{"id":"https://openalex.org/W2761533866","doi":"https://doi.org/10.1145/3132402.3132435","title":"Evaluating hybrid memory cube infrastructure to support high-performance sparse algorithms","display_name":"Evaluating hybrid memory cube infrastructure to support high-performance sparse algorithms","publication_year":2017,"publication_date":"2017-10-02","ids":{"openalex":"https://openalex.org/W2761533866","doi":"https://doi.org/10.1145/3132402.3132435","mag":"2761533866"},"language":"en","primary_location":{"id":"doi:10.1145/3132402.3132435","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132402.3132435","pdf_url":null,"source":{"id":"https://openalex.org/S4306524191","display_name":"Proceedings of the International Symposium on Memory Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Symposium on Memory Systems","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/A5025724246","display_name":"Kartikay Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kartikay Garg","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074170797","display_name":"Jeffrey Young","orcid":"https://orcid.org/0000-0001-9841-4057"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Young","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025724246"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14704131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"112","last_page":"114"},"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":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991999864578247,"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":0.8519980311393738},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7619441747665405},{"id":"https://openalex.org/keywords/out-of-core-algorithm","display_name":"Out-of-core algorithm","score":0.5839359164237976},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5677928924560547},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.5391033887863159},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.4778275489807129},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4687258005142212},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4621162712574005},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.45472800731658936},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4330996870994568},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4290737509727478},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37870389223098755},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37557339668273926},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2722221314907074},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09460258483886719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519980311393738},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7619441747665405},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.5839359164237976},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5677928924560547},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5391033887863159},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4778275489807129},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4687258005142212},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4621162712574005},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.45472800731658936},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4330996870994568},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4290737509727478},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37870389223098755},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37557339668273926},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2722221314907074},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09460258483886719},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3132402.3132435","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132402.3132435","pdf_url":null,"source":{"id":"https://openalex.org/S4306524191","display_name":"Proceedings of the International Symposium on Memory Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Symposium on Memory Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1587659039","https://openalex.org/W2048044823","https://openalex.org/W2125320251","https://openalex.org/W2141331848"],"related_works":["https://openalex.org/W233983175","https://openalex.org/W1944865817","https://openalex.org/W2355089277","https://openalex.org/W2312486021","https://openalex.org/W2560781234","https://openalex.org/W2081192312","https://openalex.org/W2518567779","https://openalex.org/W2613275038","https://openalex.org/W1588915715","https://openalex.org/W1845197037"],"abstract_inverted_index":{"This":[0],"work":[1],"is":[2,37],"focused":[3],"on":[4,96],"analyzing":[5],"potential":[6],"performance":[7],"improvements":[8],"of":[9,41,108],"HPC":[10,25],"applications":[11],"using":[12,68],"stacked":[13,89],"memories":[14],"like":[15,44,76],"the":[16,57],"Hybrid":[17],"Memory":[18],"Cube,":[19],"or":[20],"HMC.":[21],"We":[22],"target":[23],"a":[24,38,81,87,105,113],"sparse":[26],"direct":[27],"solver":[28],"library,":[29,50],"SuperLU":[30],"[4],":[31],"that":[32,64],"performs":[33],"LU":[34],"decomposition":[35],"and":[36,73,78,116],"core":[39],"piece":[40],"simulation":[42],"codes":[43],"NIMROD":[45],"[1].":[46],"To":[47],"accelerate":[48],"this":[49],"we":[51,92],"are":[52],"interested":[53],"in":[54],"mapping":[55,97],"both":[56],"computationally":[58],"intense":[59],"Spare":[60],"Matrix-Vector":[61],"(SpMV)":[62],"kernels":[63],"can":[65],"be":[66],"implemented":[67],"matrix-matrix":[69],"multiply":[70],"(GEMM)":[71],"calls":[72],"memory-intensive":[74],"primitives":[75],"Scatter":[77],"Gather":[79],"to":[80,99],"reconfigurable":[82],"fabric":[83],"tightly":[84],"integrated":[85],"with":[86,112],"3D":[88],"memory.":[90],"Here":[91],"provide":[93],"initial":[94],"results":[95],"GEMM":[98],"OpenCL-based":[100],"devices":[101],"as":[102,104],"well":[103],"trace-driven":[106],"evaluation":[107],"SuperLU's":[109],"memory":[110],"accesses":[111],"combined":[114],"FPGA":[115],"HMC":[117],"platform.":[118]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}