Shall we add half_t support to Random<cpu, DType>
KiddoZhu opened this issue · 2 comments
KiddoZhu commented
Member functions in Random<cpu, DType>
are not overload for half_t
type. As a result, it fails when we use Random<cpu, half_t>
to generate a tensor. This is quite inconvenient for generating noise inside a mxnet operator that is templated by DType.
Shall we add half_t
support to Random<cpu, DType>
?
BiranLi commented
I think Random<gpu, DType> is important too.
It's not supported by curand function in CUDA9. But I support U.