std1.0.0-beta-7 SafeC docs

std :: ml::gpu_cuda

Function std::cuda_half_add

#include <std/ml/gpu_cuda.h> source ยท definition

int cuda_half_add(struct CudaHalfBuf a, struct CudaHalfBuf b, struct CudaHalfBuf out)

16-bit elementwise ops (fp32 arithmetic, one rounding per value; a, b and out of one dtype and a.len elements).