Function f16x2_add

pub unsafe fn f16x2_add(a: f16x2, b: f16x2) -> f16x2

🔬This is a nightly-only experimental API. (stdarch_nvptx #111199)

Available on target_arch="nvptx64" only.

Add two values, round to nearest even

https://docs.nvidia.com/cuda/parallel-thread-execution/#half-precision-floating-point-instructions-add

Corresponds to the CUDA C intrinsics:

• __hadd2
• __hadd2_rn