{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2B6BYJFXWC33IQL77URYXSD74I","short_pith_number":"pith:2B6BYJFX","schema_version":"1.0","canonical_sha256":"d07c1c24b7b0b7b4417ffd238bc87fe215b24fabf50a1afea823391a664e19c2","source":{"kind":"arxiv","id":"1803.04014","version":1},"attestation_state":"computed","paper":{"title":"NVIDIA Tensor Core Programmability, Performance & Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Erwin Laure, Ivy Bo Peng, Jeffrey S. Vetter, Stefano Markidis, Steven Wei Der Chien","submitted_at":"2018-03-11T18:55:29Z","abstract_excerpt":"The NVIDIA Volta GPU microarchitecture introduces a specialized unit, called \"Tensor Core\" that performs one matrix-multiply-and-accumulate on 4x4 matrices per clock cycle. The NVIDIA Tesla V100 accelerator, featuring the Volta microarchitecture, provides 640 Tensor Cores with a theoretical peak performance of 125 Tflops/s in mixed precision. In this paper, we investigate current approaches to program NVIDIA Tensor Cores, their performances and the precision loss due to computation in mixed precision.\n  Currently, NVIDIA provides three different ways of programming matrix-multiply-and-accumula"},"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":"1803.04014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-03-11T18:55:29Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"ed3f22361147bc994313153fc86079becea37a01dacc923facf4560e8cebaa44","abstract_canon_sha256":"706862a2dfc70279e552a07241c81bab87ba82d384a42e9c8c05d3e843d87bbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:14.517031Z","signature_b64":"5C9T557Fd/X5/k/zZyDbNpUERwjmS5OSxlZQFwzNZSiydvRIQFJw96BiVXbAPXlMVmdMoV788NDoWmQ57EWbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d07c1c24b7b0b7b4417ffd238bc87fe215b24fabf50a1afea823391a664e19c2","last_reissued_at":"2026-05-17T23:58:14.516530Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:14.516530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NVIDIA Tensor Core Programmability, Performance & Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Erwin Laure, Ivy Bo Peng, Jeffrey S. Vetter, Stefano Markidis, Steven Wei Der Chien","submitted_at":"2018-03-11T18:55:29Z","abstract_excerpt":"The NVIDIA Volta GPU microarchitecture introduces a specialized unit, called \"Tensor Core\" that performs one matrix-multiply-and-accumulate on 4x4 matrices per clock cycle. The NVIDIA Tesla V100 accelerator, featuring the Volta microarchitecture, provides 640 Tensor Cores with a theoretical peak performance of 125 Tflops/s in mixed precision. In this paper, we investigate current approaches to program NVIDIA Tensor Cores, their performances and the precision loss due to computation in mixed precision.\n  Currently, NVIDIA provides three different ways of programming matrix-multiply-and-accumula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04014","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":"1803.04014","created_at":"2026-05-17T23:58:14.516614+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.04014v1","created_at":"2026-05-17T23:58:14.516614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04014","created_at":"2026-05-17T23:58:14.516614+00:00"},{"alias_kind":"pith_short_12","alias_value":"2B6BYJFXWC33","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"2B6BYJFXWC33IQL7","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"2B6BYJFX","created_at":"2026-05-18T12:31:59.375834+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/2B6BYJFXWC33IQL77URYXSD74I","json":"https://pith.science/pith/2B6BYJFXWC33IQL77URYXSD74I.json","graph_json":"https://pith.science/api/pith-number/2B6BYJFXWC33IQL77URYXSD74I/graph.json","events_json":"https://pith.science/api/pith-number/2B6BYJFXWC33IQL77URYXSD74I/events.json","paper":"https://pith.science/paper/2B6BYJFX"},"agent_actions":{"view_html":"https://pith.science/pith/2B6BYJFXWC33IQL77URYXSD74I","download_json":"https://pith.science/pith/2B6BYJFXWC33IQL77URYXSD74I.json","view_paper":"https://pith.science/paper/2B6BYJFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.04014&json=true","fetch_graph":"https://pith.science/api/pith-number/2B6BYJFXWC33IQL77URYXSD74I/graph.json","fetch_events":"https://pith.science/api/pith-number/2B6BYJFXWC33IQL77URYXSD74I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2B6BYJFXWC33IQL77URYXSD74I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2B6BYJFXWC33IQL77URYXSD74I/action/storage_attestation","attest_author":"https://pith.science/pith/2B6BYJFXWC33IQL77URYXSD74I/action/author_attestation","sign_citation":"https://pith.science/pith/2B6BYJFXWC33IQL77URYXSD74I/action/citation_signature","submit_replication":"https://pith.science/pith/2B6BYJFXWC33IQL77URYXSD74I/action/replication_record"}},"created_at":"2026-05-17T23:58:14.516614+00:00","updated_at":"2026-05-17T23:58:14.516614+00:00"}