-
Notifications
You must be signed in to change notification settings - Fork 157
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
const scaling paramters not supported for gemm_batch #447
Comments
@AidanBeltonS This looks like a real gap. Thanks for reporting this. We will take a look. For non-array parameters, we typically don't use |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Summary
gemm_batch and possibly other batch methods do not allow
const Ts*
types for thealpha
andbeta
scaling parameters. I believe this should be the case as it is documented within the oneMKL spec. I also believe this to be a reasonable parameter argument as alpha and beta are read only data types and therefore should not be modified. My reference: https://www.intel.com/content/www/us/en/docs/onemkl/developer-reference-dpcpp/2023-0/gemm-batch.htmlVersion
oneMKL hash: 7d2044e
Environment
oneMKL works with multiple HW and backend libraries and also depends on the
compiler and build environment. Include
the following information to help reproduce the issue:
Steps to reproduce
Compile with for NVidia GPUs:
icpx -fsycl -fsycl-targets=nvptx64-nvidia-cuda reproducer_onemkl_batch.cpp -lonemkl
or for Intel GPUs:
icpx -fsycl reproducer_onemkl_batch.cpp -lonemkl
Error:
I would expect this to compile based upon the documentation linked and the fact the parameter is read only
The text was updated successfully, but these errors were encountered: