{"id":"https://openalex.org/W4416004316","doi":"https://doi.org/10.1145/3731599.3767518","title":"MT4G: A Tool for Reliable Auto-Discovery of NVIDIA and AMD GPU Compute and Memory Topologies","display_name":"MT4G: A Tool for Reliable Auto-Discovery of NVIDIA and AMD GPU Compute and Memory Topologies","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004316","doi":"https://doi.org/10.1145/3731599.3767518"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767518","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767518","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093240775","display_name":"Stepan Vanecek","orcid":"https://orcid.org/0009-0008-4120-9472"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Stepan Vanecek","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"],"raw_orcid":"https://orcid.org/0009-0008-4120-9472","affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120297602","display_name":"Manuel Walter Mu\u00dfbacher","orcid":"https://orcid.org/0009-0006-9776-6994"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manuel Walter Mu\u00dfbacher","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"],"raw_orcid":"https://orcid.org/0009-0006-9776-6994","affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120297603","display_name":"Dominik Gr\u00f6\u00dfler","orcid":"https://orcid.org/0009-0006-7923-7466"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Gr\u00f6\u00dfler","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"],"raw_orcid":"https://orcid.org/0009-0006-7923-7466","affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093307321","display_name":"Urvij Saroliya","orcid":"https://orcid.org/0009-0009-0953-5048"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Urvij Saroliya","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"],"raw_orcid":"https://orcid.org/0009-0009-0953-5048","affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045289712","display_name":"Martin Schulz","orcid":"https://orcid.org/0000-0001-9013-435X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Schulz","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9013-435X","affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093240775"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35403599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1574","last_page":"1586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5066999793052673,"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":0.5066999793052673,"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/T14347","display_name":"Big Data and Digital Economy","score":0.05869999900460243,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.04610000178217888,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.6175000071525574},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.35100001096725464},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.32409998774528503},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.32330000400543213},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.31450000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.6175000071525574},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5576000213623047},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4307999908924103},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731599.3767518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767518","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.05958","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.05958","pdf_url":"https://arxiv.org/pdf/2511.05958","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767518","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1560368109","https://openalex.org/W1961751213","https://openalex.org/W1969923711","https://openalex.org/W1975684011","https://openalex.org/W1989016323","https://openalex.org/W2002555321","https://openalex.org/W2017579069","https://openalex.org/W2032010164","https://openalex.org/W2035959221","https://openalex.org/W2080609534","https://openalex.org/W2109240172","https://openalex.org/W2111876017","https://openalex.org/W2163687928","https://openalex.org/W2167334577","https://openalex.org/W2515822248","https://openalex.org/W2909693411","https://openalex.org/W2999848761","https://openalex.org/W3134495297","https://openalex.org/W4246740707","https://openalex.org/W4247848308","https://openalex.org/W4255375128","https://openalex.org/W4388581328","https://openalex.org/W4399282354"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"GPU":[1,20],"topology":[2],"is":[3,22],"essential":[4],"for":[5,14],"performance-related":[6],"tasks":[7],"in":[8],"HPC":[9],"or":[10],"AI.":[11],"Yet,":[12],"unlike":[13],"CPUs":[15],"with":[16],"tools":[17],"like":[18],"hwloc,":[19],"information":[21],"hard":[23],"to":[24],"come":[25],"by,":[26],"incomplete,":[27],"and":[28],"vendor-specific.":[29]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-07T00:00:00"}