using eig to find the eigenvalues and eigenvectors of a large matrix on GPU

17 次查看（过去 30 天）

Qiu Xu 2021-10-23

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1569923-using-eig-to-find-the-eigenvalues-and-eigenvectors-of-a-large-matrix-on-gpu

评论： Matt J 2021-10-26

Hi,

I have matrix A with 7936*7936 dimensions. I use eig to find its eigenvalues and eigenvectors, the command is [vect,eigen]=eig(A). But if I perform this calculations on GPU, it is more slower than cpu. My code on GPU is as follows

A=rand(7936,7936,'gpuArray');

[vect,eigen]=eig(A);

I do not know why is this calculations on GPU is so slowly? Are there some other good methods to accelerate the eig on GPU?

Thanks very much!

2 个评论
显示无隐藏无

Walter Roberson 2021-10-23

For your purposes, could you switch to single precision?

Qiu Xu 2021-10-23

Thanks for your reply. I have tested for swithc the matrix to single, but is also very slowly, it looks like the GPU does not work, and the calclulation is still performed on CPU.

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Matt J 2021-10-23

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1569923-using-eig-to-find-the-eigenvalues-and-eigenvectors-of-a-large-matrix-on-gpu#answer_814728

编辑：Matt J 2021-10-23

It might be a question of your hardware. On the GTX 1050 in R2020b, I see only about a 10% speed-up in double precision and about 50% in single-precision. On the GTX 1080 Ti in R2020a, I see a factor of 2 speed-up at both precisions.

gd=gpuDevice;

Ac=rand(2500);

Ag=gpuArray(Ac);

tic;

[vect,eigen]=eig(Ac);

toc;

tic;

[vect,eigen]=eig(Ag);

wait(gd)

toc

Elapsed time is 9.484250 seconds.

Elapsed time is 5.183906 seconds.