Rewrite kron with broadcasting at::mul (#50927)
Summary:
Because it is shorter, faster, and does not have TF32 issue.
Benchmark: https://github.com/zasdfgbnm/things/blob/master/2021Q1/kron.ipynb
Pull Request resolved: https://github.com/pytorch/pytorch/pull/50927
Reviewed By: glaringlee
Differential Revision: D26022385
Pulled By: ngimel
fbshipit-source-id: 513c9e9138c35c70d3a475a8407728af21321dae
