std :: ml::gpu_rocm
Function std::rocm_half_gemm
int rocm_half_gemm(
struct RocmHalfBuf a,
int ta,
struct RocmHalfBuf b,
int tb,
struct RocmHalfBuf c,
unsigned long m,
unsigned long n,
unsigned long k,
)c[m,n] = op(a)[m,k] * op(b)[k,n], 16-bit a and b of the same dtype, fp32 accumulation; c in the same 16-bit dtype, or fp32 with _f32.