interleave2 Class — pytorch Architecture
Architecture documentation for the interleave2 class in vec_common_sve.h from the pytorch codebase.
Entity Profile
Source Code
aten/src/ATen/cpu/vec/sve/vec_common_sve.h lines 133–146
template <>
std::pair<Vectorized<double>, Vectorized<double>> inline interleave2<double>(
const Vectorized<double>& a,
const Vectorized<double>& b) {
// inputs:
// a = {a0, a1, a3, a3}
// b = {b0, b1, b2, b3}
// group cols crossing lanes:
// return {a0, b0, a1, b1}
// {a2, b2, a3, b3}
return std::make_pair(
Vectorized<double>(svzip1_f64(a, b)),
Vectorized<double>(svzip2_f64(a, b)));
}
Source
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free