{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JPZMLXXDZXZXOTRDFIPT6OTD55","short_pith_number":"pith:JPZMLXXD","schema_version":"1.0","canonical_sha256":"4bf2c5dee3cdf3774e232a1f3f3a63ef63131ecb0391ff3eea956698e00a45a8","source":{"kind":"arxiv","id":"1607.04245","version":1},"attestation_state":"computed","paper":{"title":"Finite Element Integration with Quadrature on the GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MS","authors_text":"Andy R. Terrel, Karl Rupp, Matthew G. Knepley","submitted_at":"2016-07-14T18:53:48Z","abstract_excerpt":"We present a novel, quadrature-based finite element integration method for low-order elements on GPUs, using a pattern we call \\textit{thread transposition} to avoid reductions while vectorizing aggressively. On the NVIDIA GTX580, which has a nominal single precision peak flop rate of 1.5 TF/s and a memory bandwidth of 192 GB/s, we achieve close to 300 GF/s for element integration on first-order discretization of the Laplacian operator with variable coefficients in two dimensions, and over 400 GF/s in three dimensions. From our performance model we find that this corresponds to 90\\% of our mea"},"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":"1607.04245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MS","submitted_at":"2016-07-14T18:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"82fe874743c4c9e6ea507c3caab897748c6e0465900890e6cd9df8666cc63cc1","abstract_canon_sha256":"c5eabf6d10a9dd16266558e0a3de79d57e8419153f9b9c2de8c7e215c3824af1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:03.779176Z","signature_b64":"fPuTeyl2JIfbC1NtqpIHzskGs1bHFWE5rCOfIycfAiCdja/n7dllhCWA1Wj1N3lAeN/Fdk7ugUlPRVtK/AS4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bf2c5dee3cdf3774e232a1f3f3a63ef63131ecb0391ff3eea956698e00a45a8","last_reissued_at":"2026-05-18T01:11:03.778737Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:03.778737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite Element Integration with Quadrature on the GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MS","authors_text":"Andy R. Terrel, Karl Rupp, Matthew G. Knepley","submitted_at":"2016-07-14T18:53:48Z","abstract_excerpt":"We present a novel, quadrature-based finite element integration method for low-order elements on GPUs, using a pattern we call \\textit{thread transposition} to avoid reductions while vectorizing aggressively. On the NVIDIA GTX580, which has a nominal single precision peak flop rate of 1.5 TF/s and a memory bandwidth of 192 GB/s, we achieve close to 300 GF/s for element integration on first-order discretization of the Laplacian operator with variable coefficients in two dimensions, and over 400 GF/s in three dimensions. From our performance model we find that this corresponds to 90\\% of our mea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04245","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":"1607.04245","created_at":"2026-05-18T01:11:03.778816+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.04245v1","created_at":"2026-05-18T01:11:03.778816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04245","created_at":"2026-05-18T01:11:03.778816+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPZMLXXDZXZX","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPZMLXXDZXZXOTRD","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPZMLXXD","created_at":"2026-05-18T12:30:25.849896+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/JPZMLXXDZXZXOTRDFIPT6OTD55","json":"https://pith.science/pith/JPZMLXXDZXZXOTRDFIPT6OTD55.json","graph_json":"https://pith.science/api/pith-number/JPZMLXXDZXZXOTRDFIPT6OTD55/graph.json","events_json":"https://pith.science/api/pith-number/JPZMLXXDZXZXOTRDFIPT6OTD55/events.json","paper":"https://pith.science/paper/JPZMLXXD"},"agent_actions":{"view_html":"https://pith.science/pith/JPZMLXXDZXZXOTRDFIPT6OTD55","download_json":"https://pith.science/pith/JPZMLXXDZXZXOTRDFIPT6OTD55.json","view_paper":"https://pith.science/paper/JPZMLXXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.04245&json=true","fetch_graph":"https://pith.science/api/pith-number/JPZMLXXDZXZXOTRDFIPT6OTD55/graph.json","fetch_events":"https://pith.science/api/pith-number/JPZMLXXDZXZXOTRDFIPT6OTD55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPZMLXXDZXZXOTRDFIPT6OTD55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPZMLXXDZXZXOTRDFIPT6OTD55/action/storage_attestation","attest_author":"https://pith.science/pith/JPZMLXXDZXZXOTRDFIPT6OTD55/action/author_attestation","sign_citation":"https://pith.science/pith/JPZMLXXDZXZXOTRDFIPT6OTD55/action/citation_signature","submit_replication":"https://pith.science/pith/JPZMLXXDZXZXOTRDFIPT6OTD55/action/replication_record"}},"created_at":"2026-05-18T01:11:03.778816+00:00","updated_at":"2026-05-18T01:11:03.778816+00:00"}