{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFPP2K3TCPIRX3MAFL6TDR777Q","short_pith_number":"pith:XFPP2K3T","schema_version":"1.0","canonical_sha256":"b95efd2b7313d11bed802afd31c7fffc1875bf3635240baaa9d8b03407feed47","source":{"kind":"arxiv","id":"2407.00243","version":1},"attestation_state":"computed","paper":{"title":"Improving Locality in Sparse and Dense Matrix Multiplications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Kazem Cheshmi, Mohammad Mahdi Salehi Dezfuli","submitted_at":"2024-06-28T21:50:37Z","abstract_excerpt":"Consecutive matrix multiplications are commonly used in graph neural networks and sparse linear solvers. These operations frequently access the same matrices for both reading and writing. While reusing these matrices improves data locality, it presents a challenge due to the irregular dependencies between iterations across the two multiplication operations. Existing fusion methods often introduce excessive synchronization overhead or overlapped computations with limited benefits. This paper proposes tile fusion, a runtime approach that fuses tiles of the two matrix-matrix multiplications, wher"},"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":"2407.00243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-28T21:50:37Z","cross_cats_sorted":[],"title_canon_sha256":"033e8fa710679ec9e61af573af42992875fd1c0867cbe7de23898015625cff2e","abstract_canon_sha256":"890e5a814facaaba5153caff7cd654a0327b09f47775d4273bf26905363d1fc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:16.488429Z","signature_b64":"S5ck56rCE6O7WIEkxJSKOqFeCw64WV2yh0ahMfHrt8W5D12RKER/yn5ebOHQVfhqZKRdqqqD7c70truYU/zMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b95efd2b7313d11bed802afd31c7fffc1875bf3635240baaa9d8b03407feed47","last_reissued_at":"2026-07-05T08:38:16.487986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:16.487986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Locality in Sparse and Dense Matrix Multiplications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Kazem Cheshmi, Mohammad Mahdi Salehi Dezfuli","submitted_at":"2024-06-28T21:50:37Z","abstract_excerpt":"Consecutive matrix multiplications are commonly used in graph neural networks and sparse linear solvers. These operations frequently access the same matrices for both reading and writing. While reusing these matrices improves data locality, it presents a challenge due to the irregular dependencies between iterations across the two multiplication operations. Existing fusion methods often introduce excessive synchronization overhead or overlapped computations with limited benefits. This paper proposes tile fusion, a runtime approach that fuses tiles of the two matrix-matrix multiplications, wher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00243","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/2407.00243/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":"2407.00243","created_at":"2026-07-05T08:38:16.488046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00243v1","created_at":"2026-07-05T08:38:16.488046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00243","created_at":"2026-07-05T08:38:16.488046+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFPP2K3TCPIR","created_at":"2026-07-05T08:38:16.488046+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFPP2K3TCPIRX3MA","created_at":"2026-07-05T08:38:16.488046+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFPP2K3T","created_at":"2026-07-05T08:38:16.488046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.15174","citing_title":"A Novel Compiler Transformation for Fast Sparse Matrix Multiplication in GPUs","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q","json":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q.json","graph_json":"https://pith.science/api/pith-number/XFPP2K3TCPIRX3MAFL6TDR777Q/graph.json","events_json":"https://pith.science/api/pith-number/XFPP2K3TCPIRX3MAFL6TDR777Q/events.json","paper":"https://pith.science/paper/XFPP2K3T"},"agent_actions":{"view_html":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q","download_json":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q.json","view_paper":"https://pith.science/paper/XFPP2K3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00243&json=true","fetch_graph":"https://pith.science/api/pith-number/XFPP2K3TCPIRX3MAFL6TDR777Q/graph.json","fetch_events":"https://pith.science/api/pith-number/XFPP2K3TCPIRX3MAFL6TDR777Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q/action/storage_attestation","attest_author":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q/action/author_attestation","sign_citation":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q/action/citation_signature","submit_replication":"https://pith.science/pith/XFPP2K3TCPIRX3MAFL6TDR777Q/action/replication_record"}},"created_at":"2026-07-05T08:38:16.488046+00:00","updated_at":"2026-07-05T08:38:16.488046+00:00"}