{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NWRTQ3ERZ3EMYAMXK2QLQSNF34","short_pith_number":"pith:NWRTQ3ER","schema_version":"1.0","canonical_sha256":"6da3386c91cec8cc019756a0b849a5df04c7fb108d98dca728edea47fc3b137b","source":{"kind":"arxiv","id":"2501.05938","version":1},"attestation_state":"computed","paper":{"title":"ML-Based Optimum Number of CUDA Streams for the GPU Implementation of the Tridiagonal Partition Method","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Milena Veneva, Toshiyuki Imamura","submitted_at":"2025-01-10T13:02:22Z","abstract_excerpt":"This paper presents a heuristic for finding the optimum number of CUDA streams by using tools common to the modern AI-oriented approaches and applied to the parallel partition algorithm. A time complexity model for the GPU realization of the partition method is built. Further, a refined time complexity model for the partition algorithm being executed on multiple CUDA streams is formulated. Computational experiments for different SLAE sizes are conducted, and the optimum number of CUDA streams for each of them is found empirically. Based on the collected data a model for the sum of the times fo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.05938","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2025-01-10T13:02:22Z","cross_cats_sorted":[],"title_canon_sha256":"455acf53dfaba991bbd6da5a726b628b3ab4470bfed754ed73b5142ac091471c","abstract_canon_sha256":"c22ae5e79f3b8f81684bfddbee757d859741a43d12eb94b1f7dbf373df64c54e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:41.219428Z","signature_b64":"jJM67JG7WzBmstoK6O66yOvhCVe2gn+c7vs0GJzLAfbx4yfwczAwIg7sxRVjdZmrjRkvAlKgc/Qu1Zg/h53mDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6da3386c91cec8cc019756a0b849a5df04c7fb108d98dca728edea47fc3b137b","last_reissued_at":"2026-05-22T01:03:41.218582Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:41.218582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ML-Based Optimum Number of CUDA Streams for the GPU Implementation of the Tridiagonal Partition Method","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Milena Veneva, Toshiyuki Imamura","submitted_at":"2025-01-10T13:02:22Z","abstract_excerpt":"This paper presents a heuristic for finding the optimum number of CUDA streams by using tools common to the modern AI-oriented approaches and applied to the parallel partition algorithm. A time complexity model for the GPU realization of the partition method is built. Further, a refined time complexity model for the partition algorithm being executed on multiple CUDA streams is formulated. Computational experiments for different SLAE sizes are conducted, and the optimum number of CUDA streams for each of them is found empirically. Based on the collected data a model for the sum of the times fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05938","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.05938/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.05938","created_at":"2026-05-22T01:03:41.218695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05938v1","created_at":"2026-05-22T01:03:41.218695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05938","created_at":"2026-05-22T01:03:41.218695+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWRTQ3ERZ3EM","created_at":"2026-05-22T01:03:41.218695+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWRTQ3ERZ3EMYAMX","created_at":"2026-05-22T01:03:41.218695+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWRTQ3ER","created_at":"2026-05-22T01:03:41.218695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.27351","citing_title":"ML-Based Optimum Sub-system Size Heuristic for the GPU Implementation of the Tridiagonal Partition Method","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34","json":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34.json","graph_json":"https://pith.science/api/pith-number/NWRTQ3ERZ3EMYAMXK2QLQSNF34/graph.json","events_json":"https://pith.science/api/pith-number/NWRTQ3ERZ3EMYAMXK2QLQSNF34/events.json","paper":"https://pith.science/paper/NWRTQ3ER"},"agent_actions":{"view_html":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34","download_json":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34.json","view_paper":"https://pith.science/paper/NWRTQ3ER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05938&json=true","fetch_graph":"https://pith.science/api/pith-number/NWRTQ3ERZ3EMYAMXK2QLQSNF34/graph.json","fetch_events":"https://pith.science/api/pith-number/NWRTQ3ERZ3EMYAMXK2QLQSNF34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34/action/storage_attestation","attest_author":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34/action/author_attestation","sign_citation":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34/action/citation_signature","submit_replication":"https://pith.science/pith/NWRTQ3ERZ3EMYAMXK2QLQSNF34/action/replication_record"}},"created_at":"2026-05-22T01:03:41.218695+00:00","updated_at":"2026-05-22T01:03:41.218695+00:00"}