{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZBINGEWDZYKQCXEOTMMZ7EV5HA","short_pith_number":"pith:ZBINGEWD","schema_version":"1.0","canonical_sha256":"c850d312c3ce15015c8e9b199f92bd383466230d340aac581d4569e8dec8d671","source":{"kind":"arxiv","id":"2307.04995","version":1},"attestation_state":"computed","paper":{"title":"PowerFusion: A Tensor Compiler with Explicit Data Movement Description and Instruction-level Graph IR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Chen Zhang, Haojie Wang, Huanqi Cao, Jidong Zhai, Jingze Xing, Kezhao Huang, Liyan Zheng, Penghan Wang, Shizhi Tang, Zixuan Ma","submitted_at":"2023-07-11T03:17:40Z","abstract_excerpt":"Deep neural networks (DNNs) are of critical use in different domains. To accelerate DNN computation, tensor compilers are proposed to generate efficient code on different domain-specific accelerators. Existing tensor compilers mainly focus on optimizing computation efficiency. However, memory access is becoming a key performance bottleneck because the computational performance of accelerators is increasing much faster than memory performance. The lack of direct description of memory access and data dependence in current tensor compilers' intermediate representation (IR) brings significant chal"},"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":"2307.04995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-11T03:17:40Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"b70068c41035f1e6477f09c95a3427e59f29024b4b437927cd17f034e507a155","abstract_canon_sha256":"0bc597cb4cada83239c9d5a98c6dace2c653722f70a0bedd704f50dd0089cf8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:24.565182Z","signature_b64":"E2v/pkL5/A17YtPSqGuJOyVtOcRTurRcL7UH/2kIIOYJy7qGMjZr9B35UjiQE+j/g6UY7UpHjJb9CYOzeoWoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c850d312c3ce15015c8e9b199f92bd383466230d340aac581d4569e8dec8d671","last_reissued_at":"2026-07-05T06:29:24.564578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:24.564578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PowerFusion: A Tensor Compiler with Explicit Data Movement Description and Instruction-level Graph IR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Chen Zhang, Haojie Wang, Huanqi Cao, Jidong Zhai, Jingze Xing, Kezhao Huang, Liyan Zheng, Penghan Wang, Shizhi Tang, Zixuan Ma","submitted_at":"2023-07-11T03:17:40Z","abstract_excerpt":"Deep neural networks (DNNs) are of critical use in different domains. To accelerate DNN computation, tensor compilers are proposed to generate efficient code on different domain-specific accelerators. Existing tensor compilers mainly focus on optimizing computation efficiency. However, memory access is becoming a key performance bottleneck because the computational performance of accelerators is increasing much faster than memory performance. The lack of direct description of memory access and data dependence in current tensor compilers' intermediate representation (IR) brings significant chal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04995","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/2307.04995/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":"2307.04995","created_at":"2026-07-05T06:29:24.564652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04995v1","created_at":"2026-07-05T06:29:24.564652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04995","created_at":"2026-07-05T06:29:24.564652+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBINGEWDZYKQ","created_at":"2026-07-05T06:29:24.564652+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBINGEWDZYKQCXEO","created_at":"2026-07-05T06:29:24.564652+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBINGEWD","created_at":"2026-07-05T06:29:24.564652+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/ZBINGEWDZYKQCXEOTMMZ7EV5HA","json":"https://pith.science/pith/ZBINGEWDZYKQCXEOTMMZ7EV5HA.json","graph_json":"https://pith.science/api/pith-number/ZBINGEWDZYKQCXEOTMMZ7EV5HA/graph.json","events_json":"https://pith.science/api/pith-number/ZBINGEWDZYKQCXEOTMMZ7EV5HA/events.json","paper":"https://pith.science/paper/ZBINGEWD"},"agent_actions":{"view_html":"https://pith.science/pith/ZBINGEWDZYKQCXEOTMMZ7EV5HA","download_json":"https://pith.science/pith/ZBINGEWDZYKQCXEOTMMZ7EV5HA.json","view_paper":"https://pith.science/paper/ZBINGEWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04995&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBINGEWDZYKQCXEOTMMZ7EV5HA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBINGEWDZYKQCXEOTMMZ7EV5HA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBINGEWDZYKQCXEOTMMZ7EV5HA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBINGEWDZYKQCXEOTMMZ7EV5HA/action/storage_attestation","attest_author":"https://pith.science/pith/ZBINGEWDZYKQCXEOTMMZ7EV5HA/action/author_attestation","sign_citation":"https://pith.science/pith/ZBINGEWDZYKQCXEOTMMZ7EV5HA/action/citation_signature","submit_replication":"https://pith.science/pith/ZBINGEWDZYKQCXEOTMMZ7EV5HA/action/replication_record"}},"created_at":"2026-07-05T06:29:24.564652+00:00","updated_at":"2026-07-05T06:29:24.564652+00:00"}