Showing results for

- Intel Community
- Software
- Software Development SDKs and Libraries
- Intel® oneAPI Math Kernel Library
- Intel MKL BSR sparse matrix product operations

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Mute
- Printer Friendly Page

Sérgio_Caldas

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-26-2016
01:30 PM

102 Views

Intel MKL BSR sparse matrix product operations

hello,

In a Msc. project we are implementing hadarmard, kathri-rao, and kronecker products on BSR sparse matrices. Is there any paper/reference regarding the algorithms implemented in the normal Intel MKL Sparse MX * MX multiplication.

Regards,

Sérgio Caldas

Link Copied

2 Replies

Alexander_K_Intel2

Employee

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-27-2016
01:51 AM

102 Views

Hi Sergio,

We cannot share algorithm used in MKL except general words. In any case, which case of matrix multiplication you interested in, matrix vector, matrix mult sparse matrix or matrix mult dense matrix?

Thanks,

Alex

Sérgio_Caldas

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-27-2016
03:41 AM

102 Views

Hi Alex,

We are interested in sparse matrix matrix multiplication.

We are also preceding in another way into correction. We are investigating the possibility of defining these product (hadamard, kronecker, kathri-rao) from LA transformations and then normal matrix multiplication.

If you have any articles regarding this approach please refer them,

Regards,

Sergio Caldas

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

For more complete information about compiler optimizations, see our Optimization Notice.