Each matrix is approximately 500 MB. Dimensions are roughly 2 million rows by 2 million columns. I'm only planning to use a single x86 processor, and I'd like to use either gcc or g++ as a compiler.
I've been considering SparseLib++, but I can't find any reviews of it. Is there something more mainstream?
"Which C/C++ libraries are the fastest at multiplying very sparse matrices?
SparseLib++ is good
else
why do not you write the code youself using
linklist multiplication?
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment