{"id":"https://openalex.org/W4230551151","doi":"https://doi.org/10.1109/llvm-hpc.2016.007","title":"Towards Automatic HBM Allocation Using LLVM: A Case Study with Knights Landing","display_name":"Towards Automatic HBM Allocation Using LLVM: A Case Study with Knights Landing","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W4230551151","doi":"https://doi.org/10.1109/llvm-hpc.2016.007"},"language":"en","primary_location":{"id":"doi:10.1109/llvm-hpc.2016.007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/llvm-hpc.2016.007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Third Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5017736536","display_name":"Dounia Khaldi","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dounia Khaldi","raw_affiliation_strings":["Institute for Advanced Computational Science, Stony Brook University, Stony Brook, NY"],"affiliations":[{"raw_affiliation_string":"Institute for Advanced Computational Science, Stony Brook University, Stony Brook, NY","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053733660","display_name":"Barbara Chapman","orcid":"https://orcid.org/0000-0001-8449-8579"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Chapman","raw_affiliation_strings":["Institute for Advanced Computational Science, Stony Brook University, Stony Brook, NY"],"affiliations":[{"raw_affiliation_string":"Institute for Advanced Computational Science, Stony Brook University, Stony Brook, NY","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017736536"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":2.2073,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88038368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.8971061706542969},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7666991949081421},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5024034976959229},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4987194538116455},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.46194204688072205},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4551009237766266},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2197815477848053},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08665040135383606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8971061706542969},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7666991949081421},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5024034976959229},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4987194538116455},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.46194204688072205},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4551009237766266},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2197815477848053},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08665040135383606},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/llvm-hpc.2016.007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/llvm-hpc.2016.007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Third Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320331904","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33"},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W307918303","https://openalex.org/W1918785179","https://openalex.org/W1977813547","https://openalex.org/W1982205631","https://openalex.org/W1984689820","https://openalex.org/W2059843741","https://openalex.org/W2102976251","https://openalex.org/W2161172908","https://openalex.org/W2505067803","https://openalex.org/W2610316720","https://openalex.org/W3139307873","https://openalex.org/W3145506805","https://openalex.org/W3146814121","https://openalex.org/W4237977381","https://openalex.org/W4246166885","https://openalex.org/W4248722156","https://openalex.org/W6631615826","https://openalex.org/W6683502165","https://openalex.org/W6737171665"],"related_works":["https://openalex.org/W4379115841","https://openalex.org/W2083794993","https://openalex.org/W1511772879","https://openalex.org/W4394660363","https://openalex.org/W2186315912","https://openalex.org/W2248125223","https://openalex.org/W2588591308","https://openalex.org/W2127898439","https://openalex.org/W3082894236","https://openalex.org/W3195664246"],"abstract_inverted_index":{"In":[0],"this":[1,119],"paper,":[2],"we":[3,154,212,229],"introduce":[4],"a":[5,47,112,140,147,231],"new":[6,48],"LLVM":[7,68,123,192,237],"analysis,":[8],"called":[9],"Bandwidth-Critical":[10],"Data":[11],"Analysis":[12],"(BCDA),":[13],"to":[14,20,72,84,89,129,132,199,205,245],"decide":[15,85],"when":[16,201],"it":[17,196,202],"is":[18,46,137,145,185,203],"beneficial":[19,204],"allocate":[21,90,206,213],"data":[22,76,103,207,215],"in":[23,40,82,190,208,216],"High-Bandwidth":[24,43],"Memory":[25,44],"(HBM)":[26,45],"and":[27,65,77,105,108,139,194,239],"then":[28],"transform":[29,130],"allocation":[30,35],"calls":[31],"into":[32],"specific":[33],"HBM":[34,93,133,136,144,177],"calls,":[36,128],"for":[37,63,115,150,170],"increased":[38],"performance":[39,233],"parallel":[41,66],"systems.":[42],"memory":[49,80],"technology":[50],"that":[51],"features":[52],"stacked":[53],"3D":[54],"chips":[55],"on":[56,86,178,197],"processor":[57],"dies.The":[58],"well-known":[59],"SSA-based":[60],"compilation":[61],"infrastructure":[62],"sequential":[64],"languages":[67],"will":[69,124],"be":[70,168],"used":[71,75],"detect":[73,200],"frequently":[74],"patterns":[78],"of":[79,102,143,173,249],"accesses":[81],"order":[83],"which":[87],"level":[88],"the":[91,100,157,163,171,176,179,191,209,214,217,224,236,246],"data:":[92],"or":[94],"DDR.":[95],"BCDA":[96,189],"core":[97],"analysis":[98],"counts":[99],"number":[101],"uses":[104],"detects":[106],"irregular":[107],"simultaneous":[109],"accesses,":[110],"generating":[111],"priority":[113,120,225],"value":[114,121],"every":[116],"variable.":[117],"Using":[118,223],"information,":[122],"generate":[125],"memkind_alloc":[126],"function":[127],"mallocs":[131],"allocations":[134],"if":[135],"present":[138],"sufficient":[141],"size":[142],"available.As":[146],"use":[148,172],"case":[149],"validating":[151],"our":[152],"approach,":[153],"show":[155],"how":[156],"Conjugate":[158],"Gradient":[159],"(CG)":[160],"benchmark":[161],"from":[162],"NAS":[164],"Parallel":[165],"suite":[166],"can":[167],"optimized":[169],"MCDRAM,":[174],"as":[175],"Knights":[180],"Landing":[181],"Xeon":[182],"Phi":[183],"processors":[184],"called.":[186],"We":[187],"implement":[188],"compiler":[193,238,243],"apply":[195],"CG":[198],"HBM.":[210],"Then,":[211],"MCDRAM":[218],"using":[219,235,241],"hbwmalloc":[220],"library":[221],"calls.":[222],"generated":[226],"by":[227],"BCDA,":[228],"achieved":[230],"2.29\u00d7":[232],"improvement":[234],"2.33\u00d7":[240],"Intel's":[242],"compared":[244],"DDR":[247],"version":[248],"CG.":[250]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
