CUDA Templates for Linear Algebra Subroutines and Solvers
Public Types | Public Member Functions | Static Public Member Functions | Static Public Attributes | List of all members
cutlass::NumericArrayConverter< half_t, float, 2, FloatRoundStyle::round_to_nearest > Struct Template Reference

Partial specialization for Array<half, 2> <= Array<float, 2>, round to nearest.

#include <numeric_conversion.h>

Public Types

using result_type = Array< half_t, 2 >
using source_type = Array< float, 2 >

Public Member Functions

CUTLASS_HOST_DEVICE result_type operator() (source_type const &s)

Static Public Member Functions

static CUTLASS_HOST_DEVICE result_type convert (source_type const &source)

Static Public Attributes

static FloatRoundStyle const round_style = FloatRoundStyle::round_to_nearest

Member Typedef Documentation

Member Function Documentation

Member Data Documentation

The documentation for this struct was generated from the following file: