{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C4HG2JNE5774UMUKYOX74OC74O","short_pith_number":"pith:C4HG2JNE","schema_version":"1.0","canonical_sha256":"170e6d25a4efffca328ac3affe385fe3a3c4266353cfe4b8e7ebccdef4db53e8","source":{"kind":"arxiv","id":"1901.00858","version":1},"attestation_state":"computed","paper":{"title":"HG-Caffe: Mobile and Embedded Neural Network GPU (OpenCL) Inference Engine with FP16 Supporting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Zhuoran Ji","submitted_at":"2019-01-03T03:39:12Z","abstract_excerpt":"Breakthroughs in the fields of deep learning and mobile system-on-chips are radically changing the way we use our smartphones. However, deep neural networks inference is still a challenging task for edge AI devices due to the computational overhead on mobile CPUs and a severe drain on the batteries. In this paper, we present a deep neural network inference engine named HG-Caffe, which supports GPUs with half precision. HG-Caffe provides up to 20 times speedup with GPUs compared to the original implementations. In addition to the speedup, the peak memory usage is also reduced to about 80%. With"},"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":"1901.00858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-03T03:39:12Z","cross_cats_sorted":[],"title_canon_sha256":"de885d96775b5b58a62d8bdf4a313bc25aa871446810f0fa267c7ec276762b90","abstract_canon_sha256":"f05efcb0c50c6c4549ac06c3d3244aca52770f665e9971002ca519eb87b7edee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:57.857955Z","signature_b64":"kFmxQ+OoSW27KNMZTkUlKRocUDUyI2arkLO6iOC9AKz+s2TfmG4lJL5m1mPLJNZ6ivsLQjCcoCDxNMdAhjUHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"170e6d25a4efffca328ac3affe385fe3a3c4266353cfe4b8e7ebccdef4db53e8","last_reissued_at":"2026-05-17T23:56:57.857264Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:57.857264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HG-Caffe: Mobile and Embedded Neural Network GPU (OpenCL) Inference Engine with FP16 Supporting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Zhuoran Ji","submitted_at":"2019-01-03T03:39:12Z","abstract_excerpt":"Breakthroughs in the fields of deep learning and mobile system-on-chips are radically changing the way we use our smartphones. However, deep neural networks inference is still a challenging task for edge AI devices due to the computational overhead on mobile CPUs and a severe drain on the batteries. In this paper, we present a deep neural network inference engine named HG-Caffe, which supports GPUs with half precision. HG-Caffe provides up to 20 times speedup with GPUs compared to the original implementations. In addition to the speedup, the peak memory usage is also reduced to about 80%. With"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00858","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":""},"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":"1901.00858","created_at":"2026-05-17T23:56:57.857394+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.00858v1","created_at":"2026-05-17T23:56:57.857394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00858","created_at":"2026-05-17T23:56:57.857394+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4HG2JNE5774","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4HG2JNE5774UMUK","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4HG2JNE","created_at":"2026-05-18T12:33:12.712433+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/C4HG2JNE5774UMUKYOX74OC74O","json":"https://pith.science/pith/C4HG2JNE5774UMUKYOX74OC74O.json","graph_json":"https://pith.science/api/pith-number/C4HG2JNE5774UMUKYOX74OC74O/graph.json","events_json":"https://pith.science/api/pith-number/C4HG2JNE5774UMUKYOX74OC74O/events.json","paper":"https://pith.science/paper/C4HG2JNE"},"agent_actions":{"view_html":"https://pith.science/pith/C4HG2JNE5774UMUKYOX74OC74O","download_json":"https://pith.science/pith/C4HG2JNE5774UMUKYOX74OC74O.json","view_paper":"https://pith.science/paper/C4HG2JNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.00858&json=true","fetch_graph":"https://pith.science/api/pith-number/C4HG2JNE5774UMUKYOX74OC74O/graph.json","fetch_events":"https://pith.science/api/pith-number/C4HG2JNE5774UMUKYOX74OC74O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4HG2JNE5774UMUKYOX74OC74O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4HG2JNE5774UMUKYOX74OC74O/action/storage_attestation","attest_author":"https://pith.science/pith/C4HG2JNE5774UMUKYOX74OC74O/action/author_attestation","sign_citation":"https://pith.science/pith/C4HG2JNE5774UMUKYOX74OC74O/action/citation_signature","submit_replication":"https://pith.science/pith/C4HG2JNE5774UMUKYOX74OC74O/action/replication_record"}},"created_at":"2026-05-17T23:56:57.857394+00:00","updated_at":"2026-05-17T23:56:57.857394+00:00"}