Recursion leads to automatic variable blocking for dense linear-algebra algorithms

We describe some modifications of the LAPACK dense linear-algebra algorithms using recursion. Recursion leads to automatic variable blocking. LAPACK's level-2 versions transform into level-3 codes by using recursion. The new recursive codes are written in FORTRAN 77, which does not support recu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IBM journal of research and development Jg. 41; H. 6; S. 737 - 755
1. Verfasser: Gustavson, F. G.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Armonk, NY International Business Machines 01.11.1997
International Business Machines Corporation
Schlagworte:
Algorithmics. Computability. Computer arithmetics
Algorithms
Applied sciences
Computer science; control theory; systems
Exact sciences and technology
Linear programming
Theoretical computing
Variables
Experimental result
Computer arithmetic
Cholesky method
Recursive algorithm
Factorization
Linear algebra
ISSN:0018-8646, 0018-8646, 2151-8556
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We describe some modifications of the LAPACK dense linear-algebra algorithms using recursion. Recursion leads to automatic variable blocking. LAPACK's level-2 versions transform into level-3 codes by using recursion. The new recursive codes are written in FORTRAN 77, which does not support recursion as a language feature. Gaussian elimination with partial pivoting and Cholesky factorization are considered. Very clear algorithms emerge with the use of recursion. The recursive codes do exactly the same computation as the LAPACK codes, and a single recursive code replaces both the level-2 and level-3 versions of the corresponding LAPACK codes. We present an analysis of the recursive algorithm in terms of both FLOP count and storage usage. The matrix operands are more `squarish' using recursion. The total area of the submatrices used in the recursive algorithm is less than the total area used by the LAPACK level-3 right-/left-looking algorithms. We quantify the difference; we also quantify how the FLOPS are computed. Also, we show that the algorithms exhibit high performance on RISC-type processors. In fact, except for small matrices, the recursive version outperforms the level-3 LAPACK versions of DGETRF and DPOTRF on an RS /6000 super(TM) workstation. For the level-2 versions, the performance gain approaches a factor of 3. We also demonstrate that a change to the LAPACK DLASWP routine can improve the performance of both the recursive version and DGETRF by more than 15 percent.
AbstractList We describe some modifications of the LAPACK dense linear-algebra algorithms using recursion. Recursion leads to automatic variable blocking. LAPACK's level-2 versions transform into level-3 codes by using recursion. The new recursive codes are written in FORTRAN 77, which does not support recursion as a language feature. Gaussian elimination with partial pivoting and Cholesky factorization are considered. Very clear algorithms emerge with the use of recursion. The recursive codes do exactly the same computation as the LAPACK codes, and a single recursive code replaces both the level-2 and level-3 versions of the corresponding LAPACK codes. We present an analysis of the recursive algorithm in terms of both FLOP count and storage usage. The matrix operands are more `squarish' using recursion. The total area of the submatrices used in the recursive algorithm is less than the total area used by the LAPACK level-3 right-/left-looking algorithms. We quantify the difference; we also quantify how the FLOPS are computed. Also, we show that the algorithms exhibit high performance on RISC-type processors. In fact, except for small matrices, the recursive version outperforms the level-3 LAPACK versions of DGETRF and DPOTRF on an RS /6000 super(TM) workstation. For the level-2 versions, the performance gain approaches a factor of 3. We also demonstrate that a change to the LAPACK DLASWP routine can improve the performance of both the recursive version and DGETRF by more than 15 percent.
Gustavson describes some modifications of the LAPACK dense linear-algebra algorithms using recursion, which leads to automatic variable blocking.
Author Gustavson, F. G.
Author_xml – sequence: 1
  givenname: F. G.
  surname: Gustavson
  fullname: Gustavson, F. G.
  organization: IBM Research Division, Thomas J. Watson Research Center, P.O. Box 2I8, Yorktown Heights, New York 10598, USA
BackLink http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=2120453$$DView record in Pascal Francis
BookMark eNpt0U1LxDAQBuAgCurqyT8QRLxI1yRNm3gU8QsEQfRcJslUo9lEk1bw39tlFxHxNHN4Zhjm3SWbMUUk5ICzOedSnWY3l7ydM1WrDbLDGNeVbmW7-avfJrulvDLGGinPdsjDA9oxF58iDQiu0CFRGIe0gMFb-gnZgwlITUj2zcdn2qdMHcaCNPiIkCsIz2gy0Kmm7IeXRdkjWz2EgvvrOiNPV5ePFzfV3f317cX5XWVrrodKudqBNC0TzhqjG2MMt61qjDJaid44KbRAjtoBcoHSGNDSaSEs46yWqp6R49Xe95w-RixDt_DFYggQMY2lE_ys0Vos4eEf-JrGHKfbOiFY2zCp5ISO1giKhdBniNaX7j37BeSvaZlgsqkndrJiNqdSMvY_grNumUGXXTdl0C0zmDT_o60fps-mOGTw4d-ZbwYzjC8
CODEN IBMJAE
CitedBy_id crossref_primary_10_1002_wics_164
crossref_primary_10_1145_3061664
crossref_primary_10_1145_358438_349325
crossref_primary_10_1137_090769156
crossref_primary_10_1017_S0962492914000038
crossref_primary_10_1145_358438_349323
crossref_primary_10_1137_100788926
crossref_primary_10_1002_cpe_728
crossref_primary_10_1016_j_jpdc_2013_10_005
crossref_primary_10_1016_j_cam_2008_11_012
crossref_primary_10_1017_S0962492916000015
crossref_primary_10_1109_JPROC_2008_917732
crossref_primary_10_1016_j_parco_2015_10_003
crossref_primary_10_1023_A_1021928926132
crossref_primary_10_1145_383738_383741
crossref_primary_10_1002_cpe_2974
crossref_primary_10_1002_cpe_3306
crossref_primary_10_1002_cpe_630
crossref_primary_10_1145_568014_379559
crossref_primary_10_1016_j_laa_2006_03_018
crossref_primary_10_1007_s00607_016_0537_2
crossref_primary_10_1145_2395116_2395121
crossref_primary_10_1177_10943420221136848
crossref_primary_10_1016_j_jpdc_2014_02_003
crossref_primary_10_1145_1057387_1057388
crossref_primary_10_1145_1067967_1067969
crossref_primary_10_1109_TCAD_2019_2925377
crossref_primary_10_1137_130929060
crossref_primary_10_2478_amcs_2019_0030
crossref_primary_10_1145_2491491_2491492
crossref_primary_10_1016_S0377_0427_00_00401_5
crossref_primary_10_1002_cpe_4055
crossref_primary_10_1016_j_infsof_2014_10_001
crossref_primary_10_1016_j_procs_2012_04_003
crossref_primary_10_1023_A_1007560600904
crossref_primary_10_1109_TPDS_2002_1058095
crossref_primary_10_1002_cpe_661
crossref_primary_10_1137_S0036144503428693
crossref_primary_10_1016_j_future_2003_07_007
crossref_primary_10_1016_j_parco_2008_10_002
crossref_primary_10_1109_TPDS_2012_242
crossref_primary_10_1002_cpe_1467
crossref_primary_10_1145_2427023_2427026
crossref_primary_10_1016_j_jcp_2023_112137
crossref_primary_10_1002_cpe_3110
crossref_primary_10_1145_592843_592845
crossref_primary_10_1007_s10766_016_0441_6
crossref_primary_10_1016_j_procs_2012_04_012
crossref_primary_10_1023_A_1012293814832
crossref_primary_10_1145_1837853_1693484
crossref_primary_10_1145_504210_504213
crossref_primary_10_1145_383845_383867
crossref_primary_10_1002_cpe_857
crossref_primary_10_1177_1094342017725568
crossref_primary_10_1016_j_parco_2003_05_014
crossref_primary_10_1016_j_parco_2009_12_002
crossref_primary_10_1137_090760969
crossref_primary_10_1002_spe_626
crossref_primary_10_1007_s11227_012_0824_4
ContentType Journal Article
Copyright 1998 INIST-CNRS
Copyright International Business Machines Corporation Nov 1997
Copyright_xml – notice: 1998 INIST-CNRS
– notice: Copyright International Business Machines Corporation Nov 1997
DBID AAYXX
CITATION
IQODW
3V.
7WY
7WZ
7XB
87Z
88I
8AL
8AO
8FE
8FG
8FK
8FL
8G5
ABUWG
AFKRA
ARAPS
AZQEC
BEC
BENPR
BEZIV
BGLVJ
CCPQU
DWQXO
FRNLG
F~G
GNUQQ
GUQSH
HCIFZ
JQ2
K60
K6~
K7-
L.-
M0C
M0N
M2O
M2P
MBDVC
P5Z
P62
PHGZM
PHGZT
PKEHL
PQBIZ
PQBZA
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
Q9U
7SC
8FD
L7M
L~C
L~D
DOI 10.1147/rd.416.0737
DatabaseName CrossRef
Pascal-Francis
ProQuest Central (Corporate)
ProQuest ABI/INFORM Collection
ABI/INFORM Global (PDF only)
ProQuest Central (purchase pre-March 2016)
ABI/INFORM Collection
Science Database (Alumni Edition)
Computing Database (Alumni Edition)
ProQuest Pharma Collection
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
ABI/INFORM Collection (Alumni Edition)
Research Library (Alumni Edition)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
eLibrary
ProQuest Central
Business Premium Collection
Technology collection
ProQuest One Community College
ProQuest Central
Business Premium Collection (Alumni)
ABI/INFORM Global (Corporate)
ProQuest Central Student
Research Library Prep
SciTech Premium Collection
ProQuest Computer Science Collection
ProQuest Business Collection (Alumni Edition)
ProQuest Business Collection
Computer Science Database
ABI/INFORM Professional Advanced
ABI/INFORM Global
Computing Database
Research Library
Science Database
Research Library (Corporate)
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
ProQuest One Academic Middle East (New)
ProQuest One Business (UW System Shared)
ProQuest One Business (Alumni)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
ProQuest Central Basic
Computer and Information Systems Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
ABI/INFORM Global (Corporate)
ProQuest Business Collection (Alumni Edition)
ProQuest One Business
Research Library Prep
Computer Science Database
ProQuest Central Student
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
elibrary
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
Research Library (Alumni Edition)
ProQuest Pharma Collection
ProQuest Central China
ABI/INFORM Complete
ProQuest Central
ABI/INFORM Professional Advanced
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Research Library
ProQuest Central (New)
ABI/INFORM Complete (Alumni Edition)
Advanced Technologies & Aerospace Collection
Business Premium Collection
ABI/INFORM Global
ProQuest Computing
ProQuest Science Journals (Alumni Edition)
ABI/INFORM Global (Alumni Edition)
ProQuest Central Basic
ProQuest Science Journals
ProQuest Computing (Alumni Edition)
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Business Collection
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest One Business (Alumni)
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
Business Premium Collection (Alumni)
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts
ABI/INFORM Global (Corporate)
Database_xml – sequence: 1
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
Computer Science
Applied Sciences
EISSN 0018-8646
2151-8556
EndPage 755
ExternalDocumentID 25309172
2120453
10_1147_rd_416_0737
Genre Feature
GroupedDBID --Z
-~X
.DC
29I
3EH
41~
53G
5GY
6IK
6TJ
7WY
88I
8AO
8EE
8FE
8FG
8FL
8G5
8R4
8R5
9M8
AAFWJ
AAIKC
AAJGR
AAMNW
AAYXX
ABEFU
ABFSI
ABJNI
ABPPZ
ABUFD
ABUWG
ABVLG
ACGFO
ACGFS
ACGOD
ACNCT
AENEX
AETEA
AFFHD
AFFNX
AFKRA
AI.
ALMA_UNASSIGNED_HOLDINGS
ARAPS
AZQEC
BCR
BCU
BEC
BEFXN
BENPR
BES
BEZIV
BFFAM
BGLVJ
BGNUA
BKEBE
BLC
BPEOZ
BPHCQ
C1A
CCPQU
CITATION
CYX
DWQXO
E.L
EBS
EJD
FRNLG
GNUQQ
GROUPED_ABI_INFORM_RESEARCH
GUQSH
HCIFZ
H~9
IPLJI
JAVBF
K60
K6V
K6~
K7-
M0C
M2O
M2P
M43
MS~
MVM
OCL
OHT
OVT
P-O
P2P
P62
PHGZM
PHGZT
PQBIZ
PQBZA
PQGLB
PQQKQ
PROAC
Q2X
RNS
RWL
S10
SJFOW
TAE
TN5
U5U
UPT
VH1
VOH
WH7
XSB
ZCA
ZCG
ZE2
ZY4
~02
ABAZT
IQODW
XJT
3V.
7XB
8AL
8FK
JQ2
L.-
M0N
MBDVC
PKEHL
PQEST
PQUKI
PRINS
Q9U
7SC
8FD
L7M
L~C
L~D
ID FETCH-LOGICAL-c318t-7d3da4b602dcbb85bbb1c675b7b872fbd4282e1e8dae12e4bba84d822c0103473
IEDL.DBID BENPR
ISICitedReferencesCount 131
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000071347200008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-8646
IngestDate Sun Nov 09 12:20:07 EST 2025
Sun Nov 30 05:35:52 EST 2025
Mon Jul 21 09:18:31 EDT 2025
Tue Nov 18 20:42:39 EST 2025
Sat Nov 29 07:09:53 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Keywords Experimental result
Computer arithmetic
Cholesky method
Recursive algorithm
Factorization
Linear algebra
Language English
License CC BY 4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c318t-7d3da4b602dcbb85bbb1c675b7b872fbd4282e1e8dae12e4bba84d822c0103473
Notes SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
PQID 220650474
PQPubID 41123
PageCount 19
ParticipantIDs proquest_miscellaneous_21958827
proquest_journals_220650474
pascalfrancis_primary_2120453
crossref_primary_10_1147_rd_416_0737
crossref_citationtrail_10_1147_rd_416_0737
PublicationCentury 1900
PublicationDate 1997-11-01
PublicationDateYYYYMMDD 1997-11-01
PublicationDate_xml – month: 11
  year: 1997
  text: 1997-11-01
  day: 01
PublicationDecade 1990
PublicationPlace Armonk, NY
PublicationPlace_xml – name: Armonk, NY
– name: Armonk
PublicationTitle IBM journal of research and development
PublicationYear 1997
Publisher International Business Machines
International Business Machines Corporation
Publisher_xml – name: International Business Machines
– name: International Business Machines Corporation
SSID ssj0005449
Score 1.9122609
Snippet Gustavson describes some modifications of the LAPACK dense linear-algebra algorithms using recursion, which leads to automatic variable blocking.
We describe some modifications of the LAPACK dense linear-algebra algorithms using recursion. Recursion leads to automatic variable blocking. LAPACK's level-2...
SourceID proquest
pascalfrancis
crossref
SourceType Aggregation Database
Index Database
Enrichment Source
StartPage 737
SubjectTerms Algorithmics. Computability. Computer arithmetics
Algorithms
Applied sciences
Computer science; control theory; systems
Exact sciences and technology
Linear programming
Theoretical computing
Variables
Title Recursion leads to automatic variable blocking for dense linear-algebra algorithms
URI https://www.proquest.com/docview/220650474
https://www.proquest.com/docview/21958827
Volume 41
WOSCitedRecordID wos000071347200008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: ABI/INFORM Global (OCUL)
  customDbUrl:
  eissn: 0018-8646
  dateEnd: 20090131
  omitProxy: false
  ssIdentifier: ssj0005449
  issn: 0018-8646
  databaseCode: M0C
  dateStart: 19961101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/abiglobal
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 0018-8646
  dateEnd: 20090131
  omitProxy: false
  ssIdentifier: ssj0005449
  issn: 0018-8646
  databaseCode: P5Z
  dateStart: 19961101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 0018-8646
  dateEnd: 20090131
  omitProxy: false
  ssIdentifier: ssj0005449
  issn: 0018-8646
  databaseCode: K7-
  dateStart: 19961101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest ABI/INFORM Collection
  customDbUrl:
  eissn: 0018-8646
  dateEnd: 20090131
  omitProxy: false
  ssIdentifier: ssj0005449
  issn: 0018-8646
  databaseCode: 7WY
  dateStart: 19961101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/abicomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 0018-8646
  dateEnd: 20090131
  omitProxy: false
  ssIdentifier: ssj0005449
  issn: 0018-8646
  databaseCode: BENPR
  dateStart: 19961101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Research Library
  customDbUrl:
  eissn: 0018-8646
  dateEnd: 20090131
  omitProxy: false
  ssIdentifier: ssj0005449
  issn: 0018-8646
  databaseCode: M2O
  dateStart: 19961101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/pqrl
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 0018-8646
  dateEnd: 20090131
  omitProxy: false
  ssIdentifier: ssj0005449
  issn: 0018-8646
  databaseCode: M2P
  dateStart: 19961101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fS9xAEB6qVrBIbU-lp9Xug0-FVbO3ye49FRWlUHo9jpZaX8L-Cgp6OZOcf39ncntXxdKXvmwI2cCSmd35ZjIzH8BB4jw6PibjaIwEl9Jrrq2Q3GaZC32JRib1LdmEGgz05WV_GHNz6phWOT8T24Pal45i5EdCEJiQSn6a3HMijaKfq5FBYwlWqFEZqvnK6flgOPqT4yEj_k1wCZnMYoFeItVR5Q8RixyihqsnJml9Ymr8OsWM1uLZCd2anYuN_1zwG3gd8SY7mSnIW3gRxh3YmHM5sLi1O_DqUWPCDqy2iaGu3oTRiALyFFJjt6gONWtKZqZN2XZ6ZQ_oaVPtFbNoEynozhADMzzK6sAIv5qKE48IeuQMr7i85vqu3oIfF-ffzz7zyMPAHe74hivf80ba7Fh4Z61OrbWJQ0fDKquVKKxHF0aEJGhvQiKCtNZoFLoQjkgkpOptw_K4HId3wIIyxrrMFrJvpDNENmMQYaaF14UqUt2Fj3NR5C42KSeujNt8VkCt8srnKLec5NaFg8Xkyaw3x9-n7T2R6WIuWm0EtL0u7M4FmMcNXOcL6XXhw-Ip7jz6nWLGoZziFOrTo4Xa-ef7u7DWdrxtyxffw3JTTcMevHQPzU1d7cOS-vlrP6ot3n1RHMevx2c0im_tOMRxmF79BtLS-5Q
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1NTxRBEK0gaJAQ0EXjikAf8GLSwPT2TvcejCEogQAbQzDhNnZ190STdWedmcXwo_iPVM_HCtF44-BpDlMzSXe_qnr9VQ9gO7KOJj4m5pSMBJfSaa5RSI5xbP1AUpLpu0psQg2H-vJy8HkObtq7MOFYZRsTq0DtMhvWyHeFCGRCKvlh8pMH0aiwudoqaNSoOPHXv2jGVrw__kjD-1aIw08XB0e8ERXgluBbcuV6zkiM94SziLqPiJEl1owKtRIpOuLjwkdeO-Mj4SWi0dQCIWxQRJCqR_99BAuS5l3Brc72Dn6fKJEN246owbGMm-uAkVS7udsh5rND_qTuJcDliSloLNJaROOPfFAlucPV_6x7nsFKw6bZfg3_5zDnxx1YbZUqWBO4OrB0p-xiB55Ux15tsQbn52G7ISwYshGBvWBlxsy0zKo6tuzKkHfiyDOkjB-2FBgxfEaBuvAssHOT86CSgrlh9KTuKL_9KF7Alwdp8UuYH2dj_wqYV8agjTGVAyOtCVI6hvhzP3U6VWlfd-FdO_SJbUqwByWQUVJfD1dJ7hLCSRJw0oXtmfGkrjzyd7ONexia2RInIbre68J6C5ikCU9FMkNLF7ZmbymuhM0iM_bZlExCFSIt1Ot_fr8Fi0cXZ6fJ6fHwZB2eVrV9q4uab2C-zKd-Ax7bq_J7kW9WrsLg60OD7xZ-E1Mb
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VAhUIUViKupRSH8oFyV3idWLvASFEWVEVlqoCqbfUYzsq0rLZJtlW_DT-HeN8LFQgbj1wyiFOJNtvZp7t8TyA3cg6WviYhFMwElxKp7lGITkmifUjSUEmdrXYhJpM9MnJ6GgFfnR3YUJaZecTa0ftchv2yAdCBDIhlRxkbVbE0f749fycBwGpcNDaqWk0CDn03y9p9Va-OtinqX4uxPjd57fveSswwC1BueLKDZ2RmLwUziLqGBEjSwwaFWolMnTEzYWPvHbGR8JLRKOpN0LYoI4g1ZD-ewNuKhnLYFwfxadf2SWyZd4RdT6RSXs1MJJqULg9YkF7ZFvqSjC8NzclzUvWCGr8ERvqgDde_4-H6gHcb1k2e9OYxUNY8bMerHcKFqx1aD24-1s5xh7crtNhbfkIjo_DMUTYSGRTMoKSVTkziyqv69uyC0NWi1PPkJhAOGpgxPwZOfDSs8DaTcGDegoWhtGThqM6-1ZuwJdr6fFjWJ3lM78JzCtj0CaYyZGR1gSJHUO8Os6czlQW6z686GCQ2rY0e1AImabNtXGVFi4lzKQBM33YXTaeNxVJ_t5s-wqelm2JqxCNH_ZhqwNP2rqtMl0ipw87y7fkb8Ihkpn5fEFNQnUiLdSTf36_A2uEufTDweRwC-7UJX_r-5tPYbUqFn4bbtmL6mtZPKuthsHpdWPvJ5kqXAI
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Recursion+leads+to+automatic+variable+blocking+for+dense+linear-algebra+algorithms&rft.jtitle=IBM+journal+of+research+and+development&rft.au=Gustavson%2C+F+G&rft.date=1997-11-01&rft.issn=0018-8646&rft.volume=41&rft.issue=6&rft.spage=737&rft.epage=755&rft_id=info:doi/10.1147%2Frd.416.0737&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-8646&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-8646&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-8646&client=summon