{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PH7NMZ7ISQRRFC4PKKHZOZWMUU","short_pith_number":"pith:PH7NMZ7I","schema_version":"1.0","canonical_sha256":"79fed667e89423128b8f528f9766cca528b44bb9699153acb3dbe2d178dfbd87","source":{"kind":"arxiv","id":"2409.14317","version":1},"attestation_state":"computed","paper":{"title":"Dissecting CXL Memory Performance at Scale: Analysis, Modeling, and Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.OS","authors_text":"Daniel S. Berger, Hamid Hadian, Hanchen Xu, Huaicheng Li, Jinshu Liu","submitted_at":"2024-09-22T05:11:16Z","abstract_excerpt":"We present SupMario, a characterization framework designed to thoroughly analyze, model, and optimize CXL memory performance. SupMario is based on extensive evaluation of 265 workloads spanning 4 real CXL devices within 7 memory latency configurations across 4 processor platforms. SupMario uncovers many key insights, including detailed workload performance at sub-us memory latencies (140-410 ns), CXL tail latencies, CPU tolerance to CXL latencies, CXL performance root-cause analysis and precise performance prediction models. In particular, SupMario performance models rely solely on 12 CPU perf"},"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":"2409.14317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2024-09-22T05:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"964667009d0f60d0734b2931de80d6bcc5ebfa88eecc8af248794632ae2e2a4b","abstract_canon_sha256":"9167ec00162207804e487f383bd26f0092187634c1c11273ce35fc2f591f3820"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:14.825140Z","signature_b64":"fhRPM0bwKhKxuGMXAocHLdfVmBBnG5mEAfDsFE+bDaISNDay3oUpeJJbDWOFVZF6rGvpZj7W/n+vs+VwbfZIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79fed667e89423128b8f528f9766cca528b44bb9699153acb3dbe2d178dfbd87","last_reissued_at":"2026-07-05T09:10:14.824721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:14.824721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dissecting CXL Memory Performance at Scale: Analysis, Modeling, and Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.OS","authors_text":"Daniel S. Berger, Hamid Hadian, Hanchen Xu, Huaicheng Li, Jinshu Liu","submitted_at":"2024-09-22T05:11:16Z","abstract_excerpt":"We present SupMario, a characterization framework designed to thoroughly analyze, model, and optimize CXL memory performance. SupMario is based on extensive evaluation of 265 workloads spanning 4 real CXL devices within 7 memory latency configurations across 4 processor platforms. SupMario uncovers many key insights, including detailed workload performance at sub-us memory latencies (140-410 ns), CXL tail latencies, CPU tolerance to CXL latencies, CXL performance root-cause analysis and precise performance prediction models. In particular, SupMario performance models rely solely on 12 CPU perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14317","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/2409.14317/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":"2409.14317","created_at":"2026-07-05T09:10:14.824787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14317v1","created_at":"2026-07-05T09:10:14.824787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14317","created_at":"2026-07-05T09:10:14.824787+00:00"},{"alias_kind":"pith_short_12","alias_value":"PH7NMZ7ISQRR","created_at":"2026-07-05T09:10:14.824787+00:00"},{"alias_kind":"pith_short_16","alias_value":"PH7NMZ7ISQRRFC4P","created_at":"2026-07-05T09:10:14.824787+00:00"},{"alias_kind":"pith_short_8","alias_value":"PH7NMZ7I","created_at":"2026-07-05T09:10:14.824787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20370","citing_title":"Clove: Object-Level CXL Memory Management in Managed Runtimes","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08800","citing_title":"Equilibria: Fair Multi-Tenant CXL Memory Tiering At Scale","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19494","citing_title":"DPC: A Distributed Page Cache over CXL","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU","json":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU.json","graph_json":"https://pith.science/api/pith-number/PH7NMZ7ISQRRFC4PKKHZOZWMUU/graph.json","events_json":"https://pith.science/api/pith-number/PH7NMZ7ISQRRFC4PKKHZOZWMUU/events.json","paper":"https://pith.science/paper/PH7NMZ7I"},"agent_actions":{"view_html":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU","download_json":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU.json","view_paper":"https://pith.science/paper/PH7NMZ7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14317&json=true","fetch_graph":"https://pith.science/api/pith-number/PH7NMZ7ISQRRFC4PKKHZOZWMUU/graph.json","fetch_events":"https://pith.science/api/pith-number/PH7NMZ7ISQRRFC4PKKHZOZWMUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU/action/storage_attestation","attest_author":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU/action/author_attestation","sign_citation":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU/action/citation_signature","submit_replication":"https://pith.science/pith/PH7NMZ7ISQRRFC4PKKHZOZWMUU/action/replication_record"}},"created_at":"2026-07-05T09:10:14.824787+00:00","updated_at":"2026-07-05T09:10:14.824787+00:00"}