method · first seen 4 Oct 2026
Ozaki scheme
Also: OzII, Ozaki-II, Ozaki emulation, Ozaki scheme II
A technique that performs high-precision matrix multiplication using lower-precision integer matrix multiply units via residue number representations.
Mentions per week
PapersCodeDiscussion
Earliest sources
- You Only Convert Twice: Ozaki Scheme II for Chained Tensor Mode ProductsPapers · 4 Oct 2026 · Xuanzhengbo Ren
- The Missing Fourth Term for the Emulation Tensor Memory Equilibrium (TME) Model: The Residue Deconstruction CostPapers · 7 Oct 2026 · Harun Bayraktar, John Gunnels, Peter Caday
- Emulating DGEMM and ZGEMM with INT8 Matrix Engines on Intel Arc GPUs: Ozaki Scheme II on the Xe2 ArchitecturePapers · 18 Oct 2026 · Rostislavs Rostovskis, Aleksandrs Platonenko
- Accelerating SO(2)-Equivariant Materials Models through Low-Precision EmulationPapers · 26 Oct 2026 · Denghui Lu, Alexander Maeder, Alexandros Nikolaos Ziogas, Mathieu Luisier, Manas…
- FP64 Performance and the Limits of Ozaki Emulation on HPC SystemsPapers · 9 Nov 2026 · Katarzyna, Swirydowicz, Nicholas Malaya, Noah Wolfe, Paul Bauman, Pieter Ghysels…
- AdaMenu: Query-Adaptive Menus for Decision Models over Large Label SpacesPapers · 13 Nov 2026 · Jiangze Yan, Yi Shen, Jieyun Huang, Wenjing Zhang, Zhaoxiang Liu, Ning Wang, Kai…
Latest sources
- Providing Accuracy Guarantees for the Fixed-Point Emulation of Matrix MultiplicationPapers · 13 Nov 2026 · Cole Brower, Peter Caday, John Gunnels
- AdaMenu: Query-Adaptive Menus for Decision Models over Large Label SpacesPapers · 13 Nov 2026 · Jiangze Yan, Yi Shen, Jieyun Huang, Wenjing Zhang, Zhaoxiang Liu, Ning Wang, Kai…
- FP64 Performance and the Limits of Ozaki Emulation on HPC SystemsPapers · 9 Nov 2026 · Katarzyna, Swirydowicz, Nicholas Malaya, Noah Wolfe, Paul Bauman, Pieter Ghysels…
- Accelerating SO(2)-Equivariant Materials Models through Low-Precision EmulationPapers · 26 Oct 2026 · Denghui Lu, Alexander Maeder, Alexandros Nikolaos Ziogas, Mathieu Luisier, Manas…
- Emulating DGEMM and ZGEMM with INT8 Matrix Engines on Intel Arc GPUs: Ozaki Scheme II on the Xe2 ArchitecturePapers · 18 Oct 2026 · Rostislavs Rostovskis, Aleksandrs Platonenko
- The Missing Fourth Term for the Emulation Tensor Memory Equilibrium (TME) Model: The Residue Deconstruction CostPapers · 7 Oct 2026 · Harun Bayraktar, John Gunnels, Peter Caday
- You Only Convert Twice: Ozaki Scheme II for Chained Tensor Mode ProductsPapers · 4 Oct 2026 · Xuanzhengbo Ren