pytorch Architecture Docs
Home / Class/ lapack_work_to_int Class — pytorch Architecture

lapack_work_to_int Class — pytorch Architecture

Architecture documentation for the lapack_work_to_int class in BatchLinearAlgebraKernel.cpp from the pytorch codebase.

Class cpp

Entity Profile

Source Code

aten/src/ATen/native/BatchLinearAlgebraKernel.cpp lines 201–206

template <typename T>
inline
std::enable_if_t<std::is_floating_point_v<T>, int> lapack_work_to_int(const T val) {
    const auto next_after = std::nextafter(val, std::numeric_limits<T>::infinity());
    return std::max<int>(1, std::ceil(next_after));
}

Source

Analyze Your Own Codebase

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

Try Supermodel Free