maximum Class — pytorch Architecture

Architecture documentation for the maximum class in vec128_half_neon.h from the pytorch codebase.

Class c

Entity Profile

Source Code

aten/src/ATen/cpu/vec/vec128/vec128_half_neon.h lines 464–477

template <>
Vectorized<c10::Half> inline maximum(
    const Vectorized<c10::Half>& a,
    const Vectorized<c10::Half>& b) {
#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
  return Vectorized<c10::Half>(vmaxq_f16(a, b));
#else
  return binary_operator_via_float(
      static_cast<Vectorized<float> (*)(
          const Vectorized<float>&, const Vectorized<float>&)>(&maximum),
      a,
      b);
#endif
}

Source

View on GitHub

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free