JuliaGPU/CUDA.jl

Schur decomposition

Open

#2,077 创建于 2023年9月11日

在 GitHub 查看
 (1 评论) (0 反应) (0 负责人)Julia (274 fork)batch import
enhancementhelp wanted

仓库指标

Star
 (1,408 star)
PR 合并指标
 (平均合并 5天 5小时) (30 天内合并 16 个 PR)

描述

Schur decomposition is implemented efficiently on GPU in PyTorch, Jax, and MatLab. It is an essential ingredient for the efficient computation of matrix square root (sqrtm).

It would be ideal to have this decomposition implemented directly in CUDA.jl. The only alternative I see at the moment is full-on diagonalization which is less efficient and less stable.

贡献者指南