{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QTJH5BAWVL2TMTKJOSQSO2TULT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7b7416dc2dbeb13add6bc12b55b00fa68e8a7e68494170307dadb33023f1cde9","cross_cats_sorted":["cs.AI","cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T06:32:47Z","title_canon_sha256":"b7487ea4f7d832ab4653ed1c5560cad0ed291f57a03234df7b6e6768b993d432"},"schema_version":"1.0","source":{"id":"2410.23668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23668","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23668v1","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23668","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_12","alias_value":"QTJH5BAWVL2T","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_16","alias_value":"QTJH5BAWVL2TMTKJ","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_8","alias_value":"QTJH5BAW","created_at":"2026-07-05T09:29:03Z"}],"graph_snapshots":[{"event_id":"sha256:9583f9e51db4f83def681f739058b390460751e30416cdb2151fa507a1f4f0f5","target":"graph","created_at":"2026-07-05T09:29:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.23668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Token generation speed is critical to power the next wave of AI inference applications. GPUs significantly underperform during token generation due to synchronization overheads at kernel boundaries, utilizing only 21% of their peak memory bandwidth. While recent dataflow architectures mitigate these overheads by enabling aggressive fusion of decoder layers into a single kernel, they too leave performance on the table due to synchronization penalties at layer boundaries.\n  This paper presents kernel looping, a specialized global optimization technique which exploits an optimization opportunity ","authors_text":"Angela Wang, Darshan Gandhi, David Koeplinger, Han Wang, Leon Zhang, Matheen Musaddiq, Matthew Shaffer, Mingran Wang, Nathan Sheeley, Pushkar Nandkar, Raghu Prabhakar, Reid Goodbar","cross_cats":["cs.AI","cs.AR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T06:32:47Z","title":"Kernel Looping: Eliminating Synchronization Boundaries for Peak Inference Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23668","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:28de729486831a83539201bb55a7d9bcf8981426b0707e42ef486e143f73da96","target":"record","created_at":"2026-07-05T09:29:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7b7416dc2dbeb13add6bc12b55b00fa68e8a7e68494170307dadb33023f1cde9","cross_cats_sorted":["cs.AI","cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T06:32:47Z","title_canon_sha256":"b7487ea4f7d832ab4653ed1c5560cad0ed291f57a03234df7b6e6768b993d432"},"schema_version":"1.0","source":{"id":"2410.23668","kind":"arxiv","version":1}},"canonical_sha256":"84d27e8416aaf5364d4974a1276a745cf20d03aa1dc22332e3b939cd2399fa92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84d27e8416aaf5364d4974a1276a745cf20d03aa1dc22332e3b939cd2399fa92","first_computed_at":"2026-07-05T09:29:03.634671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:03.634671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KxszhKTL/4DtvhrGfdXfAPA8R+5f1vz/F2/h5niFL8UW+kd36ks4zF0Tair+Dd669rD8UlkJ7qiFv/IV+kX7Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:03.635177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28de729486831a83539201bb55a7d9bcf8981426b0707e42ef486e143f73da96","sha256:9583f9e51db4f83def681f739058b390460751e30416cdb2151fa507a1f4f0f5"],"state_sha256":"0e7d32b2a0377a07e53afbee20dd50b4e109f237516ac93de7e49865a0d70c2e"}