{"id":"https://openalex.org/W3172225290","doi":"https://doi.org/10.1145/3447818.3460380","title":"Topology-aware optimizations for multi-GPU ptychographic image reconstruction","display_name":"Topology-aware optimizations for multi-GPU ptychographic image reconstruction","publication_year":2021,"publication_date":"2021-06-03","ids":{"openalex":"https://openalex.org/W3172225290","doi":"https://doi.org/10.1145/3447818.3460380","mag":"3172225290"},"language":"en","primary_location":{"id":"doi:10.1145/3447818.3460380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447818.3460380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052001478","display_name":"Xiaodong Yu","orcid":"https://orcid.org/0000-0001-6244-1264"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Yu","raw_affiliation_strings":["Argonne National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038566298","display_name":"Tekin Bi\u00e7er","orcid":"https://orcid.org/0000-0002-8428-5159"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tekin Bicer","raw_affiliation_strings":["Argonne National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068373159","display_name":"Rajkumar Kettimuthu","orcid":"https://orcid.org/0000-0002-0046-9883"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajkumar Kettimuthu","raw_affiliation_strings":["Argonne National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["Argonne National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":13.0979,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.99496403,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"354","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11183","display_name":"Advanced X-ray Imaging Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11183","display_name":"Advanced X-ray Imaging Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10378","display_name":"Advanced MRI Techniques and Applications","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8527194261550903},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.7313633561134338},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5538522005081177},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.5275055170059204},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.4451349675655365},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4386962056159973},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3776998221874237},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1755489706993103},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.14535900950431824},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.09795078635215759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8527194261550903},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.7313633561134338},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5538522005081177},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.5275055170059204},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.4451349675655365},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4386962056159973},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3776998221874237},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1755489706993103},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.14535900950431824},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.09795078635215759},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447818.3460380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447818.3460380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W193807271","https://openalex.org/W1980938256","https://openalex.org/W1988307172","https://openalex.org/W1992432622","https://openalex.org/W1993193439","https://openalex.org/W1996693511","https://openalex.org/W2009741028","https://openalex.org/W2022462155","https://openalex.org/W2025388037","https://openalex.org/W2029674034","https://openalex.org/W2030907924","https://openalex.org/W2084750801","https://openalex.org/W2133665775","https://openalex.org/W2149658259","https://openalex.org/W2165161875","https://openalex.org/W2165505098","https://openalex.org/W2208150243","https://openalex.org/W2223956994","https://openalex.org/W2382024644","https://openalex.org/W2422616509","https://openalex.org/W2480699195","https://openalex.org/W2519702500","https://openalex.org/W2564118258","https://openalex.org/W2580688187","https://openalex.org/W2581090187","https://openalex.org/W2612387305","https://openalex.org/W2618550415","https://openalex.org/W2621889996","https://openalex.org/W2772629285","https://openalex.org/W2786496600","https://openalex.org/W2787701215","https://openalex.org/W2791746987","https://openalex.org/W2898319404","https://openalex.org/W2903901007","https://openalex.org/W2907753541","https://openalex.org/W2922391227","https://openalex.org/W2926767350","https://openalex.org/W2954988505","https://openalex.org/W2963875241","https://openalex.org/W2971519680","https://openalex.org/W2972776862","https://openalex.org/W2980029740","https://openalex.org/W2980047166","https://openalex.org/W2985814104","https://openalex.org/W3011398701","https://openalex.org/W3039165326","https://openalex.org/W3042378002","https://openalex.org/W3043494828","https://openalex.org/W3043803354","https://openalex.org/W3101708369","https://openalex.org/W3103417206","https://openalex.org/W3105462645","https://openalex.org/W3106011734","https://openalex.org/W3130398772","https://openalex.org/W4245208434"],"related_works":["https://openalex.org/W4385894176","https://openalex.org/W2347371119","https://openalex.org/W2612768808","https://openalex.org/W3131402800","https://openalex.org/W2593071546","https://openalex.org/W2388965158","https://openalex.org/W2808480228","https://openalex.org/W2366201982","https://openalex.org/W2805641962","https://openalex.org/W1599154403"],"abstract_inverted_index":{"Ptychography":[0],"is":[1],"an":[2],"advanced":[3],"high-resolution":[4,22],"X-ray":[5],"imaging":[6],"technique":[7],"that":[8,53,82,167,178],"can":[9,104],"generate":[10],"extremely":[11],"large":[12],"datasets.":[13],"Ptychographic":[14],"reconstruction":[15,41],"transforms":[16],"reciprocal":[17],"space":[18],"experimental":[19],"data":[20,106,137,147],"to":[21,31,61,124,188],"2D":[23],"real-space":[24],"images.":[25],"GPUs":[26],"have":[27],"been":[28],"used":[29],"extensively":[30],"meet":[32],"the":[33,37,126,169,183],"computational":[34],"requirements":[35],"of":[36,85,114,168],"reconstruction.":[38],"Generic":[39],"multi-GPU":[40],"solutions":[42],"use":[43],"common":[44,67],"communication":[45,99,142,192],"topologies,":[46],"such":[47],"as":[48],"P2P":[49,171],"graph":[50],"and":[51,58,90,101,112,122,129,144,149,155,159,162,172,185,190,193],"ring,":[52],"are":[54,83],"provided":[55],"by":[56],"MPI":[57],"NCCL":[59],"libraries,":[60],"establish":[62],"inter-GPU":[63],"communications.":[64],"However,":[65],"these":[66],"topologies":[68],"assume":[69],"homogeneous":[70],"physical":[71,102],"links":[72],"between":[73,97],"GPUs,":[74],"resulting":[75],"in":[76],"sub-optimal":[77],"performance":[78,165],"on":[79],"heterogeneous":[80],"configurations":[81],"composed":[84],"both":[86],"high-":[87],"(e.g.,":[88,92],"NVLink)":[89],"low-speed":[91],"PCIe)":[93],"interconnects.":[94],"This":[95],"mismatch":[96,128],"application-level":[98],"topology":[100],"interconnection":[103],"cause":[105],"transfer":[107],"congestion,":[108],"inefficient":[109],"memory":[110],"access,":[111],"under-utilization":[113],"network":[115],"resources.":[116],"Here":[117],"we":[118],"present":[119],"topology-aware":[120,136],"designs":[121],"optimizations":[123,156,180],"address":[125],"aforementioned":[127],"boost":[130],"end-to-end":[131,194],"application":[132,195],"performance.":[133],"We":[134,151],"introduce":[135],"splitting,":[138],"propose":[139],"a":[140],"novel":[141],"topology,":[143],"incorporate":[145],"asynchronous":[146],"movement":[148],"computation.":[150],"evaluate":[152],"our":[153,179],"design":[154],"using":[157],"real":[158],"artificial":[160],"datasets":[161],"compare":[163],"its":[164],"with":[166],"direct":[170],"NCCL-based":[173],"approaches.":[174],"The":[175],"results":[176],"show":[177],"always":[181],"outperform":[182],"counterparts":[184],"achieve":[186],"up":[187],"5.13\u00d7":[189],"1.63\u00d7":[191],"speedups,":[196],"respectively.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}