Metraipolis › archive › dc_8488cbf6902f

zkDuel: Characterizing SumCheck Prover Kernels across GPU Programming Models — arXiv:2610.37710

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37710
License (as archived)
CC0-1.0
Archived
2026-10-31T06:19:42.939Z
SHA-256 of the archived text
c5059ecf069868bf3ee0433e1d2b85d9a3e78ca72c46065517e71bc473c40ddc
Stable URL of this page
https://metraipolis.com/documento/dc_8488cbf6902f

How to cite

zkDuel: Characterizing SumCheck Prover Kernels across GPU Programming Models — arXiv:2610.37710 — arXiv (en), https://arxiv.org/abs/2610.37710 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8488cbf6902f (Metraipolis archive dc_8488cbf6902f, sha256 c5059ecf069868bf3ee0433e1d2b85d9a3e78ca72c46065517e71bc473c40ddc)
BibTeX
@misc{dc8488cbf6902f,
  title = {zkDuel: Characterizing SumCheck Prover Kernels across GPU Programming Models — arXiv:2610.37710},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37710},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8488cbf6902f; sha256 c5059ecf069868bf3ee0433e1d2b85d9a3e78ca72c46065517e71bc473c40ddc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37710. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

SumCheck is a central prover primitive in zero-knowledge proofs, exposing table-parallel work that maps naturally to GPUs but becomes increasingly arithmetic-intensive as finite fields widen. We study how this shift affects the cost of programming SumCheck in Triton rather than CUDA. Our benchmark, zkDuel, provides matched implementations of 25 zkPHIRE-derived constraints alongside diagnostic polynomials, covering 32-, 64-, 128-, and 256-bit prime fields, with independent CPU-reference validation and cross-backend checksum gating. Of 800 configurations attempted on an NVIDIA H100, 758 complete with matching checksums. CUDA's median advantage over Triton falls from 3.5x at 32 bits to 1.4x at 256 bits, and Triton is faster on 19 large-table configurations; the same convergence appears on an A100, where the gap falls from 4.4x to 1.6x. Profiling shows that the small-field gap largely reflects host launch overhead and redundant modular additions in Triton's original block reduction, whose relative costs diminish as multi-limb Montgomery work grows. Replacing that reduction with this http URL brings Triton's median kernel time within 8% of CUDA on both GPUs, while specialized point interpolation improves 256-bit evaluation kernels by 1.55-1.75x. At cryptographic widths, these results show that a Python-embedded DSL can approach CUDA performance, although the largest fully unrolled constraints still expose compiler-scalability limits.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno).
Categorie arXiv: Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2610.37710 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T06:08:08.283Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).