GPU backslash performance much slower than CPU

9 visualizaciones (últimos 30 días)
Meme Young
Meme Young el 27 de Dic. de 2020
Editada: Matt J el 26 de Mayo de 2022
I am doing numerical power flow caclulation by modifying the functions of matpower, an open source toolbox. By modifying its function newtonpf.m, GPU computation can be implemented. However, I found that GPU performance is much much slower than CPU. When calculating the built-in case3012wp of matpower, the matrix in newtonpf.m will be :
A: 5725 * 5725 sparse double, b: 5725 * 1 double.
The process of A \ b in the 1st iteration of newtonpf() will generally take around 0.01 sec on my i7-10750H + RTX 2070super MSI-GL65.
But if A and b are changed into GPU arrays, the process of A \ b will take the following time if A is the following types:
full double, 0.8 sec
sparse double, 4 sec
full single, 0.1 sec
(sparse single is not supported)
So why is the diference in performance? I thought GPU could do things much faster than CPU.
Files are attached as follows. Atest is sparse and Agpu is a sparse gpu array. All are doubles.
  9 comentarios
kant
kant el 26 de Mayo de 2022
I also have this problem for my matlab code? Has the problem been solved?
Matt J
Matt J el 26 de Mayo de 2022
Editada: Matt J el 26 de Mayo de 2022
@kant It has been concluded that this is expected behavior, but see below.

Iniciar sesión para comentar.

Respuestas (1)

Matt J
Matt J el 27 de Dic. de 2020
This thread looks relevant. It appears that sparse mldivide on the GPU is not expected to be faster.
  13 comentarios
Meme Young
Meme Young el 30 de Dic. de 2020
What do you mean sparse solver algorithm Mr Knight? like pcg()? I have tried it is not as efficient as this way: reordering using amd(), LU decomp, and two backslashes based on the decomp, especially when coping with the type of sparse matrix that I uploaded
Joss Knight
Joss Knight el 10 de En. de 2021
Editada: Joss Knight el 10 de En. de 2021
Yes, PCG, GMRES, CGS, LSQR, QMR, TFQMR, BICG, BICGSTAB. Try them all, play with tolerance, iterations and preconditioning - something is likely to work. I'm not an expert in this field but this is what the sparse community tend to do.

Iniciar sesión para comentar.

Categorías

Más información sobre Sparse Matrices en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by