{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C27SYLEIAXUFOSSJCS77DHWIPT","short_pith_number":"pith:C27SYLEI","schema_version":"1.0","canonical_sha256":"16bf2c2c8805e8574a4914bff19ec87ccfbdc43f1dcb3adccb967f6ac863da48","source":{"kind":"arxiv","id":"2303.04739","version":1},"attestation_state":"computed","paper":{"title":"Advancing Direct Convolution using Convolution Slicing Optimization and ISA Extensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.LG","cs.PF"],"primary_cat":"cs.CV","authors_text":"Guido Araujo, Jo\\~ao P. L. de Carvalho, Jos\\'e Moreira, Jos\\'e Nelson Amaral, Marcio Pereira, Rafael Sousa, Victor Ferrari","submitted_at":"2023-03-08T17:23:39Z","abstract_excerpt":"Convolution is one of the most computationally intensive operations that must be performed for machine-learning model inference. A traditional approach to compute convolutions is known as the Im2Col + BLAS method. This paper proposes SConv: a direct-convolution algorithm based on a MLIR/LLVM code-generation toolchain that can be integrated into machine-learning compilers . This algorithm introduces: (a) Convolution Slicing Analysis (CSA) - a convolution-specific 3D cache-blocking analysis pass that focuses on tile reuse over the cache hierarchy; (b) Convolution Slicing Optimization (CSO) - a c"},"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":"2303.04739","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-08T17:23:39Z","cross_cats_sorted":["cs.AR","cs.LG","cs.PF"],"title_canon_sha256":"b67fb9038b4a4e0c8427464eb938329fdf659b3ac44420280fa9cc0d72075959","abstract_canon_sha256":"e0fc31dffc1a536fb0908da3320882a60c5b3ab27b9c11c874bb1d1ac7571dcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:24.602083Z","signature_b64":"zE51Hg+hYJms7Rynh0+MMCHJsjNkxXpEsCYJOzf7YWVRPoPeMR2UxdDY8xN1KxIJVDCwAV7PS59yCbATj57jBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16bf2c2c8805e8574a4914bff19ec87ccfbdc43f1dcb3adccb967f6ac863da48","last_reissued_at":"2026-07-05T05:49:24.601672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:24.601672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Direct Convolution using Convolution Slicing Optimization and ISA Extensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.LG","cs.PF"],"primary_cat":"cs.CV","authors_text":"Guido Araujo, Jo\\~ao P. L. de Carvalho, Jos\\'e Moreira, Jos\\'e Nelson Amaral, Marcio Pereira, Rafael Sousa, Victor Ferrari","submitted_at":"2023-03-08T17:23:39Z","abstract_excerpt":"Convolution is one of the most computationally intensive operations that must be performed for machine-learning model inference. A traditional approach to compute convolutions is known as the Im2Col + BLAS method. This paper proposes SConv: a direct-convolution algorithm based on a MLIR/LLVM code-generation toolchain that can be integrated into machine-learning compilers . This algorithm introduces: (a) Convolution Slicing Analysis (CSA) - a convolution-specific 3D cache-blocking analysis pass that focuses on tile reuse over the cache hierarchy; (b) Convolution Slicing Optimization (CSO) - a c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04739","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/2303.04739/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":"2303.04739","created_at":"2026-07-05T05:49:24.601735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04739v1","created_at":"2026-07-05T05:49:24.601735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04739","created_at":"2026-07-05T05:49:24.601735+00:00"},{"alias_kind":"pith_short_12","alias_value":"C27SYLEIAXUF","created_at":"2026-07-05T05:49:24.601735+00:00"},{"alias_kind":"pith_short_16","alias_value":"C27SYLEIAXUFOSSJ","created_at":"2026-07-05T05:49:24.601735+00:00"},{"alias_kind":"pith_short_8","alias_value":"C27SYLEI","created_at":"2026-07-05T05:49:24.601735+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/C27SYLEIAXUFOSSJCS77DHWIPT","json":"https://pith.science/pith/C27SYLEIAXUFOSSJCS77DHWIPT.json","graph_json":"https://pith.science/api/pith-number/C27SYLEIAXUFOSSJCS77DHWIPT/graph.json","events_json":"https://pith.science/api/pith-number/C27SYLEIAXUFOSSJCS77DHWIPT/events.json","paper":"https://pith.science/paper/C27SYLEI"},"agent_actions":{"view_html":"https://pith.science/pith/C27SYLEIAXUFOSSJCS77DHWIPT","download_json":"https://pith.science/pith/C27SYLEIAXUFOSSJCS77DHWIPT.json","view_paper":"https://pith.science/paper/C27SYLEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04739&json=true","fetch_graph":"https://pith.science/api/pith-number/C27SYLEIAXUFOSSJCS77DHWIPT/graph.json","fetch_events":"https://pith.science/api/pith-number/C27SYLEIAXUFOSSJCS77DHWIPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C27SYLEIAXUFOSSJCS77DHWIPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C27SYLEIAXUFOSSJCS77DHWIPT/action/storage_attestation","attest_author":"https://pith.science/pith/C27SYLEIAXUFOSSJCS77DHWIPT/action/author_attestation","sign_citation":"https://pith.science/pith/C27SYLEIAXUFOSSJCS77DHWIPT/action/citation_signature","submit_replication":"https://pith.science/pith/C27SYLEIAXUFOSSJCS77DHWIPT/action/replication_record"}},"created_at":"2026-07-05T05:49:24.601735+00:00","updated_at":"2026-07-05T05:49:24.601735+00:00"}