![]() |
imate
C++/CUDA Reference
|


Go to the source code of this file.
Namespaces | |
| namespace | cu_arithmetic |
perform arithmetics for __half and __nv_bfloat16 types in round-to-nearest-even mode. | |
| namespace | cu_arithmetics |
Cast from float to __half and __nv_bfloat16 types and vice-versa, and float to double and vice-versa. | |
Functions | |
| template<typename DataType > | |
| __host__ __device__ DataType | cu_arithmetics::sub (const DataType x, const DataType y) |
| Subtract two floating point numbers in round-to-nearest-even mode. | |
| template<> | |
| __host__ __device__ float | cu_arithmetics::sub< float > (const float x, const float y) |
Subtract two __nv_fp8_e5m2 type numbers in round-to-nearest-even mode. | |
| template<> | |
| __host__ __device__ double | cu_arithmetics::sub< double > (const double x, const double y) |
Subtract two double type float numbers. | |