{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IYAQBYKA2CP6RZDUY7HJNYIOAO","short_pith_number":"pith:IYAQBYKA","schema_version":"1.0","canonical_sha256":"460100e140d09fe8e474c7ce96e10e039f22e9f1f9de112ac3647c06bdd83985","source":{"kind":"arxiv","id":"2404.05368","version":2},"attestation_state":"computed","paper":{"title":"Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Jan Klhufek, Lukas Sekanina, Miroslav Safar, Vojtech Mrazek, Zdenek Vasicek","submitted_at":"2024-04-08T10:10:30Z","abstract_excerpt":"Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors, including a weight quantization strategy (i.e., data types and bit-widths) and mapping (i.e., placement and scheduling of DNN elementary operations on hardware units of the accelerator). We show that enabling rich mixed quantization schemes during the implementation can open a previously hidden space of mappings that utilize the hardware resources more effectively. CNNs utilizing quantized weights and activations and suitable mappings can significant"},"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":"2404.05368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2024-04-08T10:10:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e23fb72579d1298c53bde8c6ec1e638b8d685e1c91e8f104b89a787b1ce3f18","abstract_canon_sha256":"4c6e71ab825d22ba7e2ab37e75df121985efe3c80cfb5f0c6528737c4bee5eda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:48.168082Z","signature_b64":"Pxg+5a9yGbhdd63QJUEUwuhU62FJwkPKko0QtdStQeEpU6ky7rkU+hbsuSjH3TG21IbfQiuc9D82SAnsDnl1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"460100e140d09fe8e474c7ce96e10e039f22e9f1f9de112ac3647c06bdd83985","last_reissued_at":"2026-07-05T11:40:48.167585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:48.167585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Jan Klhufek, Lukas Sekanina, Miroslav Safar, Vojtech Mrazek, Zdenek Vasicek","submitted_at":"2024-04-08T10:10:30Z","abstract_excerpt":"Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors, including a weight quantization strategy (i.e., data types and bit-widths) and mapping (i.e., placement and scheduling of DNN elementary operations on hardware units of the accelerator). We show that enabling rich mixed quantization schemes during the implementation can open a previously hidden space of mappings that utilize the hardware resources more effectively. CNNs utilizing quantized weights and activations and suitable mappings can significant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05368","kind":"arxiv","version":2},"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/2404.05368/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":"2404.05368","created_at":"2026-07-05T11:40:48.167641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05368v2","created_at":"2026-07-05T11:40:48.167641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05368","created_at":"2026-07-05T11:40:48.167641+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYAQBYKA2CP6","created_at":"2026-07-05T11:40:48.167641+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYAQBYKA2CP6RZDU","created_at":"2026-07-05T11:40:48.167641+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYAQBYKA","created_at":"2026-07-05T11:40:48.167641+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/IYAQBYKA2CP6RZDUY7HJNYIOAO","json":"https://pith.science/pith/IYAQBYKA2CP6RZDUY7HJNYIOAO.json","graph_json":"https://pith.science/api/pith-number/IYAQBYKA2CP6RZDUY7HJNYIOAO/graph.json","events_json":"https://pith.science/api/pith-number/IYAQBYKA2CP6RZDUY7HJNYIOAO/events.json","paper":"https://pith.science/paper/IYAQBYKA"},"agent_actions":{"view_html":"https://pith.science/pith/IYAQBYKA2CP6RZDUY7HJNYIOAO","download_json":"https://pith.science/pith/IYAQBYKA2CP6RZDUY7HJNYIOAO.json","view_paper":"https://pith.science/paper/IYAQBYKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05368&json=true","fetch_graph":"https://pith.science/api/pith-number/IYAQBYKA2CP6RZDUY7HJNYIOAO/graph.json","fetch_events":"https://pith.science/api/pith-number/IYAQBYKA2CP6RZDUY7HJNYIOAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYAQBYKA2CP6RZDUY7HJNYIOAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYAQBYKA2CP6RZDUY7HJNYIOAO/action/storage_attestation","attest_author":"https://pith.science/pith/IYAQBYKA2CP6RZDUY7HJNYIOAO/action/author_attestation","sign_citation":"https://pith.science/pith/IYAQBYKA2CP6RZDUY7HJNYIOAO/action/citation_signature","submit_replication":"https://pith.science/pith/IYAQBYKA2CP6RZDUY7HJNYIOAO/action/replication_record"}},"created_at":"2026-07-05T11:40:48.167641+00:00","updated_at":"2026-07-05T11:40:48.167641+00:00"}