{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4IP6B5HFI43UTGGUPX7FUGKJEL","short_pith_number":"pith:4IP6B5HF","schema_version":"1.0","canonical_sha256":"e21fe0f4e547374998d47dfe5a194922e6d4f0715ed70642f65e43bfc479e2a8","source":{"kind":"arxiv","id":"2009.02381","version":2},"attestation_state":"computed","paper":{"title":"Sparse Systolic Tensor Array for Efficient CNN Hardware Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Matthew Mattina, Paul N. Whatmough, Zhi-Gang Liu","submitted_at":"2020-09-04T20:17:42Z","abstract_excerpt":"Convolutional neural network (CNN) inference on mobile devices demands efficient hardware acceleration of low-precision (INT8) general matrix multiplication (GEMM). Exploiting data sparsity is a common approach to further accelerate GEMM for CNN inference, and in particular, structural sparsity has the advantages of predictable load balancing and very low index overhead. In this paper, we address a key architectural challenge with structural sparsity: how to provide support for a range of sparsity levels while maintaining high utilization of the hardware. We describe a time unrolled formulatio"},"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":"2009.02381","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2020-09-04T20:17:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"868c354600124263e2458280640ba0978302d2b042165b0cd7ffc31c91b852c6","abstract_canon_sha256":"70314d26091b0e04b462013ac3039af9a809cc5a8af991056714e34a456fbd6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:21.673370Z","signature_b64":"K8v3QyaEAUaqD8RGpmJSoqnLaiVXm/rVviuHvnaHBhr5ty/PvYkzpbzWuHHKEKj0sXFMPL+RyQo7vINqvMdbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e21fe0f4e547374998d47dfe5a194922e6d4f0715ed70642f65e43bfc479e2a8","last_reissued_at":"2026-07-05T01:42:21.672823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:21.672823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Systolic Tensor Array for Efficient CNN Hardware Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Matthew Mattina, Paul N. Whatmough, Zhi-Gang Liu","submitted_at":"2020-09-04T20:17:42Z","abstract_excerpt":"Convolutional neural network (CNN) inference on mobile devices demands efficient hardware acceleration of low-precision (INT8) general matrix multiplication (GEMM). Exploiting data sparsity is a common approach to further accelerate GEMM for CNN inference, and in particular, structural sparsity has the advantages of predictable load balancing and very low index overhead. In this paper, we address a key architectural challenge with structural sparsity: how to provide support for a range of sparsity levels while maintaining high utilization of the hardware. We describe a time unrolled formulatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.02381","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/2009.02381/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":"2009.02381","created_at":"2026-07-05T01:42:21.672894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.02381v2","created_at":"2026-07-05T01:42:21.672894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.02381","created_at":"2026-07-05T01:42:21.672894+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IP6B5HFI43U","created_at":"2026-07-05T01:42:21.672894+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IP6B5HFI43UTGGU","created_at":"2026-07-05T01:42:21.672894+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IP6B5HF","created_at":"2026-07-05T01:42:21.672894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03763","citing_title":"Systolic Sparse Tensor Slices: FPGA Building Blocks for Sparse and Dense AI Acceleration","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL","json":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL.json","graph_json":"https://pith.science/api/pith-number/4IP6B5HFI43UTGGUPX7FUGKJEL/graph.json","events_json":"https://pith.science/api/pith-number/4IP6B5HFI43UTGGUPX7FUGKJEL/events.json","paper":"https://pith.science/paper/4IP6B5HF"},"agent_actions":{"view_html":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL","download_json":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL.json","view_paper":"https://pith.science/paper/4IP6B5HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.02381&json=true","fetch_graph":"https://pith.science/api/pith-number/4IP6B5HFI43UTGGUPX7FUGKJEL/graph.json","fetch_events":"https://pith.science/api/pith-number/4IP6B5HFI43UTGGUPX7FUGKJEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL/action/storage_attestation","attest_author":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL/action/author_attestation","sign_citation":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL/action/citation_signature","submit_replication":"https://pith.science/pith/4IP6B5HFI43UTGGUPX7FUGKJEL/action/replication_record"}},"created_at":"2026-07-05T01:42:21.672894+00:00","updated_at":"2026-07-05T01:42:21.672894+00:00"}