{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:X5AHL4BGWROMKOLRABP4RNAVED","short_pith_number":"pith:X5AHL4BG","schema_version":"1.0","canonical_sha256":"bf4075f026b45cc53971005fc8b41520d14719d2bda0a790bf2d5f87c1af6562","source":{"kind":"arxiv","id":"1811.12174","version":1},"attestation_state":"computed","paper":{"title":"Data-parallel distributed training of very large models beyond GPU capacity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Amit Juneja, Anar Yusifov, Bryant Nelson, Max Grossman, Minsik Cho, Samuel Matzek","submitted_at":"2018-11-29T14:22:05Z","abstract_excerpt":"GPUs have limited memory and it is difficult to train wide and/or deep models that cause the training process to go out of memory. It is shown in this paper how an open source tool called Large Model Support (LMS) can utilize a high bandwidth NVLink connection between CPUs and GPUs to accomplish training of deep convolutional networks. LMS performs tensor swapping between CPU memory and GPU memory such that only a minimal number of tensors required in a training step are kept in the GPU memory. It is also shown how LMS can be combined with an MPI based distributed deep learning module to train"},"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":"1811.12174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-11-29T14:22:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f67b995559506165223c06e7ff4e9d595f6919cc2a06baf332abc1eb3065282","abstract_canon_sha256":"84dfe05461a9d054acc362521751c075b34e71d086731944f35163a8376b586c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:34.214339Z","signature_b64":"yIWFbWdLBBJ6Af0/6wYVOzw7hf4Uzh9NGTP+txirS3xJHUjHqmFLhdyJsV24Yd+vf9oNzgOMp05IVANpqVxxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf4075f026b45cc53971005fc8b41520d14719d2bda0a790bf2d5f87c1af6562","last_reissued_at":"2026-05-17T23:59:34.213597Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:34.213597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-parallel distributed training of very large models beyond GPU capacity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Amit Juneja, Anar Yusifov, Bryant Nelson, Max Grossman, Minsik Cho, Samuel Matzek","submitted_at":"2018-11-29T14:22:05Z","abstract_excerpt":"GPUs have limited memory and it is difficult to train wide and/or deep models that cause the training process to go out of memory. It is shown in this paper how an open source tool called Large Model Support (LMS) can utilize a high bandwidth NVLink connection between CPUs and GPUs to accomplish training of deep convolutional networks. LMS performs tensor swapping between CPU memory and GPU memory such that only a minimal number of tensors required in a training step are kept in the GPU memory. It is also shown how LMS can be combined with an MPI based distributed deep learning module to train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12174","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":""},"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":"1811.12174","created_at":"2026-05-17T23:59:34.213730+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12174v1","created_at":"2026-05-17T23:59:34.213730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12174","created_at":"2026-05-17T23:59:34.213730+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5AHL4BGWROM","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5AHL4BGWROMKOLR","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5AHL4BG","created_at":"2026-05-18T12:33:01.666342+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/X5AHL4BGWROMKOLRABP4RNAVED","json":"https://pith.science/pith/X5AHL4BGWROMKOLRABP4RNAVED.json","graph_json":"https://pith.science/api/pith-number/X5AHL4BGWROMKOLRABP4RNAVED/graph.json","events_json":"https://pith.science/api/pith-number/X5AHL4BGWROMKOLRABP4RNAVED/events.json","paper":"https://pith.science/paper/X5AHL4BG"},"agent_actions":{"view_html":"https://pith.science/pith/X5AHL4BGWROMKOLRABP4RNAVED","download_json":"https://pith.science/pith/X5AHL4BGWROMKOLRABP4RNAVED.json","view_paper":"https://pith.science/paper/X5AHL4BG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12174&json=true","fetch_graph":"https://pith.science/api/pith-number/X5AHL4BGWROMKOLRABP4RNAVED/graph.json","fetch_events":"https://pith.science/api/pith-number/X5AHL4BGWROMKOLRABP4RNAVED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5AHL4BGWROMKOLRABP4RNAVED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5AHL4BGWROMKOLRABP4RNAVED/action/storage_attestation","attest_author":"https://pith.science/pith/X5AHL4BGWROMKOLRABP4RNAVED/action/author_attestation","sign_citation":"https://pith.science/pith/X5AHL4BGWROMKOLRABP4RNAVED/action/citation_signature","submit_replication":"https://pith.science/pith/X5AHL4BGWROMKOLRABP4RNAVED/action/replication_record"}},"created_at":"2026-05-17T23:59:34.213730+00:00","updated_at":"2026-05-17T23:59:34.213730+00:00"}