{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NIP2OLVQKABXBHH3RFNWXQGVCN","short_pith_number":"pith:NIP2OLVQ","schema_version":"1.0","canonical_sha256":"6a1fa72eb05003709cfb895b6bc0d5135e777d34852be05a9e03b035886bebbb","source":{"kind":"arxiv","id":"2103.11991","version":1},"attestation_state":"computed","paper":{"title":"Kokkos Kernels: Performance Portable Sparse/Dense Linear Algebra and Graph Kernels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MS","authors_text":"Brian Kelley, Christian R. Trott, Evan Harvey, Ichitaro Yamazaki, Jeremiah Wilke, Luc Berger-Vergiat, Nathan Ellingwood, Seher Acer, Sivasankaran Rajamanickam, Vinh Dang","submitted_at":"2021-03-22T16:36:12Z","abstract_excerpt":"As hardware architectures are evolving in the push towards exascale, developing Computational Science and Engineering (CSE) applications depend on performance portable approaches for sustainable software development. This paper describes one aspect of performance portability with respect to developing a portable library of kernels that serve the needs of several CSE applications and software frameworks. We describe Kokkos Kernels, a library of kernels for sparse linear algebra, dense linear algebra and graph kernels. We describe the design principles of such a library and demonstrate portable "},"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":"2103.11991","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MS","submitted_at":"2021-03-22T16:36:12Z","cross_cats_sorted":[],"title_canon_sha256":"14d1b1a48f27c156fb4a8007c917328d1b4aaeaaf475c4522dd5c37bc1f4d363","abstract_canon_sha256":"0a04ad4a3e2a0de9487db16433837ed4dac359fb3afd8c333c971986e965a78b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:14.059136Z","signature_b64":"D9wVugXfNkzQyqJcQ47WOk/u3gk65wzONsrBI1lvg6+pRtHgRFXWI6kPvEP0b63IeNmboqDUhSG1Ri1UDi8yAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a1fa72eb05003709cfb895b6bc0d5135e777d34852be05a9e03b035886bebbb","last_reissued_at":"2026-07-05T02:25:14.058736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:14.058736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kokkos Kernels: Performance Portable Sparse/Dense Linear Algebra and Graph Kernels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MS","authors_text":"Brian Kelley, Christian R. Trott, Evan Harvey, Ichitaro Yamazaki, Jeremiah Wilke, Luc Berger-Vergiat, Nathan Ellingwood, Seher Acer, Sivasankaran Rajamanickam, Vinh Dang","submitted_at":"2021-03-22T16:36:12Z","abstract_excerpt":"As hardware architectures are evolving in the push towards exascale, developing Computational Science and Engineering (CSE) applications depend on performance portable approaches for sustainable software development. This paper describes one aspect of performance portability with respect to developing a portable library of kernels that serve the needs of several CSE applications and software frameworks. We describe Kokkos Kernels, a library of kernels for sparse linear algebra, dense linear algebra and graph kernels. We describe the design principles of such a library and demonstrate portable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11991","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/2103.11991/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":"2103.11991","created_at":"2026-07-05T02:25:14.058787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.11991v1","created_at":"2026-07-05T02:25:14.058787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11991","created_at":"2026-07-05T02:25:14.058787+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIP2OLVQKABX","created_at":"2026-07-05T02:25:14.058787+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIP2OLVQKABXBHH3","created_at":"2026-07-05T02:25:14.058787+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIP2OLVQ","created_at":"2026-07-05T02:25:14.058787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.02228","citing_title":"Algebraic Temporal Blocking for Sparse Iterative Solvers on Multi-Core CPUs","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03208","citing_title":"Kerncap: Automated Kernel Extraction and Isolation for AMD GPUs","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03208","citing_title":"Kerncap: Automated Kernel Extraction and Isolation for AMD GPUs","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN","json":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN.json","graph_json":"https://pith.science/api/pith-number/NIP2OLVQKABXBHH3RFNWXQGVCN/graph.json","events_json":"https://pith.science/api/pith-number/NIP2OLVQKABXBHH3RFNWXQGVCN/events.json","paper":"https://pith.science/paper/NIP2OLVQ"},"agent_actions":{"view_html":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN","download_json":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN.json","view_paper":"https://pith.science/paper/NIP2OLVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.11991&json=true","fetch_graph":"https://pith.science/api/pith-number/NIP2OLVQKABXBHH3RFNWXQGVCN/graph.json","fetch_events":"https://pith.science/api/pith-number/NIP2OLVQKABXBHH3RFNWXQGVCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN/action/storage_attestation","attest_author":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN/action/author_attestation","sign_citation":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN/action/citation_signature","submit_replication":"https://pith.science/pith/NIP2OLVQKABXBHH3RFNWXQGVCN/action/replication_record"}},"created_at":"2026-07-05T02:25:14.058787+00:00","updated_at":"2026-07-05T02:25:14.058787+00:00"}