{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IYCOVIDBTTAGJW75AEQG7DZO6U","short_pith_number":"pith:IYCOVIDB","schema_version":"1.0","canonical_sha256":"4604eaa0619cc064dbfd01206f8f2ef51b58c12c8b8447fedc6fbb8c3c35b452","source":{"kind":"arxiv","id":"2606.11716","version":1},"attestation_state":"computed","paper":{"title":"A Fast Locality Simulator for GEMM Design-Space Exploration on Multi-Chiplet GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Euijun Chung, Hyesoon Kim","submitted_at":"2026-06-10T06:43:39Z","abstract_excerpt":"Multi-chiplet GPUs split memory into local and remote HBM regions across a silicon interposer, and reducing the remote HBM traffic is crucial for the performance and energy efficiency of multi-chiplet GPUs. For general matrix multiplication (GEMM), the dominant operator in large language models (LLMs), the resulting inter-chiplet traffic depends strongly on kernel choices such as operand layout, CTA traversal order, and data placement, and the optimal strategy to minimize remote accesses is nontrivial. We present a fast, functional, tile-level locality simulator that models CTA scheduling, per"},"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":"2606.11716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-10T06:43:39Z","cross_cats_sorted":[],"title_canon_sha256":"da9ee8e04b20c72bc8517c37ddc6ec2240e2d8bbaac118094a23098fa8b7fd47","abstract_canon_sha256":"59df1cdd0bee973558e58b37cb79cb56bc83240d66229081136f6c2496f5d4a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:04.458089Z","signature_b64":"USye3vT/LXJzWk7QwDdqTcxEoiattnd6EEaYIK6rd2MdNzNuCnY8adA7LI3Oxea1pLjjAzdgoiBa2+G+zLBVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4604eaa0619cc064dbfd01206f8f2ef51b58c12c8b8447fedc6fbb8c3c35b452","last_reissued_at":"2026-06-11T01:10:04.457062Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:04.457062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fast Locality Simulator for GEMM Design-Space Exploration on Multi-Chiplet GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Euijun Chung, Hyesoon Kim","submitted_at":"2026-06-10T06:43:39Z","abstract_excerpt":"Multi-chiplet GPUs split memory into local and remote HBM regions across a silicon interposer, and reducing the remote HBM traffic is crucial for the performance and energy efficiency of multi-chiplet GPUs. For general matrix multiplication (GEMM), the dominant operator in large language models (LLMs), the resulting inter-chiplet traffic depends strongly on kernel choices such as operand layout, CTA traversal order, and data placement, and the optimal strategy to minimize remote accesses is nontrivial. We present a fast, functional, tile-level locality simulator that models CTA scheduling, per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11716","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/2606.11716/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":"2606.11716","created_at":"2026-06-11T01:10:04.457203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11716v1","created_at":"2026-06-11T01:10:04.457203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11716","created_at":"2026-06-11T01:10:04.457203+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYCOVIDBTTAG","created_at":"2026-06-11T01:10:04.457203+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYCOVIDBTTAGJW75","created_at":"2026-06-11T01:10:04.457203+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYCOVIDB","created_at":"2026-06-11T01:10:04.457203+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/IYCOVIDBTTAGJW75AEQG7DZO6U","json":"https://pith.science/pith/IYCOVIDBTTAGJW75AEQG7DZO6U.json","graph_json":"https://pith.science/api/pith-number/IYCOVIDBTTAGJW75AEQG7DZO6U/graph.json","events_json":"https://pith.science/api/pith-number/IYCOVIDBTTAGJW75AEQG7DZO6U/events.json","paper":"https://pith.science/paper/IYCOVIDB"},"agent_actions":{"view_html":"https://pith.science/pith/IYCOVIDBTTAGJW75AEQG7DZO6U","download_json":"https://pith.science/pith/IYCOVIDBTTAGJW75AEQG7DZO6U.json","view_paper":"https://pith.science/paper/IYCOVIDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11716&json=true","fetch_graph":"https://pith.science/api/pith-number/IYCOVIDBTTAGJW75AEQG7DZO6U/graph.json","fetch_events":"https://pith.science/api/pith-number/IYCOVIDBTTAGJW75AEQG7DZO6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYCOVIDBTTAGJW75AEQG7DZO6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYCOVIDBTTAGJW75AEQG7DZO6U/action/storage_attestation","attest_author":"https://pith.science/pith/IYCOVIDBTTAGJW75AEQG7DZO6U/action/author_attestation","sign_citation":"https://pith.science/pith/IYCOVIDBTTAGJW75AEQG7DZO6U/action/citation_signature","submit_replication":"https://pith.science/pith/IYCOVIDBTTAGJW75AEQG7DZO6U/action/replication_record"}},"created_at":"2026-06-11T01:10:04.457203+00:00","updated_at":"2026-06-11T01:10:04.457203+00:00"}