# Performance Enhancement of the Ozaki Scheme on Integer Matrix Multiplication Unit

arXiv: https://arxiv.org/abs/2409.13313 · HTML: https://mlsanity.com/paper/2409.13313/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2024.

## Built on by (most cited first, 2 of 2)

- [Double-Precision Matrix Multiplication Emulation via Ozaki-II Scheme with FP8 Quantization](https://mlsanity.com/paper/2603.10634/) (2026)
- [MorphingNet: Symbolic Regression Where the Network Is the Formula](https://mlsanity.com/paper/2610.19942/) (2026)

## Abstract (arXiv)

This study was aimed at simultaneously achieving sufficient accuracy and high performance for general matrix multiplications. Recent architectures, such as NVIDIA GPUs, feature high-performance units designed for low-precision matrix multiplications in machine learning models, and next-generation architectures are expected to follow the same design principle. The key to achieving superior performance is to fully leverage such architectures. The Ozaki scheme, a highly accurate matrix multiplication algorithm using error-free transformations, enables higher-precision matrix multiplication to be performed through multiple lower-precision matrix multiplications and higher-precision matrix additions. Ootomo et al. implemented the Ozaki scheme on high-performance matrix multiplication units with the aim of achieving both sufficient accuracy and high performance. This paper proposes alternative approaches to improving performance by reducing the numbers of lower-precision matrix multiplications and higher-precision matrix additions. Numerical experiments demonstrate the accuracy of the results and conduct performance benchmarks of the proposed approaches. These approaches are expected to yield more efficient results in next-generation architectures.