{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IS42M7XTTU42FICUPQZA2UAXMT","short_pith_number":"pith:IS42M7XT","schema_version":"1.0","canonical_sha256":"44b9a67ef39d39a2a0547c320d501764f8a2d6f55614c1368a241ee152aa8bb1","source":{"kind":"arxiv","id":"2203.00448","version":1},"attestation_state":"computed","paper":{"title":"Memory Planning for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Maksim Levental","submitted_at":"2022-02-23T05:28:18Z","abstract_excerpt":"We study memory allocation patterns in DNNs during inference, in the context of large-scale systems. We observe that such memory allocation patterns, in the context of multi-threading, are subject to high latencies, due to \\texttt{mutex} contention in the system memory allocator. Latencies incurred due to such \\texttt{mutex} contention produce undesirable bottlenecks in user-facing services. Thus, we propose a \"memorization\" based technique, \\texttt{MemoMalloc}, for optimizing overall latency, with only moderate increases in peak memory usage. Specifically, our technique consists of a runtime "},"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":"2203.00448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-23T05:28:18Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"919b7e7028ab68f42c867adc9683b8d34a40fa1d94e136ddc12baeced225fa6c","abstract_canon_sha256":"53ec179d1fc2c686cb61dadd489fb9d8c2594244f9c56922712c1cbd860379da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:17.452901Z","signature_b64":"of5x4bJj2SSXuRG68BKmlQkBdwvXEPmg4NkJ2jL2E5r2ozVthgchNIOi/NIUNCdHhl25vupSkbbvO9hr+LEpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44b9a67ef39d39a2a0547c320d501764f8a2d6f55614c1368a241ee152aa8bb1","last_reissued_at":"2026-07-05T04:01:17.452515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:17.452515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Planning for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Maksim Levental","submitted_at":"2022-02-23T05:28:18Z","abstract_excerpt":"We study memory allocation patterns in DNNs during inference, in the context of large-scale systems. We observe that such memory allocation patterns, in the context of multi-threading, are subject to high latencies, due to \\texttt{mutex} contention in the system memory allocator. Latencies incurred due to such \\texttt{mutex} contention produce undesirable bottlenecks in user-facing services. Thus, we propose a \"memorization\" based technique, \\texttt{MemoMalloc}, for optimizing overall latency, with only moderate increases in peak memory usage. Specifically, our technique consists of a runtime "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00448","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/2203.00448/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":"2203.00448","created_at":"2026-07-05T04:01:17.452571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.00448v1","created_at":"2026-07-05T04:01:17.452571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00448","created_at":"2026-07-05T04:01:17.452571+00:00"},{"alias_kind":"pith_short_12","alias_value":"IS42M7XTTU42","created_at":"2026-07-05T04:01:17.452571+00:00"},{"alias_kind":"pith_short_16","alias_value":"IS42M7XTTU42FICU","created_at":"2026-07-05T04:01:17.452571+00:00"},{"alias_kind":"pith_short_8","alias_value":"IS42M7XT","created_at":"2026-07-05T04:01:17.452571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.11136","citing_title":"Xema: Efficient Diffusion Serving through Fine-Grained Memory Management and Auto-Configuration","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT","json":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT.json","graph_json":"https://pith.science/api/pith-number/IS42M7XTTU42FICUPQZA2UAXMT/graph.json","events_json":"https://pith.science/api/pith-number/IS42M7XTTU42FICUPQZA2UAXMT/events.json","paper":"https://pith.science/paper/IS42M7XT"},"agent_actions":{"view_html":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT","download_json":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT.json","view_paper":"https://pith.science/paper/IS42M7XT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.00448&json=true","fetch_graph":"https://pith.science/api/pith-number/IS42M7XTTU42FICUPQZA2UAXMT/graph.json","fetch_events":"https://pith.science/api/pith-number/IS42M7XTTU42FICUPQZA2UAXMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT/action/storage_attestation","attest_author":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT/action/author_attestation","sign_citation":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT/action/citation_signature","submit_replication":"https://pith.science/pith/IS42M7XTTU42FICUPQZA2UAXMT/action/replication_record"}},"created_at":"2026-07-05T04:01:17.452571+00:00","updated_at":"2026-07-05T04:01:17.452571+00:00"}