{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B6D57TGNI42ASSI5Y7RHAEC5LY","short_pith_number":"pith:B6D57TGN","schema_version":"1.0","canonical_sha256":"0f87dfcccd473409491dc7e270105d5e1c29c31b53a70f526c739b7495b5ede8","source":{"kind":"arxiv","id":"2306.11975","version":4},"attestation_state":"computed","paper":{"title":"DGEMM on Integer Matrix Multiplication Unit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hiroyuki Ootomo, Katsuhisa Ozaki, Rio Yokota","submitted_at":"2023-06-21T02:03:28Z","abstract_excerpt":"Deep learning hardware achieves high throughput and low power consumption by reducing computing precision and specializing in matrix multiplication. For machine learning inference, fixed-point value computation is commonplace, where the input and output values and the model parameters are quantized. Thus, many processors are now equipped with fast integer matrix multiplication units (IMMU). It is of significant interest to find a way to harness these IMMUs to improve the performance of HPC applications while maintaining accuracy. We focus on the Ozaki scheme, which computes a high-precision ma"},"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":"2306.11975","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-06-21T02:03:28Z","cross_cats_sorted":[],"title_canon_sha256":"bdd26b49dc67cb40bcab67a13123aa205436dfd60ab34b23efb586393c4cebbe","abstract_canon_sha256":"4860fd85016839751b2699d359274ea62131ff4d422826104b5e273422e41e2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:20.660392Z","signature_b64":"H+JLfnkplo/wB1uf2dF1FwJd0oAvhth0+iZA3TG9iDG3/FYr27ABhYNrTmR4NRUxqH+NifcYCGGl/mDFo+FbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f87dfcccd473409491dc7e270105d5e1c29c31b53a70f526c739b7495b5ede8","last_reissued_at":"2026-07-05T08:02:20.659875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:20.659875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DGEMM on Integer Matrix Multiplication Unit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hiroyuki Ootomo, Katsuhisa Ozaki, Rio Yokota","submitted_at":"2023-06-21T02:03:28Z","abstract_excerpt":"Deep learning hardware achieves high throughput and low power consumption by reducing computing precision and specializing in matrix multiplication. For machine learning inference, fixed-point value computation is commonplace, where the input and output values and the model parameters are quantized. Thus, many processors are now equipped with fast integer matrix multiplication units (IMMU). It is of significant interest to find a way to harness these IMMUs to improve the performance of HPC applications while maintaining accuracy. We focus on the Ozaki scheme, which computes a high-precision ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11975","kind":"arxiv","version":4},"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/2306.11975/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":"2306.11975","created_at":"2026-07-05T08:02:20.659935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11975v4","created_at":"2026-07-05T08:02:20.659935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11975","created_at":"2026-07-05T08:02:20.659935+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6D57TGNI42A","created_at":"2026-07-05T08:02:20.659935+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6D57TGNI42ASSI5","created_at":"2026-07-05T08:02:20.659935+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6D57TGN","created_at":"2026-07-05T08:02:20.659935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY","json":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY.json","graph_json":"https://pith.science/api/pith-number/B6D57TGNI42ASSI5Y7RHAEC5LY/graph.json","events_json":"https://pith.science/api/pith-number/B6D57TGNI42ASSI5Y7RHAEC5LY/events.json","paper":"https://pith.science/paper/B6D57TGN"},"agent_actions":{"view_html":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY","download_json":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY.json","view_paper":"https://pith.science/paper/B6D57TGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11975&json=true","fetch_graph":"https://pith.science/api/pith-number/B6D57TGNI42ASSI5Y7RHAEC5LY/graph.json","fetch_events":"https://pith.science/api/pith-number/B6D57TGNI42ASSI5Y7RHAEC5LY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY/action/storage_attestation","attest_author":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY/action/author_attestation","sign_citation":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY/action/citation_signature","submit_replication":"https://pith.science/pith/B6D57TGNI42ASSI5Y7RHAEC5LY/action/replication_record"}},"created_at":"2026-07-05T08:02:20.659935+00:00","updated_at":"2026-07-05T08:02:20.659935+00:00"}