{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6OVEHRYCGRTZTAF6XA3PKL5ZGX","short_pith_number":"pith:6OVEHRYC","schema_version":"1.0","canonical_sha256":"f3aa43c70234679980beb836f52fb935ddee426f32b2d3644e2ef40d1c59f068","source":{"kind":"arxiv","id":"2607.11603","version":1},"attestation_state":"computed","paper":{"title":"WarpMPC: Large-Batch MPC on GPU via ADMM with Unrolled $LDL^\\top$ Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.RO","authors_text":"Charles Khazoom, Henrik Hose, Sangbae Kim, Sebastian Trimpe, Se Hwan Jeon","submitted_at":"2026-07-13T14:27:47Z","abstract_excerpt":"This paper introduces numerical optimizations for maximizing throughput on GPU when solving large batches (10,000 to over 100,000) of sequential quadratic programming (SQP) iterations, where all problems have the same structure. The optimizations are implemented in a toolbox WarpMPC for model-predictive control (MPC) in JAX and Warp. Based on the insight that all MPC problem instances in a batch share the same sparsity in time, cost, and constraints, we propose unrolling sparse linear factorizations and solves, which dominate alternating direction method of multipliers (ADMM) solver runtime. W"},"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":"2607.11603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-13T14:27:47Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"6432a151b5c421ed59301d1af81b77c59e7e48466552961d58b208bd77bd9172","abstract_canon_sha256":"495b3965d9bea7953bd8947df8587a81b5733fc103c7e22f323d7fbba4b3d61c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:14.523412Z","signature_b64":"scyt+vH7d/0eHa/ZQGF2wahHNE/SqqrUVfW5ChQcIiJxIAxCfuzDsOSXPKu4nj0HnWaZwZQiIXLUPR/hJkgfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3aa43c70234679980beb836f52fb935ddee426f32b2d3644e2ef40d1c59f068","last_reissued_at":"2026-07-14T02:22:14.522387Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:14.522387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WarpMPC: Large-Batch MPC on GPU via ADMM with Unrolled $LDL^\\top$ Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.RO","authors_text":"Charles Khazoom, Henrik Hose, Sangbae Kim, Sebastian Trimpe, Se Hwan Jeon","submitted_at":"2026-07-13T14:27:47Z","abstract_excerpt":"This paper introduces numerical optimizations for maximizing throughput on GPU when solving large batches (10,000 to over 100,000) of sequential quadratic programming (SQP) iterations, where all problems have the same structure. The optimizations are implemented in a toolbox WarpMPC for model-predictive control (MPC) in JAX and Warp. Based on the insight that all MPC problem instances in a batch share the same sparsity in time, cost, and constraints, we propose unrolling sparse linear factorizations and solves, which dominate alternating direction method of multipliers (ADMM) solver runtime. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11603","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/2607.11603/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":"2607.11603","created_at":"2026-07-14T02:22:14.522974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11603v1","created_at":"2026-07-14T02:22:14.522974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11603","created_at":"2026-07-14T02:22:14.522974+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OVEHRYCGRTZ","created_at":"2026-07-14T02:22:14.522974+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OVEHRYCGRTZTAF6","created_at":"2026-07-14T02:22:14.522974+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OVEHRYC","created_at":"2026-07-14T02:22:14.522974+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/6OVEHRYCGRTZTAF6XA3PKL5ZGX","json":"https://pith.science/pith/6OVEHRYCGRTZTAF6XA3PKL5ZGX.json","graph_json":"https://pith.science/api/pith-number/6OVEHRYCGRTZTAF6XA3PKL5ZGX/graph.json","events_json":"https://pith.science/api/pith-number/6OVEHRYCGRTZTAF6XA3PKL5ZGX/events.json","paper":"https://pith.science/paper/6OVEHRYC"},"agent_actions":{"view_html":"https://pith.science/pith/6OVEHRYCGRTZTAF6XA3PKL5ZGX","download_json":"https://pith.science/pith/6OVEHRYCGRTZTAF6XA3PKL5ZGX.json","view_paper":"https://pith.science/paper/6OVEHRYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11603&json=true","fetch_graph":"https://pith.science/api/pith-number/6OVEHRYCGRTZTAF6XA3PKL5ZGX/graph.json","fetch_events":"https://pith.science/api/pith-number/6OVEHRYCGRTZTAF6XA3PKL5ZGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OVEHRYCGRTZTAF6XA3PKL5ZGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OVEHRYCGRTZTAF6XA3PKL5ZGX/action/storage_attestation","attest_author":"https://pith.science/pith/6OVEHRYCGRTZTAF6XA3PKL5ZGX/action/author_attestation","sign_citation":"https://pith.science/pith/6OVEHRYCGRTZTAF6XA3PKL5ZGX/action/citation_signature","submit_replication":"https://pith.science/pith/6OVEHRYCGRTZTAF6XA3PKL5ZGX/action/replication_record"}},"created_at":"2026-07-14T02:22:14.522974+00:00","updated_at":"2026-07-14T02:22:14.522974+00:00"}