{"id":"https://openalex.org/W4413458368","doi":"https://doi.org/10.1145/3725789.3725797","title":"GROMACS on AMD GPU-Based HPC Platforms: Using SYCL for Performance and Portability","display_name":"GROMACS on AMD GPU-Based HPC Platforms: Using SYCL for Performance and Portability","publication_year":2024,"publication_date":"2024-05-05","ids":{"openalex":"https://openalex.org/W4413458368","doi":"https://doi.org/10.1145/3725789.3725797"},"language":"en","primary_location":{"id":"doi:10.1145/3725789.3725797","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725789.3725797","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Cray User Group","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3725789.3725797","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029901108","display_name":"Andrey Alekseenko","orcid":"https://orcid.org/0000-0003-4906-7241"},"institutions":[{"id":"https://openalex.org/I2800139495","display_name":"Science for Life Laboratory","ror":"https://ror.org/04ev03g22","country_code":"SE","type":"facility","lineage":["https://openalex.org/I2800139495"]},{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Andrey Alekseenko","raw_affiliation_strings":["KTH Royal Institute of Technology, Science for Life Laboratory, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-4906-7241","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Science for Life Laboratory, Stockholm, Sweden","institution_ids":["https://openalex.org/I2800139495","https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009705616","display_name":"Szil\u00e1rd P\u00e1ll","orcid":"https://orcid.org/0000-0003-0603-5514"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Szil\u00e1rd P\u00e1ll","raw_affiliation_strings":["KTH Royal Institute of Technology, PDC Center for High Performance Computing, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-0603-5514","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, PDC Center for High Performance Computing, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008875190","display_name":"Erik Lindahl","orcid":"https://orcid.org/0000-0002-2734-2794"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]},{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Erik Lindahl","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden and Stockholm University, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-2734-2794","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden and Stockholm University, Stockholm, Sweden","institution_ids":["https://openalex.org/I161593684","https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.994700014591217,"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/software-portability","display_name":"Software portability","score":0.9006884098052979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7951635122299194},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5745094418525696},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5432819128036499},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5159705281257629},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.514951765537262},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.38470423221588135},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3627815842628479},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3444354832172394},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3296584486961365},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.10567083954811096}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.9006884098052979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951635122299194},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5745094418525696},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5432819128036499},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5159705281257629},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.514951765537262},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38470423221588135},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3627815842628479},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3444354832172394},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3296584486961365},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.10567083954811096}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3725789.3725797","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725789.3725797","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Cray User Group","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-351148","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-351148","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1886363/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3725789.3725797","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725789.3725797","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Cray User Group","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320317161","display_name":"Swedish e-Science Research Centre","ror":"https://ror.org/01e59yk92"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1031578623","https://openalex.org/W1624860839","https://openalex.org/W1895692106","https://openalex.org/W1966078827","https://openalex.org/W2150981663","https://openalex.org/W2313116527","https://openalex.org/W2788386530","https://openalex.org/W2790442679","https://openalex.org/W2921098500","https://openalex.org/W3017538311","https://openalex.org/W3035762603","https://openalex.org/W3036255981","https://openalex.org/W3046751266","https://openalex.org/W3092054218","https://openalex.org/W3103156673","https://openalex.org/W3157598604","https://openalex.org/W4225263328","https://openalex.org/W4283464776","https://openalex.org/W4294008856","https://openalex.org/W4319069056","https://openalex.org/W4362675245","https://openalex.org/W4362675404","https://openalex.org/W4387318976","https://openalex.org/W4388581070","https://openalex.org/W4388870365"],"related_works":["https://openalex.org/W3020739840","https://openalex.org/W2913998709","https://openalex.org/W3177128669","https://openalex.org/W4386875822","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538"],"abstract_inverted_index":{"GROMACS":[0,32,61,102,227],"is":[1,127,174,176,215,248],"a":[2,9,17,41,55,66,76,80,128,255,279],"widely-used":[3],"molecular":[4],"dynamics":[5],"software":[6],"package":[7],"with":[8,154,240,264,271],"focus":[10],"on":[11,92,165,225,236,275],"performance,":[12],"portability,":[13],"and":[14,28,50,70,99,125,168,192,212,261],"maintainability":[15],"across":[16,206],"broad":[18],"range":[19,208],"of":[20,45,200,209,222,258,267],"platforms.":[21],"Thanks":[22],"to":[23,87,113,139,146],"its":[24],"early":[25],"algorithmic":[26],"redesign":[27],"flexible":[29],"heterogeneous":[30],"parallelization,":[31],"has":[33,108],"successfully":[34],"harnessed":[35],"GPU":[36,96,230,281],"accelerators":[37],"for":[38,54,79,90,119,133,189,228],"more":[39],"than":[40],"decade.With":[42],"the":[43,60,101,105,110,143,187,207,220,265,272],"diversification":[44],"accelerator":[46],"platforms":[47,231],"in":[48,117],"HPC":[49,95,121,273],"no":[51],"obvious":[52],"choice":[53,86],"well-suited":[56],"multi-vendor":[57],"programming":[58,82,134],"model,":[59,83],"project":[62],"found":[63],"itself":[64],"at":[65],"crossroads.":[67],"The":[68],"performance":[69,183,205,235,252,263],"portability":[71,160,247],"requirements,":[72],"as":[73,75,196,198,278],"well":[74],"strong":[77,190],"preference":[78],"standards-based":[81],"motivated":[84],"our":[85,223],"use":[88],"SYCL":[89,106,162,277],"production":[91],"both":[93],"new":[94],"platforms:":[97],"AMD":[98,115,229],"Intel.Since":[100],"2022":[103],"release,":[104],"backend":[107],"been":[109],"primary":[111],"means":[112],"target":[114,147],"GPUs":[116,148],"preparation":[118],"exascale":[120],"architectures":[122],"like":[123],"LUMI":[124],"Frontier.SYCL":[126],"cross-platform,":[129],"royalty-free,":[130],"C++17-based":[131],"standard":[132],"hardware":[135],"accelerators,":[136],"from":[137,149],"embedded":[138],"HPC.It":[140],"allows":[141],"using":[142,232,276],"same":[144],"code":[145],"all":[150],"three":[151],"major":[152,159,251],"vendors":[153],"minimal":[155],"specialization,":[156],"which":[157],"offers":[158],"benefits.While":[161],"implementations":[163],"build":[164],"native":[166],"compilers":[167],"runtimes,":[169],"whether":[170],"such":[171],"an":[172],"approach":[173],"performant":[175],"not":[177],"immediately":[178],"evident.Biomolecular":[179],"simulations":[180],"have":[181],"challenging":[182],"characteristics:":[184],"latency":[185],"sensitivity,":[186],"need":[188],"scaling,":[191],"typical":[193],"iteration":[194],"times":[195],"short":[197],"hundreds":[199],"microseconds.":[201],"Hence,":[202],"obtaining":[203],"good":[204],"problem":[210],"sizes":[211],"scaling":[213],"regimes":[214],"particularly":[216],"challenging.Here,":[217],"we":[218],"share":[219],"results":[221],"work":[224],"readying":[226],"SYCL,and":[233],"demonstrate":[234],"Cray":[237],"EX235a":[238],"machines":[239],"MI250X":[241],"accelerators.":[242],"Our":[243],"findings":[244],"illustrate":[245],"that":[246],"possible":[249],"without":[250],"compromises.We":[253],"provide":[254],"detailed":[256],"analysis":[257],"node-level":[259],"kernel":[260],"runtime":[262],"aim":[266],"sharing":[268],"best":[269],"practices":[270],"community":[274],"performance-portable":[280],"framework.":[282]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
