdate><toplevel>online_resources</toplevel><creatorcontrib>GIACALONE, JEAN-PIERRE</creatorcontrib><creatorcontrib>LOMBARDOT, ANNE</creatorcontrib><creatorcontrib>THEODOROU, FRANCOIS</creatorcontrib><collection>USPTO Published Applications</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>GIACALONE, JEAN-PIERRE</au><au>LOMBARDOT, ANNE</au><au>THEODOROU, FRANCOIS</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ROUNDING MECHANISMS IN PROCESSORS</title><date>2003-03-20</date><risdate>2003</risdate><abstract>An arithmetic unit, for example a multiply and accumulate (MAC) unit
42,
for a processing engine includes a partial product reduction tree
480.
The partial product reduction tree will generate carry results and provides a final output to a final adder
470
connected to the partial production reduction tree. Unbiased rounding logic
476
is provided. A carry propagation tree is responsive to the carry results for anticipating a zero on each of N least significant bits of the final adder. When zero is anticipated on each of N least significant bits of the final adder, the carry propagation tree is operable to generate an output signal
477
which is used by the unbiased rounding stage to force the (N+1)th least significant bit of the final adder to zero. Through the use of a carry propagation tree to predict, or anticipate zeros on the N least significant bits, unbiased rounding can be effected without a time penalty in that a carry propagation tree can be configured to be at least a rapid as the carry propagation of the final adder. Where a zero anticipation function is provided, this can also be mapped onto the carry propagation tree, thus providing an efficient hardware implementation through sharing of that hardware between functions.</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | eng |
recordid | cdi_uspatents_applications_20030055860 |
source | USPTO Published Applications |
title | ROUNDING MECHANISMS IN PROCESSORS |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T18%3A57%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-uspatents_EFI&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=GIACALONE,%20JEAN-PIERRE&rft.date=2003-03-20&rft_id=info:doi/&rft_dat=%3Cuspatents_EFI%3E20030055860%3C/uspatents_EFI%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 |