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
I was planning to make a wrapper for MKL - which would include much more than BLAS - but I could not find the time yet. I think it should be doable reasonably with c2nim; at least I was able to wrap CUDA rather comfortably after making some extension to c2nim itself. Maybe you want to try? ;-)
Would be nice to have some BLAS extensions like right now I would use
cblas_?gemm_batch
andcblas_gemm_s16s16s32
from MKL.See
https://software.intel.com/en-us/mkl-developer-reference-c-cblas-gemm-batch
https://software.intel.com/en-us/mkl-developer-reference-c-cblas-gemm-1
Although they are available only for people using MKL.
The text was updated successfully, but these errors were encountered: