{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N5F57DHM2NMYI7UUUIVPDV24EQ","short_pith_number":"pith:N5F57DHM","schema_version":"1.0","canonical_sha256":"6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76","source":{"kind":"arxiv","id":"2512.00053","version":3},"attestation_state":"computed","paper":{"title":"Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles.","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Blaise Tine, Nikhil Rout","submitted_at":"2025-11-19T15:57:09Z","abstract_excerpt":"Efficient mixed-precision MMA operations are critical for accelerating deep learning workloads on GPGPUs. However, existing open-source Tensor Core implementations rely on discrete arithmetic unit designs, leading to high latency, accumulated rounding errors, and poor resource utilization. To address these challenges, we propose Ten-Four, a configurable mixed-precision fused dot product unit integrating both floating-point and integer arithmetic pipelines within a unified architecture, implemented as part of the open-source RISC-V-based Vortex GPGPU's Tensor Core Unit extension. It supports lo"},"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":true},"canonical_record":{"source":{"id":"2512.00053","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-11-19T15:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"9a16540b679ce3b1d3f9b511bcb58992b05470451552dbf60d8f66c60b597aa9","abstract_canon_sha256":"894fbefdede516dc5790e0d6455a94ec946cb2cfcd4166046a9fc71ab9f75cd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:17.298653Z","signature_b64":"AKNGRuiYTar2h4Ym3tf6ZmPz9bv8/gWvUfq/o92QnwrE7Kn3sKuFRDGU3gUV8dSW82JWxb9DiJUvV4XMlgDHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76","last_reissued_at":"2026-06-12T01:09:17.297750Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:17.297750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles.","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Blaise Tine, Nikhil Rout","submitted_at":"2025-11-19T15:57:09Z","abstract_excerpt":"Efficient mixed-precision MMA operations are critical for accelerating deep learning workloads on GPGPUs. However, existing open-source Tensor Core implementations rely on discrete arithmetic unit designs, leading to high latency, accumulated rounding errors, and poor resource utilization. To address these challenges, we propose Ten-Four, a configurable mixed-precision fused dot product unit integrating both floating-point and integer arithmetic pipelines within a unified architecture, implemented as part of the open-source RISC-V-based Vortex GPGPU's Tensor Core Unit extension. It supports lo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Ten-Four achieves 4-cycle operation latency at 262.325 MHz Fmax, delivering 134.308 GFLOPS peak throughput per Tensor Core on the AMD Xilinx Alveo U55C FPGA, demonstrating ~3.1x performance improvement over an equivalent Berkeley HardFloat-based implementation at less than 60% the area cost.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the fused pipeline preserves exact numerical equivalence to discrete units across all supported formats (FP16/BF16/FP8/BF8/INT8/INT4) without hidden rounding differences that only appear under specific input patterns or when integrated into the full Vortex Tensor Core.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Ten-Four delivers a fused mixed-precision dot-product unit for open-source GPGPUs that runs in 4 cycles at 262 MHz, matches NVIDIA numerical accuracy, and uses less than 60% the area of a prior open implementation while delivering 3.1x higher throughput.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"330ed9e535d85a13fd73b3f1f1b2561ef556128a1ec8af7593e0595485888f78"},"source":{"id":"2512.00053","kind":"arxiv","version":3},"verdict":{"id":"c7a68bf3-5005-48d4-8b28-716166a6e185","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T20:32:14.255485Z","strongest_claim":"Ten-Four achieves 4-cycle operation latency at 262.325 MHz Fmax, delivering 134.308 GFLOPS peak throughput per Tensor Core on the AMD Xilinx Alveo U55C FPGA, demonstrating ~3.1x performance improvement over an equivalent Berkeley HardFloat-based implementation at less than 60% the area cost.","one_line_summary":"Ten-Four delivers a fused mixed-precision dot-product unit for open-source GPGPUs that runs in 4 cycles at 262 MHz, matches NVIDIA numerical accuracy, and uses less than 60% the area of a prior open implementation while delivering 3.1x higher throughput.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the fused pipeline preserves exact numerical equivalence to discrete units across all supported formats (FP16/BF16/FP8/BF8/INT8/INT4) without hidden rounding differences that only appear under specific input patterns or when integrated into the full Vortex Tensor Core.","pith_extraction_headline":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.00053/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":2,"snapshot_sha256":"3f3a1ec68ad5750dd2f34c0e4c70f0eb7c36de5975423351257c572d3726c114"},"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":"2512.00053","created_at":"2026-06-12T01:09:17.297857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.00053v3","created_at":"2026-06-12T01:09:17.297857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.00053","created_at":"2026-06-12T01:09:17.297857+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5F57DHM2NMY","created_at":"2026-06-12T01:09:17.297857+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5F57DHM2NMYI7UU","created_at":"2026-06-12T01:09:17.297857+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5F57DHM","created_at":"2026-06-12T01:09:17.297857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ","json":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ.json","graph_json":"https://pith.science/api/pith-number/N5F57DHM2NMYI7UUUIVPDV24EQ/graph.json","events_json":"https://pith.science/api/pith-number/N5F57DHM2NMYI7UUUIVPDV24EQ/events.json","paper":"https://pith.science/paper/N5F57DHM"},"agent_actions":{"view_html":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ","download_json":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ.json","view_paper":"https://pith.science/paper/N5F57DHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.00053&json=true","fetch_graph":"https://pith.science/api/pith-number/N5F57DHM2NMYI7UUUIVPDV24EQ/graph.json","fetch_events":"https://pith.science/api/pith-number/N5F57DHM2NMYI7UUUIVPDV24EQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/action/storage_attestation","attest_author":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/action/author_attestation","sign_citation":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/action/citation_signature","submit_replication":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/action/replication_record"}},"created_at":"2026-06-12T01:09:17.297857+00:00","updated_at":"2026-06-12T01:09:17.297857+00:00"}