- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
It seems that MKL_DIRECT_CALL does not apply to zgemm3 and cgemm3, only zgemm and cgemm
It seems slightly annoying that this is not the case as zgemm3 is significantly more numerically efficient for large matrices and is therefore a replacement for zgemm and it would have been helpful for MKL_DIRECT_CALL to switch calls of zgemm3 as well as zgemm for small matrices
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
you right, this optimization would be added later into one of the next versions. We will update this record accordingly.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Great! At the moment I do my own test of the sizes and switch to zgemm3 for N>128 (say)
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
To make sure we understand your request correctly, you use zgemm instead of zgemm3m if the matrices are smaller than 128, right? And, you would like MKL_DIRECT_CALL feature to do a similar transformation if the matrices are small enough?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
In my existing code, I only call zgemm3 - never zgemm
I want to use MKL_DIRECT_CALL but since MKL_DIRECT_CALL does not support zgemm3, I have added wrapper code that calls zgemm3 for N>=128, and zgemm for N<128
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thank you for the details! I got it know. Please let us know if there are other high priority routines that the MKL_DIRECT_CALL feature would help.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Andrew, please check how it works with the latest MKL 11.2 update 2 which has been released the last week.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Yes, direct call to zgemm3/cgemm3 works great in the latest update to MKL.
thank you!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Andrew, Thanks for nice words about Intel(R) MKL. Please don't hesitate report us any issues. regards, Gennady

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