Skip to content
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

MKL library dependency #503

Closed
uu-praveeng opened this issue Jul 3, 2019 · 2 comments
Closed

MKL library dependency #503

uu-praveeng opened this issue Jul 3, 2019 · 2 comments
Assignees
Labels

Comments

@uu-praveeng
Copy link

Hi,

It appears that the latest release does not include the MKL libraries as a dependency .
We were using few APIs(vsAdd,vsMul) from the MKL library for elementwise addition and elementwise multiplication.
Could you let us know any APIs present in mkldnn to do the same ?
Are these APIs being merged into MKLDNN ?

Thank you,
Praveen.

@emfomenk
Copy link

emfomenk commented Jul 3, 2019

Hi @uu-praveeng,

Starting with Intel MKL-DNN v1.0 the library no more depends on Intel MKL. All the required implementations (mostly integer and floating point gemm) were ported directly to Intel MKL-DNN. So that's why we will stop publishing Intel MKL-ML small libraries here.

If you use Intel MKL functionality you can download it from one of the channels (see this answer).

vsAdd, vsMul are not in Intel MKL-DNN. We plan to add some generic tensor arithmetic primitives, and +/* would be there (which might be an overkill, though, you simply want to add/multiply two vectors unrelated to Intel MKL-DNN memory objects). But we don't have any timeline for that yet.

@emfomenk
Copy link

Close the issue since the question is answered.
Feel free to reopen or open a new one in case of additional questions.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

3 participants