{"id":"https://openalex.org/W4311300562","doi":"https://doi.org/10.1145/3565387.3565443","title":"An Accelerated First Principle Method Implemented on IntelGPU","display_name":"An Accelerated First Principle Method Implemented on IntelGPU","publication_year":2022,"publication_date":"2022-10-21","ids":{"openalex":"https://openalex.org/W4311300562","doi":"https://doi.org/10.1145/3565387.3565443"},"language":"en","primary_location":{"id":"doi:10.1145/3565387.3565443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3565387.3565443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 6th International Conference on Computer Science and Application Engineering","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/A5024359069","display_name":"Le Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Le Xu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085758579","display_name":"Hong An","orcid":"https://orcid.org/0000-0002-3900-3722"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong An","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024359069"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13567839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/porting","display_name":"Porting","score":0.9245169758796692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8660967946052551},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5642209053039551},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5122281908988953},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49773409962654114},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4905218482017517},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.4843076765537262},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4608798027038574},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4448966085910797},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3877788484096527},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.34979167580604553},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.10922509431838989},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.08606505393981934}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.9245169758796692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8660967946052551},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5642209053039551},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5122281908988953},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49773409962654114},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4905218482017517},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4843076765537262},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4608798027038574},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4448966085910797},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3877788484096527},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.34979167580604553},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.10922509431838989},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08606505393981934},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3565387.3565443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3565387.3565443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 6th International Conference on Computer Science and Application Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1245637661","https://openalex.org/W1967853451","https://openalex.org/W2064160620","https://openalex.org/W2104757784","https://openalex.org/W2165768408","https://openalex.org/W2334930320","https://openalex.org/W2617890897","https://openalex.org/W2756519801","https://openalex.org/W2964323977","https://openalex.org/W3007178273","https://openalex.org/W3046816984","https://openalex.org/W3174757733","https://openalex.org/W3175770118","https://openalex.org/W4200216396","https://openalex.org/W4206836072","https://openalex.org/W4225263328","https://openalex.org/W4226024494","https://openalex.org/W4244796164","https://openalex.org/W4285513601"],"related_works":["https://openalex.org/W2621501241","https://openalex.org/W2208757713","https://openalex.org/W3177128669","https://openalex.org/W2991848348","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W3037515626","https://openalex.org/W4394633758","https://openalex.org/W2502510154"],"abstract_inverted_index":{"High":[0],"performance":[1],"computing":[2],"has":[3],"been":[4],"developing":[5],"rapidly":[6],"over":[7,213],"the":[8,75,104,114,118,123,202],"past":[9],"decades.":[10],"Nowadays,":[11],"most":[12,53],"super":[13],"computers":[14],"are":[15,34,56,193],"still":[16],"using":[17],"traditional":[18,214],"pure":[19],"CPU":[20],"architecture":[21],"or":[22],"very":[23,36,58],"limited":[24],"heterogeneous":[25,54,152],"devices":[26,33,55],"like":[27],"Nvidia":[28],"GPU.":[29],"Many":[30],"other":[31],"vendor's":[32],"also":[35],"reliable,":[37],"such":[38],"as":[39],"Intel":[40,85,88,132,197],"GPU,":[41,180],"which":[42,134],"was":[43],"first":[44],"introduced":[45],"few":[46],"years":[47],"ago.":[48],"As":[49],"programming":[50],"methods":[51,168],"on":[52,140,195],"always":[57],"strongly":[59],"restricted":[60],"by":[61],"vendors,":[62],"porting":[63,105],"from":[64],"one":[65],"platform":[66],"to":[67,84,128,131,137,171],"another":[68,210],"is":[69],"usually":[70],"difficult":[71],"and":[72,87,110,155,181,201],"time-costing.":[73],"With":[74],"great":[76],"help":[77],"of":[78,107,126,167,169],"ONEAPI,":[79,133],"applications":[80,130],"can":[81],"be":[82],"ported":[83],"GPU":[86],"FPGA":[89],"with":[90],"almost":[91],"zero":[92],"cost,":[93],"rather":[94],"than":[95,187],"rebuild":[96],"kernel":[97],"codes":[98],"in":[99,117,159,179],"CUDA.":[100],"This":[101],"paper":[102],"demonstrates":[103],"work":[106],"an":[108,150,209],"important":[109],"widely":[111],"used":[112],"application,":[113],"GW":[115],"approximation":[116],"First":[119],"Principle.":[120],"We":[121],"introduce":[122,149],"whole":[124],"workflow":[125],"how":[127,170],"port":[129],"allows":[135],"us":[136],"execute":[138],"application":[139],"all":[141,146,188],"platforms.":[142],"To":[143],"fully":[144],"use":[145],"devices,":[147],"we":[148,163],"automatic":[151],"device":[153],"sneaking":[154],"workload":[156,173],"balance":[157,174],"method":[158,186,207],"this":[160],"paper.":[161],"Moreover,":[162],"develop":[164],"a":[165,183],"series":[166],"achieve":[172],"for":[175],"each":[176],"single":[177],"core":[178],"design":[182],"better":[184],"reduction":[185],"previous":[189],"works.":[190],"The":[191],"tests":[192],"taken":[194],"2":[196],"Xe-HP":[198],"ATS-P":[199],"GPUs,":[200],"results":[203],"show":[204],"that":[205],"our":[206],"achieves":[208],"65x":[211],"acceleration":[212],"OpenMP":[215],"+":[216],"MPI":[217],"implementation.":[218]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}