arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.08321cs.DC
收藏

基于中国剩余定理的复杂矩阵乘法仿真

Emulation of Complex Matrix Multiplication based on the Chinese Remainder Theorem

RIKEN Center for Computational Science(理化学研究所计算科学中心);Department of Mathematical Science Shibaura Institute of Technology(芝浦工业大学数理科学系);Computer Science Department Ecole Normale Superieure de Lyon(里昂高等师范学校计算机科学系)

Yuki Uchino, Qianxiang Ma, Toshiyuki Imamura, Katsuhisa Ozaki, Patrick Lars Gutsche

AI总结:

本文基于Ozaki-II框架,提出在INT8矩阵引擎上实现单/双精度复数矩阵乘法的高效仿真方法,实现在NVIDIA B200 GPU上达到4.4-6.5倍和4.0-5.6倍的速度提升,同时兼顾精度与能效。

摘要:

现代计算架构具有低精度矩阵乘法单元,其吞吐量显著高于高精度单元。受此趋势启发,利用低精度硬件模拟高精度矩阵乘法在高性能计算领域受到广泛关注。Ozaki、Uchino和Imamura提出了Ozaki-II方案作为通用模拟框架。在此基础上,Uchino、Ozaki和Imamura开发了在INT8矩阵引擎上实现单/双精度实矩阵乘法的高性能且节能技术。延续这一研究,本文提出基于Ozaki-II方案的高精度复数矩阵乘法仿真方法。在NVIDIA B200 GPU上,所提方法在足够大的问题规模下,相较于cuBLAS的原生单/双精度复数矩阵乘法例行程序分别实现4.4-6.5倍和4.0-5.6倍的速度提升。当允许低于标准例行程序精度时,所提方法可进一步提高速度。相反,仅在计算时间上适度增加,即可提供比标准例行程序更高的精度。这些特性表明,所提方法有潜力成为广泛应用中的默认算法。

英文摘要:

Modern computing architectures feature low-precision matrix multiplication units that achieve substantially higher throughput than their high-precision counterparts. Motivated by this architectural trend, the emulation of high-precision matrix multiplication using low-precision hardware has attracted significant interest in the high-performance computing community. Ozaki, Uchino, and Imamura proposed the Ozaki-II scheme as a general framework for emulating matrix multiplication. Building on this framework, Uchino, Ozaki, and Imamura developed high-performance and power-efficient techniques for emulating single- and double-precision real matrix multiplication on INT8 matrix engines. Extending this line of research, the present study proposes high-performance emulation methods for single- and double-precision complex matrix multiplication on INT8 matrix engines, based on the Ozaki-II scheme. On an NVIDIA B200 GPU, the proposed methods achieve 4.4--6.5x and 4.0--5.6x speedups over the native single- and double-precision complex matrix multiplication routines from cuBLAS, respectively, for sufficiently large problem sizes. When lower accuracy than that of the standard routines is acceptable, the proposed methods can operate at even higher speed. Conversely, with only a modest increase in computation time, they can deliver higher accuracy than that of the standard routines. These properties suggest that the proposed approach has the potential to serve as a default algorithm across a wide range of applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑