Description Converts both components of float2 to nv_bfloat16 precision in round-to-nearest mode and combines the results into one nv_bfloat162 number. Low 16 bits of the return value correspond to a.x and high 16 bits of the return value correspond to a.y. __host__ __device__ __nv_bfloat16 __float2bfloat16 ( const float a )
Categories