{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GUUXOCCFRO6QNSWHN4W7PJJYKW","short_pith_number":"pith:GUUXOCCF","canonical_record":{"source":{"id":"2308.15152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-08-29T09:34:18Z","cross_cats_sorted":[],"title_canon_sha256":"5bd737426369361029ad4a5ed2dd6575fe61289fc027c71496212d7222a138f9","abstract_canon_sha256":"7d8be162aea2ad0816b648cc0027f8749e7b9590c4463fd454e11a119fc5cf0c"},"schema_version":"1.0"},"canonical_sha256":"35297708458bbd06cac76f2df7a538559c6ea02648e4716cc656aa39ce55851e","source":{"kind":"arxiv","id":"2308.15152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15152","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15152v1","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15152","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"pith_short_12","alias_value":"GUUXOCCFRO6Q","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"pith_short_16","alias_value":"GUUXOCCFRO6QNSWH","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"pith_short_8","alias_value":"GUUXOCCF","created_at":"2026-07-05T06:45:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GUUXOCCFRO6QNSWHN4W7PJJYKW","target":"record","payload":{"canonical_record":{"source":{"id":"2308.15152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-08-29T09:34:18Z","cross_cats_sorted":[],"title_canon_sha256":"5bd737426369361029ad4a5ed2dd6575fe61289fc027c71496212d7222a138f9","abstract_canon_sha256":"7d8be162aea2ad0816b648cc0027f8749e7b9590c4463fd454e11a119fc5cf0c"},"schema_version":"1.0"},"canonical_sha256":"35297708458bbd06cac76f2df7a538559c6ea02648e4716cc656aa39ce55851e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:44.115472Z","signature_b64":"Mfd4IaWo06K6rjz6IkYRx5pnud44qR2h6gt7Dk/kNuttSKFr2322I96NGxYXMKFody1jWu8ZdpRSHP7lw/nRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35297708458bbd06cac76f2df7a538559c6ea02648e4716cc656aa39ce55851e","last_reissued_at":"2026-07-05T06:45:44.115025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:44.115025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.15152","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J++WoWM+zoiS8fcaQjG01jOzqx7XDYLcVhJCY32hBpKa4W7teAFdG1eT9pa4zknqJFPyJpJWsorMZ5tzCYhDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:06:40.780518Z"},"content_sha256":"eec9f9b5f84f3a43b7acd388a023035049fb8a77eb1ad50bfe60219399842d7a","schema_version":"1.0","event_id":"sha256:eec9f9b5f84f3a43b7acd388a023035049fb8a77eb1ad50bfe60219399842d7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GUUXOCCFRO6QNSWHN4W7PJJYKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reducing shared memory footprint to leverage high throughput on Tensor Cores and its flexible API extension library","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hiroyuki Ootomo, Rio Yokota","submitted_at":"2023-08-29T09:34:18Z","abstract_excerpt":"NVIDIA Tensor Core is a mixed-precision matrix-matrix multiplication and addition computing unit, where the theoretical peak performance is more than 300 TFlop/s on NVIDIA A100 GPU. NVIDIA provides WMMA API for using Tensor Cores in custom kernel functions. The most common way to use Tensor Core is to supply the input matrices from shared memory, which has higher bandwidth than global memory. However, the Bytes-per-Flops (B/F) ratio of the shared memory and Tensor Cores is small since the performance of Tensor Cores is high. Thus, it is important to reduce the shared memory footprint for effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15152","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/2308.15152/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pw0542YQOqNP5/KobC53GxSmpVmijY3PcRKxiwglyPUyE6dltGp2stmvqb8qwt+iUq3tul2VfkKYfaVLoGCbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:06:40.781303Z"},"content_sha256":"753a19d427fb8f90d344dc853cf2d46a5f533baa11c3acc63eb64907c144ea63","schema_version":"1.0","event_id":"sha256:753a19d427fb8f90d344dc853cf2d46a5f533baa11c3acc63eb64907c144ea63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUUXOCCFRO6QNSWHN4W7PJJYKW/bundle.json","state_url":"https://pith.science/pith/GUUXOCCFRO6QNSWHN4W7PJJYKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUUXOCCFRO6QNSWHN4W7PJJYKW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T19:06:40Z","links":{"resolver":"https://pith.science/pith/GUUXOCCFRO6QNSWHN4W7PJJYKW","bundle":"https://pith.science/pith/GUUXOCCFRO6QNSWHN4W7PJJYKW/bundle.json","state":"https://pith.science/pith/GUUXOCCFRO6QNSWHN4W7PJJYKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUUXOCCFRO6QNSWHN4W7PJJYKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GUUXOCCFRO6QNSWHN4W7PJJYKW","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":"7d8be162aea2ad0816b648cc0027f8749e7b9590c4463fd454e11a119fc5cf0c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-08-29T09:34:18Z","title_canon_sha256":"5bd737426369361029ad4a5ed2dd6575fe61289fc027c71496212d7222a138f9"},"schema_version":"1.0","source":{"id":"2308.15152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15152","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15152v1","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15152","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"pith_short_12","alias_value":"GUUXOCCFRO6Q","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"pith_short_16","alias_value":"GUUXOCCFRO6QNSWH","created_at":"2026-07-05T06:45:44Z"},{"alias_kind":"pith_short_8","alias_value":"GUUXOCCF","created_at":"2026-07-05T06:45:44Z"}],"graph_snapshots":[{"event_id":"sha256:753a19d427fb8f90d344dc853cf2d46a5f533baa11c3acc63eb64907c144ea63","target":"graph","created_at":"2026-07-05T06:45:44Z","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/2308.15152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"NVIDIA Tensor Core is a mixed-precision matrix-matrix multiplication and addition computing unit, where the theoretical peak performance is more than 300 TFlop/s on NVIDIA A100 GPU. NVIDIA provides WMMA API for using Tensor Cores in custom kernel functions. The most common way to use Tensor Core is to supply the input matrices from shared memory, which has higher bandwidth than global memory. However, the Bytes-per-Flops (B/F) ratio of the shared memory and Tensor Cores is small since the performance of Tensor Cores is high. Thus, it is important to reduce the shared memory footprint for effic","authors_text":"Hiroyuki Ootomo, Rio Yokota","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-08-29T09:34:18Z","title":"Reducing shared memory footprint to leverage high throughput on Tensor Cores and its flexible API extension library"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15152","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:eec9f9b5f84f3a43b7acd388a023035049fb8a77eb1ad50bfe60219399842d7a","target":"record","created_at":"2026-07-05T06:45:44Z","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":"7d8be162aea2ad0816b648cc0027f8749e7b9590c4463fd454e11a119fc5cf0c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-08-29T09:34:18Z","title_canon_sha256":"5bd737426369361029ad4a5ed2dd6575fe61289fc027c71496212d7222a138f9"},"schema_version":"1.0","source":{"id":"2308.15152","kind":"arxiv","version":1}},"canonical_sha256":"35297708458bbd06cac76f2df7a538559c6ea02648e4716cc656aa39ce55851e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35297708458bbd06cac76f2df7a538559c6ea02648e4716cc656aa39ce55851e","first_computed_at":"2026-07-05T06:45:44.115025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:44.115025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mfd4IaWo06K6rjz6IkYRx5pnud44qR2h6gt7Dk/kNuttSKFr2322I96NGxYXMKFody1jWu8ZdpRSHP7lw/nRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:44.115472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.15152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eec9f9b5f84f3a43b7acd388a023035049fb8a77eb1ad50bfe60219399842d7a","sha256:753a19d427fb8f90d344dc853cf2d46a5f533baa11c3acc63eb64907c144ea63"],"state_sha256":"e5aba9371b66e9f4e01d04e2ed4d265338ffbae55de080b0cad5115865dbbbcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDOBjdEcsCzXjxnkrRrL+UGsw2mGpjiEKw4CFVL/CsJOJ6ebeQxKR4HD8S0N9cy6lSoDStu+8oFuc/RcclCuCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:06:40.788196Z","bundle_sha256":"77b2fbaaa4ade5b9ad723d668b7365e54b05ab574d529ef3e7b8e8f9e8e88c66"}}