{"id":"https://openalex.org/W1587796446","doi":null,"title":"Techniques for Optimizing Applications: High Performance Computing","display_name":"Techniques for Optimizing Applications: High Performance Computing","publication_year":2001,"publication_date":"2001-07-25","ids":{"openalex":"https://openalex.org/W1587796446","mag":"1587796446"},"language":"en","primary_location":{"id":"pmh:oai:cds.cern.ch:1505597","doi":null,"is_oa":false,"landing_page_url":"http://cds.cern.ch/record/1505597","pdf_url":null,"source":{"id":"https://openalex.org/S4306402195","display_name":"CERN Document Server (European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069029403","display_name":"Rajat P. Garg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajat P. Garg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074323778","display_name":"Illya Sharapov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Illya Sharapov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.481,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.7438671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/performance-optimization","display_name":"performance optimization","score":0.6759999990463257},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"high-performance computing","score":0.7509999871253967},{"id":"https://openalex.org/keywords/solaris","display_name":"Solaris","score":0.7179999947547913},{"id":"https://openalex.org/keywords/ultrasparc","display_name":"UltraSPARC","score":0.8180000185966492},{"id":"https://openalex.org/keywords/compiler-optimization","display_name":"compiler optimization","score":0.6830000281333923},{"id":"https://openalex.org/keywords/profiling","display_name":"profiling","score":0.5},{"id":"https://openalex.org/keywords/program-timing","display_name":"program timing","score":0.4189999997615814},{"id":"https://openalex.org/keywords/hardware-counters","display_name":"hardware counters","score":0.5559999942779541},{"id":"https://openalex.org/keywords/parallel-programming","display_name":"parallel programming","score":0.3330000042915344},{"id":"https://openalex.org/keywords/pragma","display_name":"pragma","score":0.3919999897480011},{"id":"https://openalex.org/keywords/memory-alignment","display_name":"memory alignment","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966943979263306},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.6635531187057495},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6432098150253296},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5519801378250122},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5485672354698181},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.5362754464149475},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4437861442565918},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3955308794975281},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32721424102783203}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:cds.cern.ch:1505597","doi":null,"is_oa":false,"landing_page_url":"http://cds.cern.ch/record/1505597","pdf_url":null,"source":{"id":"https://openalex.org/S4306402195","display_name":"CERN Document Server (European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:1587796446","doi":null,"is_oa":false,"landing_page_url":"http://ci.nii.ac.jp/ncid/BA58860438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W638672877","https://openalex.org/W2348424321","https://openalex.org/W4382052962","https://openalex.org/W2186149041","https://openalex.org/W2441203882","https://openalex.org/W1522687222","https://openalex.org/W4254755508","https://openalex.org/W7100856520","https://openalex.org/W35315038","https://openalex.org/W3137783668"],"abstract_inverted_index":{"Acknowledgments.":[0],"Preface.":[1],"Who":[2],"Should":[3],"Read":[4],"This":[5,8],"Book.":[6],"How":[7],"Book":[9],"Is":[10],"Organized.":[11],"Additional":[12,89],"Resources.":[13],"Code":[14,80,91,179,338],"Examples.":[15],"Typographical":[16],"Conventions.":[17],"I.":[18],"GETTING":[19],"STARTED.":[20],"1.":[21],"Introduction.":[22],"Performance":[23,283,478,491,524,538,637,651,673,794],"Components.":[24],"Hardware.":[25,749],"Software.":[26,66],"Optimization":[27,218,548,599,666],"Process":[28,157,164,693],"Overview.":[29,190,286,444],"Serial":[30],"Optimization.":[31,33,284,339,404],"Parallel":[32,438,445,448,451,477,485,490,511,537,628,649],"2.":[34],"Overview":[35,340],"of":[36,192,209,292,341,348,521,549,589,592,600,667,745,751,755,775,816],"Sun":[37,51,58,193,196,608,650,684,697,714],"UltraSPARC":[38,756,759,764,767,770,776],"Solaris":[39,55,296,566],"Platforms.":[40],"UltraSPARC-Based":[41,47,49,349],"Desktop":[42],"and":[43,60,96,104,108,146,158,199,242,246,261,280,288,301,317,327,333,380,407,429,487,503,541,575,580,647,672,688,704,721,725,748,761],"Server":[44],"Product":[45],"Line.":[46],"Workstations.":[48],"Servers.":[50],"Technical":[52],"Compute":[53],"Farm.":[54],"Operating":[56,567],"Environment.":[57,510,568],"WorkShop":[59],"Forte":[61,154,494,806],"Developer":[62,155,495,807],"Tools.":[63,82,93,127,130,142,161,163,166,169,174,480,497,514,543],"HPC":[64],"ClusterTools":[65],"Summary.":[67,113,184,229,277,335,401,432,475,546,597,664,730],"3.":[68],"Application":[69],"Development":[70,73,95],"on":[71,427,441,525],"Solaris.":[72,442],"Basics.":[74,814],"Standards":[75],"Conformance.":[76],"Binary":[77,237],"Compatibility.":[78],"Source":[79,90,337],"Verification":[81],"Checking":[83,86],"C":[84,107,399],"Programs.":[85,88,395,400,552,669,691],"Fortran":[87,98,102,105,394,621,661,809],"Analysis":[92,254,275],"64-bit":[94,214,658],"Porting.":[97,99],"Language":[100],"Interoperability.":[101],"95":[103,622,810],"77.":[106],"Fortran.":[109],"Linking":[110,285,299,309,653],"Mixed":[111],"Languages.":[112],"II.":[114],"OPTIMIZING":[115,434],"SERIAL":[116],"APPLICATIONS.":[117,436],"4.":[118],"Measuring":[119,523],"Program":[120,128,135,140,486,517,631],"Performance.":[121,713,823],"Measurement":[122,126,479,481],"Methodology.":[123,482],"Benchmarking":[124],"Guidelines.":[125,203],"Timing":[129,131,134,138,483],"Entire":[132],"Program.":[133],"Portions.":[136,489],"Fine-Grained":[137],"Measurement.":[139],"Profiling":[141,143,148,151,326,504],"With":[144,149,181,418,493,507,594],"prof":[145],"gprof.":[147],"tcov.":[150],"Tools":[152,535],"in":[153,282,325,393,398,422,564,607,620,805,821],"6.":[156,230],"System":[159,167,512,706,737,742,798],"Monitoring":[160,168,173,492,513,529],"/proc":[162],"Tracing":[165],"Hardware":[170,175,533,740,792],"Counter":[171,176,534,793],"Measurements.":[172],"Overflow":[177],"Profiling.":[178],"Instrumentation":[180],"libcpc":[182],"Calls.":[183],"5.":[185],"Basic":[186,202],"Compiler":[187,232,259,456,459,603],"Optimizations.":[188,233,353,391],"Compilation":[189],"Structure":[191,291],"Compilers.":[194,197,609],"Using":[195,331,463,602],"-fast":[198],"-xtarget":[200],"Options.":[201,255],"-xarch.":[204],"Specifying":[205],"Target":[206],"Architecture.":[207],"Generation":[208],"Conditional":[210],"Move":[211],"Instructions.":[212],"Creating":[213,313],"Binaries.":[215],"-xchip.":[216],"-xO":[217],"Level.":[219],"-xinline,":[220],"-xcrossfile.":[221],"-xdepend.":[222],"-":[223],"xvector.":[224],"-xsfpconst.":[225],"-xprofile=collect,":[226],"use.":[227],"-xprefetch.":[228],"Advanced":[231],"IEEE":[234],"Floating-Point":[235],"Arithmetic.":[236],"Storage":[238],"Format.":[239],"Trap":[240],"Handling":[241],"-ftrap.":[243],"Gradual":[244],"Underflow":[245],"-fns.":[247],"-fsimple.":[248],"-dalign.":[249],"-xsafe=":[250],"mem.":[251],"Pointer":[252,273,396],"Alias":[253,274],"-xrestrict.":[256],"-xalias_level.":[257],"-stackvar.":[258],"Directives":[260],"Pragmas.":[262,276],"pragma":[263,265,267,269,271],"pipeloop.":[264],"opt.":[266],"prefetch.":[268],"pack.":[270],"align.":[272],"7.":[278],"Linker":[279,297,307,319,324],"Libraries":[281],"Static":[287,300],"Dynamic":[289,302,692],"Linking.":[290],"an":[293],"ELF":[294],"Binary.":[295],"Usage.":[298],"Libraries.":[303,312,315,330],"Weak":[304],"Symbol":[305],"Binding.":[306],"Mapfiles.":[308],"Optimized":[310,708],"Math":[311],"Architecture-Specific":[314],"$PLATFORM":[316],"$ISALIST":[318],"Tokens.":[320],"$ORIGIN":[321],"Token.":[322],"Runtime":[323,612,656],"Debugging.":[328],"Interposing":[329],"LD_PROFILE":[332],"LD_DEBUG.":[334],"8.":[336],"Memory":[342,344,346,351,364,643],"Hierarchy.":[343],"Levels.":[345],"Organization":[347],"Systems.":[350],"Hierarchy":[352],"Cache":[354,357,383],"Blocking.":[355],"Reducing":[356,359],"Conflicts.":[358],"TLB":[360],"Misses.":[361],"Page-Coloring":[362],"Effects.":[363],"Bank":[365],"Interleaving.":[366],"Inlining":[367],"Assembly":[368],"Templates.":[369],"Optimal":[370],"Data":[371,376,577,633,641],"Alignment.":[372,377,385],"Restructuring":[373],"for":[374,536,555],"Better":[375],"Double-Word":[378],"Load":[379],"Store":[381],"Generation.":[382],"Line":[384],"Preventing":[386],"Register":[387],"Window":[388],"Overflow.":[389],"Aliasing":[390,392,397],"9.":[402],"Loop":[403,405,409,411,413,415,679],"Unrolling":[406],"Tiling.":[408],"Interchange.":[410],"Fusion.":[412],"Fission.":[414],"Peeling.":[416],"Loops":[417],"Conditionals.":[419],"Strength":[420],"Reduction":[421],"Loops.":[423],"Division":[424],"Replacement.":[425],"Operations":[426],"Complex":[428],"Real":[430],"Operands.":[431],"III.":[433],"PARALLEL":[435],"10.":[437],"Processing":[439],"Models":[440,554,671],"Parallelization":[443,605,610,680],"Scalability":[446],"Concepts.":[447],"Architectural":[449],"Models.":[450,453,455,466,474,570],"Programming":[452,553,625,670],"Multithreading":[454,462,563],"Auto-Parallelization.":[457],"OpenMP":[458,618,624,636,646,726],"Directives.":[460],"Explicit":[461,616],"P-threads.":[464,648],"Multiprocessing":[465],"UNIX":[467],"fork/exec":[468],"Model.":[469,472,558,560,562,611],"MPI":[470,505,685,690,695,698,724],"Message-Passing":[471,668],"Hybrid":[473,722,728],"11.":[476],"a":[484,516,519,526,825,830,835],"Its":[488],"6":[496,808],"Trace":[498],"Normal":[499],"Form":[500],"Utilities.":[501],"Analyzing":[502],"Programs":[506,601],"the":[508,565,654],"Prism":[509],"Binding":[515],"to":[518,837],"Set":[520],"Processors.":[522,763],"Per-CPU":[527],"Basis.":[528],"Kernel":[530],"Lock":[531],"Statistics.":[532],"Monitoring.":[539],"cpustat":[540],"cputrack":[542],"busstat":[544],"Tool.":[545],"12.":[547],"Explicitly":[550],"Threaded":[551,572],"Multithreading.":[556],"Master-Slave":[557],"Worker-Crew":[559],"Pipeline":[561,677],"Thread":[569,582,585],"Compiling":[571],"Applications.":[573],"True":[574],"False":[576],"Sharing.":[578],"Synchronization":[579,639],"Locking.":[581],"Stack":[583],"Size.":[584],"Creation":[586],"Issues.":[587,640,657],"Pool":[588,591],"Threads.":[590],"Threads":[593],"Spin":[595],"Locks.":[596],"13.":[598],"Parallelization.":[604,615,617],"Support":[606,619,804],"Settings.":[613],"Automatic":[614],"Compiler.":[623,811],"Styles.":[626],"Section":[627],"Style.":[629,635],"Single":[630],"Multiple":[632],"(SPMD)":[634],"Considerations.":[638,674],"Scoping.":[642],"Bandwidth":[644],"Requirement.":[645],"Library.":[652,655,718],"Integer":[659],"Arguments.":[660],"SUNPERF":[662],"Module.":[663],"14.":[665],"Workload":[675],"Distribution.":[676],"Method.":[678],"Methods.":[681],"Communication":[682],"Metrics.":[683,795],"Implementation.":[686],"Building":[687],"Running":[689],"Management.":[694],"I/O.":[696],"Environment":[699],"Variables.":[700],"Diagnostic":[701],"Information.":[702],"Dedicated":[703],"Timeshared":[705],"Execution.":[707],"Collectives.":[709],"Point-to-Point":[710],"Communication.":[711],"General":[712],"Scalable":[715],"Scientific":[716],"Subroutine":[717],"MPI,":[719],"OpenMP,":[720],"Approaches.":[723,727],"Approach.":[729],"IV.":[731],"APPENDICES.":[732],"A.":[733],"Commands":[734],"That":[735],"Identify":[736],"Configuration":[738],"Parameters.":[739,741],"Configuration.":[743],"Parameters":[744],"Installed":[746],"Software":[747],"Summary":[750],"Commands.":[752],"B.":[753],"Architecture":[754,774,781],"Microprocessor":[757],"Family.":[758,778],"I":[760],"II":[762],"III":[765],"Processor.":[766,769,772],"IIi":[768],"IIe":[771],"C.":[773],"Interconnect":[777],"Ultra":[779],"Port":[780],"Interconnect.":[782,784,788,790],"Gigaplane":[783,785],"XB":[786],"Crossbar":[787],"Fireplane":[789],"D.":[791],"CPU":[796],"Counters.":[797,800],"ASIC":[799],"E.":[801],"Interval":[802,812],"Arithmetic":[803,813],"Solution":[815],"Nonlinear":[817],"Problems.":[818],"F.":[819],"Differences":[820],"I/O":[822],"Reading":[824,829],"File":[826,831,836],"with":[827,832],"read/lseek.":[828],"fread/fseek.":[833],"Mapping":[834],"Memory.":[838],"References.":[839],"Index.":[840]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
