pith:N5F57DHM
Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores
Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles.
arxiv:2512.00053 v3 · 2025-11-19 · cs.AR
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{N5F57DHM2NMYI7UUUIVPDV24EQ}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
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.
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.
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.
Formal links
Receipt and verification
| First computed | 2026-06-12T01:09:17.297750Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "894fbefdede516dc5790e0d6455a94ec946cb2cfcd4166046a9fc71ab9f75cd7",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AR",
"submitted_at": "2025-11-19T15:57:09Z",
"title_canon_sha256": "9a16540b679ce3b1d3f9b511bcb58992b05470451552dbf60d8f66c60b597aa9"
},
"schema_version": "1.0",
"source": {
"id": "2512.00053",
"kind": "arxiv",
"version": 3
}
}