{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TVRU2JGUQAY4MK4JOGUXBRFWFJ","short_pith_number":"pith:TVRU2JGU","schema_version":"1.0","canonical_sha256":"9d634d24d48031c62b8971a970c4b62a4c0a4fce31460f2001707b8621791404","source":{"kind":"arxiv","id":"2406.19580","version":2},"attestation_state":"computed","paper":{"title":"FRED: Flexible REduction-Distribution Interconnect and Communication Implementation for Wafer-Scale Distributed Training of DNN Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Puneet Gupta, Saeed Rashidi, Sudarshan Srinivasan, Tushar Krishna, William Won","submitted_at":"2024-06-28T00:05:53Z","abstract_excerpt":"Distributed Deep Neural Network (DNN) training is a technique to reduce the training overhead by distributing the training tasks into multiple accelerators, according to a parallelization strategy. However, high-performance compute and interconnects are needed for maximum speed-up and linear scaling of the system. Wafer-scale systems are a promising technology that allows for tightly integrating high-end accelerators with high-speed wafer-scale interconnects, making it an attractive platform for distributed training. However, the wafer-scale interconnect should offer high performance and flexi"},"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":"2406.19580","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AR","submitted_at":"2024-06-28T00:05:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a6d194b45d1ea1da2fb9f820864cfe27e026ad1e8deb0866ba91c749505d432","abstract_canon_sha256":"28169dad315a657351ffc35b93f8e59bc11d48340cbaff14b2a1f68968a204ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:13.055784Z","signature_b64":"sepEWS56nMOSuZ0YiKHymVbTvBH048d/BFQdDzndV05aWeieTG/s5HMIBRXMp8j8lXn7MWVBY0W4YwRyCbFNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d634d24d48031c62b8971a970c4b62a4c0a4fce31460f2001707b8621791404","last_reissued_at":"2026-07-05T11:18:13.055376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:13.055376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FRED: Flexible REduction-Distribution Interconnect and Communication Implementation for Wafer-Scale Distributed Training of DNN Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Puneet Gupta, Saeed Rashidi, Sudarshan Srinivasan, Tushar Krishna, William Won","submitted_at":"2024-06-28T00:05:53Z","abstract_excerpt":"Distributed Deep Neural Network (DNN) training is a technique to reduce the training overhead by distributing the training tasks into multiple accelerators, according to a parallelization strategy. However, high-performance compute and interconnects are needed for maximum speed-up and linear scaling of the system. Wafer-scale systems are a promising technology that allows for tightly integrating high-end accelerators with high-speed wafer-scale interconnects, making it an attractive platform for distributed training. However, the wafer-scale interconnect should offer high performance and flexi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19580","kind":"arxiv","version":2},"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/2406.19580/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":"2406.19580","created_at":"2026-07-05T11:18:13.055432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19580v2","created_at":"2026-07-05T11:18:13.055432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19580","created_at":"2026-07-05T11:18:13.055432+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVRU2JGUQAY4","created_at":"2026-07-05T11:18:13.055432+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVRU2JGUQAY4MK4J","created_at":"2026-07-05T11:18:13.055432+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVRU2JGU","created_at":"2026-07-05T11:18:13.055432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22968","citing_title":"MOCAP: Wafer-Scale-Chip-Oriented Memory-Orchestrated Chunked Pipelining Framework for Prefill-Only LLM Inference","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ","json":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ.json","graph_json":"https://pith.science/api/pith-number/TVRU2JGUQAY4MK4JOGUXBRFWFJ/graph.json","events_json":"https://pith.science/api/pith-number/TVRU2JGUQAY4MK4JOGUXBRFWFJ/events.json","paper":"https://pith.science/paper/TVRU2JGU"},"agent_actions":{"view_html":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ","download_json":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ.json","view_paper":"https://pith.science/paper/TVRU2JGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19580&json=true","fetch_graph":"https://pith.science/api/pith-number/TVRU2JGUQAY4MK4JOGUXBRFWFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TVRU2JGUQAY4MK4JOGUXBRFWFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ/action/storage_attestation","attest_author":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ/action/author_attestation","sign_citation":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ/action/citation_signature","submit_replication":"https://pith.science/pith/TVRU2JGUQAY4MK4JOGUXBRFWFJ/action/replication_record"}},"created_at":"2026-07-05T11:18:13.055432+00:00","updated_at":"2026-07-05T11:18:13.055432+00:00"}