-
Notifications
You must be signed in to change notification settings - Fork 27
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
add/fix things related to tensors and BLAS #228
base: master
Are you sure you want to change the base?
Conversation
jeffhammond
commented
May 10, 2022
•
edited
Loading
edited
- infintely is spelled wrong but also wrong in meaning. there are not infinitely more possibilities for tensors, merely combinatorially many more.
- tensors over BLAS is not optimal although it is common.
- added citations related to tensors and BLAS.
- GotoBLAS is obsolete. added OpenBLAS instead.
- added BLIS and citation.
infintely is spelled wrong but also wrong in meaning. there are not infinitely more possibilities for tensors, merely combinatorially many more.
1. tensors over BLAS is not optimal although it is common. 2. added citations related to tensors and BLAS. 3. GotoBLAS is obsolete. added OpenBLAS instead. 4. added BLIS and citation.
BLAS is an API. Netlib is an implementation. the vendors are implementing the BLAS API. they may or may not use code from Netlib (in some cases we know, in others not). also note that AMD forked BLIS, which is now cited elsewhere. AMD did not create BLIS.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @jeffhammond for the fixes! We should clarify that only P1673.bs needs to be edited. I'm not sure why we haven't deleted the old file blas_interface.md
yet. If you have the time, it would be excellent to delete it in this PR.
@@ -834,12 +835,16 @@ to some multi-indices in the Cartesian product of extents. | |||
### Tensors | |||
|
|||
We exclude tensors from this proposal, for the following reasons. | |||
First, tensor libraries naturally build on optimized dense linear | |||
First, tensor libraries often build on optimized dense linear | |||
algebra libraries like the BLAS, so a linear algebra library is a good |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
algebra libraries like the BLAS, so a linear algebra library is a good | |
algebra libraries like the BLAS. Thus, a linear algebra library is a good |
@@ -1597,7 +1602,7 @@ pioneering efforts and history lessons. | |||
SLATE Working Notes, Innovative Computing Laboratory, University of | |||
Tennessee Knoxville, Feb. 2018. | |||
|
|||
* K. Goto and R. A. van de Geijn, "Anatomy of high-performance matrix | |||
* K. Goto and R. A. van de Geijn, ["Anatomy of high-performance matrix |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good catch!
I added PR #231, which deletes the old |
PR ORNL#228 by Jeff Hammond suggests changes to P1673. Some of those can be applied to P1674 as well. This PR does that.
@jeffhammond FYI, we applied these changes to P1674, and deleted the old |