You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
The text was updated successfully, but these errors were encountered:
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.
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.
The text was updated successfully, but these errors were encountered: