{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZRSU7N6TL2UDVYUR36QAAU3JKD","short_pith_number":"pith:ZRSU7N6T","schema_version":"1.0","canonical_sha256":"cc654fb7d35ea83ae291dfa000536950d1b4ec51fc793ae48a305240ca5097fc","source":{"kind":"arxiv","id":"2305.18698","version":1},"attestation_state":"computed","paper":{"title":"AutoMM: Energy-Efficient Multi-Data-Type Matrix Multiply Design on Heterogeneous Programmable System-on-Chip","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Jinming Zhuang, Peipei Zhou, Zhuoping Yang","submitted_at":"2023-05-30T02:42:26Z","abstract_excerpt":"As the increasing complexity of Neural Network(NN) models leads to high demands for computation, AMD introduces a heterogeneous programmable system-on-chip (SoC), i.e., Versal ACAP architectures featured with programmable logic (PL), CPUs, and dedicated AI engines (AIE) ASICs which has a theoretical throughput up to 6.4 TFLOPs for FP32, 25.6 TOPs for INT16 and 102.4 TOPs for INT8. However, the higher level of complexity makes it non-trivial to achieve the theoretical performance even for well-studied applications like matrix-matrix multiply. In this paper, we provide AutoMM, an automatic white"},"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":"2305.18698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AR","submitted_at":"2023-05-30T02:42:26Z","cross_cats_sorted":[],"title_canon_sha256":"c4c7a9fd956ca8ed1ab626bb19ae4e3cae01a34f836fced5b1ecabcbf0b97c16","abstract_canon_sha256":"3877122d252dfb98ab2051034adb3cdbe9b388aa00bb962bb5fbf383482416b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:03.862266Z","signature_b64":"ci9pPCjrklJfm60A46c3b4/BmLFymvcB/jylE4R/rsvustZjVIqYdNAhePCoMkIiAeISYU1sO6HX8UKea5vYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc654fb7d35ea83ae291dfa000536950d1b4ec51fc793ae48a305240ca5097fc","last_reissued_at":"2026-07-05T06:15:03.861878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:03.861878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoMM: Energy-Efficient Multi-Data-Type Matrix Multiply Design on Heterogeneous Programmable System-on-Chip","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Jinming Zhuang, Peipei Zhou, Zhuoping Yang","submitted_at":"2023-05-30T02:42:26Z","abstract_excerpt":"As the increasing complexity of Neural Network(NN) models leads to high demands for computation, AMD introduces a heterogeneous programmable system-on-chip (SoC), i.e., Versal ACAP architectures featured with programmable logic (PL), CPUs, and dedicated AI engines (AIE) ASICs which has a theoretical throughput up to 6.4 TFLOPs for FP32, 25.6 TOPs for INT16 and 102.4 TOPs for INT8. However, the higher level of complexity makes it non-trivial to achieve the theoretical performance even for well-studied applications like matrix-matrix multiply. In this paper, we provide AutoMM, an automatic white"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18698","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/2305.18698/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":"2305.18698","created_at":"2026-07-05T06:15:03.861927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18698v1","created_at":"2026-07-05T06:15:03.861927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18698","created_at":"2026-07-05T06:15:03.861927+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRSU7N6TL2UD","created_at":"2026-07-05T06:15:03.861927+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRSU7N6TL2UDVYUR","created_at":"2026-07-05T06:15:03.861927+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRSU7N6T","created_at":"2026-07-05T06:15:03.861927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14700","citing_title":"Accelerating CRONet on AMD Versal AIE-ML Engines","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD","json":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD.json","graph_json":"https://pith.science/api/pith-number/ZRSU7N6TL2UDVYUR36QAAU3JKD/graph.json","events_json":"https://pith.science/api/pith-number/ZRSU7N6TL2UDVYUR36QAAU3JKD/events.json","paper":"https://pith.science/paper/ZRSU7N6T"},"agent_actions":{"view_html":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD","download_json":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD.json","view_paper":"https://pith.science/paper/ZRSU7N6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18698&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRSU7N6TL2UDVYUR36QAAU3JKD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRSU7N6TL2UDVYUR36QAAU3JKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD/action/storage_attestation","attest_author":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD/action/author_attestation","sign_citation":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD/action/citation_signature","submit_replication":"https://pith.science/pith/ZRSU7N6TL2UDVYUR36QAAU3JKD/action/replication_record"}},"created_at":"2026-07-05T06:15:03.861927+00:00","updated_at":"2026-07-05T06:15:03.861927+00:00"}