{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WIR3XBQVHL4PGBIZRFIV2PS47B","short_pith_number":"pith:WIR3XBQV","schema_version":"1.0","canonical_sha256":"b223bb86153af8f3051989515d3e5cf8673cf92570c79a9bfd65fc2321de7e79","source":{"kind":"arxiv","id":"2107.13386","version":2},"attestation_state":"computed","paper":{"title":"SPOTS: An Accelerator for Sparse Convolutional Networks Leveraging Systolic General Matrix-Matrix Multiplication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Mohammadreza Soltaniyeh, Richard P. Martin, Santosh Nagarakatte","submitted_at":"2021-07-28T14:26:40Z","abstract_excerpt":"This paper proposes a new hardware accelerator for sparse convolutional neural networks (CNNs) by building a hardware unit to perform the Image to Column (IM2COL) transformation of the input feature map coupled with a systolic array-based general matrix-matrix multiplication (GEMM) unit. Our design carefully overlaps the IM2COL transformation with the GEMM computation to maximize parallelism. We propose a novel design for the IM2COL unit that uses a set of distributed local memories connected by a ring network, which improves energy efficiency and latency by streaming the input feature map onl"},"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":"2107.13386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2021-07-28T14:26:40Z","cross_cats_sorted":[],"title_canon_sha256":"2561e2b3af3849d8d1f74b8d7ffdb5fa8c2ae8bdaaed4198c9111a1a541c1754","abstract_canon_sha256":"08beb71372e85691b7e1d876d855c6ce19d6e7100798c55523f2603e3ae7470b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:57.058374Z","signature_b64":"CPrM0EJ6WMqMxM0UPlZnSgqM3XhdsYsdAwCwuxwtwtohaJy8LiaL9gYbZTk7TrRliHgjr3ytFn3WeXbY0QyPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b223bb86153af8f3051989515d3e5cf8673cf92570c79a9bfd65fc2321de7e79","last_reissued_at":"2026-07-05T03:34:57.057838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:57.057838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPOTS: An Accelerator for Sparse Convolutional Networks Leveraging Systolic General Matrix-Matrix Multiplication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Mohammadreza Soltaniyeh, Richard P. Martin, Santosh Nagarakatte","submitted_at":"2021-07-28T14:26:40Z","abstract_excerpt":"This paper proposes a new hardware accelerator for sparse convolutional neural networks (CNNs) by building a hardware unit to perform the Image to Column (IM2COL) transformation of the input feature map coupled with a systolic array-based general matrix-matrix multiplication (GEMM) unit. Our design carefully overlaps the IM2COL transformation with the GEMM computation to maximize parallelism. We propose a novel design for the IM2COL unit that uses a set of distributed local memories connected by a ring network, which improves energy efficiency and latency by streaming the input feature map onl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13386","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/2107.13386/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":"2107.13386","created_at":"2026-07-05T03:34:57.057907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13386v2","created_at":"2026-07-05T03:34:57.057907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13386","created_at":"2026-07-05T03:34:57.057907+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIR3XBQVHL4P","created_at":"2026-07-05T03:34:57.057907+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIR3XBQVHL4PGBIZ","created_at":"2026-07-05T03:34:57.057907+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIR3XBQV","created_at":"2026-07-05T03:34:57.057907+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/WIR3XBQVHL4PGBIZRFIV2PS47B","json":"https://pith.science/pith/WIR3XBQVHL4PGBIZRFIV2PS47B.json","graph_json":"https://pith.science/api/pith-number/WIR3XBQVHL4PGBIZRFIV2PS47B/graph.json","events_json":"https://pith.science/api/pith-number/WIR3XBQVHL4PGBIZRFIV2PS47B/events.json","paper":"https://pith.science/paper/WIR3XBQV"},"agent_actions":{"view_html":"https://pith.science/pith/WIR3XBQVHL4PGBIZRFIV2PS47B","download_json":"https://pith.science/pith/WIR3XBQVHL4PGBIZRFIV2PS47B.json","view_paper":"https://pith.science/paper/WIR3XBQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13386&json=true","fetch_graph":"https://pith.science/api/pith-number/WIR3XBQVHL4PGBIZRFIV2PS47B/graph.json","fetch_events":"https://pith.science/api/pith-number/WIR3XBQVHL4PGBIZRFIV2PS47B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIR3XBQVHL4PGBIZRFIV2PS47B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIR3XBQVHL4PGBIZRFIV2PS47B/action/storage_attestation","attest_author":"https://pith.science/pith/WIR3XBQVHL4PGBIZRFIV2PS47B/action/author_attestation","sign_citation":"https://pith.science/pith/WIR3XBQVHL4PGBIZRFIV2PS47B/action/citation_signature","submit_replication":"https://pith.science/pith/WIR3XBQVHL4PGBIZRFIV2PS47B/action/replication_record"}},"created_at":"2026-07-05T03:34:57.057907+00:00","updated_at":"2026-07-05T03:34:57.057907+00:00"}