{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2YHM7KJEWIFBJTNDLAGHHYIY77","short_pith_number":"pith:2YHM7KJE","schema_version":"1.0","canonical_sha256":"d60ecfa924b20a14cda3580c73e118ffe8ff43f993ff3d4239b3ecac59ef110c","source":{"kind":"arxiv","id":"2202.02310","version":1},"attestation_state":"computed","paper":{"title":"EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Juan Gomez-Luna, Kees Vissers, Konstantinos Kanellopoulos, Lois Orosa, Michaela Blott, Onur Mutlu, Skanda Koppula, Yaman Umuroglu","submitted_at":"2022-02-04T18:48:36Z","abstract_excerpt":"Dilated and transposed convolutions are widely used in modern convolutional neural networks (CNNs). These kernels are used extensively during CNN training and inference of applications such as image segmentation and high-resolution image generation. Although these kernels have grown in popularity, they stress current compute systems due to their high memory intensity, exascale compute demands, and large energy consumption.\n  We find that commonly-used low-power CNN inference accelerators based on spatial architectures are not optimized for both of these convolutional kernels. Dilated and trans"},"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":"2202.02310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T18:48:36Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"0738f9f363fff9afc7accda93108f98dbaf9d4e0a4c6c19532956ed8a4744c79","abstract_canon_sha256":"15315ffe4bbfc4615aa1d33cf9d6291338bab773aab156704ed16586404c247d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:10.589990Z","signature_b64":"EmbvM8mhGW3eeVTHui4p+a2SXskwaehn3RTUC9/kYxq3viCUw/yA9zv8XKSRjzAuPQdRenOBp3vvPiESVe9cAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d60ecfa924b20a14cda3580c73e118ffe8ff43f993ff3d4239b3ecac59ef110c","last_reissued_at":"2026-07-05T03:54:10.589506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:10.589506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Juan Gomez-Luna, Kees Vissers, Konstantinos Kanellopoulos, Lois Orosa, Michaela Blott, Onur Mutlu, Skanda Koppula, Yaman Umuroglu","submitted_at":"2022-02-04T18:48:36Z","abstract_excerpt":"Dilated and transposed convolutions are widely used in modern convolutional neural networks (CNNs). These kernels are used extensively during CNN training and inference of applications such as image segmentation and high-resolution image generation. Although these kernels have grown in popularity, they stress current compute systems due to their high memory intensity, exascale compute demands, and large energy consumption.\n  We find that commonly-used low-power CNN inference accelerators based on spatial architectures are not optimized for both of these convolutional kernels. Dilated and trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02310","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/2202.02310/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":"2202.02310","created_at":"2026-07-05T03:54:10.589569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02310v1","created_at":"2026-07-05T03:54:10.589569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02310","created_at":"2026-07-05T03:54:10.589569+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YHM7KJEWIFB","created_at":"2026-07-05T03:54:10.589569+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YHM7KJEWIFBJTND","created_at":"2026-07-05T03:54:10.589569+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YHM7KJE","created_at":"2026-07-05T03:54:10.589569+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/2YHM7KJEWIFBJTNDLAGHHYIY77","json":"https://pith.science/pith/2YHM7KJEWIFBJTNDLAGHHYIY77.json","graph_json":"https://pith.science/api/pith-number/2YHM7KJEWIFBJTNDLAGHHYIY77/graph.json","events_json":"https://pith.science/api/pith-number/2YHM7KJEWIFBJTNDLAGHHYIY77/events.json","paper":"https://pith.science/paper/2YHM7KJE"},"agent_actions":{"view_html":"https://pith.science/pith/2YHM7KJEWIFBJTNDLAGHHYIY77","download_json":"https://pith.science/pith/2YHM7KJEWIFBJTNDLAGHHYIY77.json","view_paper":"https://pith.science/paper/2YHM7KJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02310&json=true","fetch_graph":"https://pith.science/api/pith-number/2YHM7KJEWIFBJTNDLAGHHYIY77/graph.json","fetch_events":"https://pith.science/api/pith-number/2YHM7KJEWIFBJTNDLAGHHYIY77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YHM7KJEWIFBJTNDLAGHHYIY77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YHM7KJEWIFBJTNDLAGHHYIY77/action/storage_attestation","attest_author":"https://pith.science/pith/2YHM7KJEWIFBJTNDLAGHHYIY77/action/author_attestation","sign_citation":"https://pith.science/pith/2YHM7KJEWIFBJTNDLAGHHYIY77/action/citation_signature","submit_replication":"https://pith.science/pith/2YHM7KJEWIFBJTNDLAGHHYIY77/action/replication_record"}},"created_at":"2026-07-05T03:54:10.589569+00:00","updated_at":"2026-07-05T03:54:10.589569+00:00"}