dot_impl_floating Class — pytorch Architecture
Architecture documentation for the dot_impl_floating class in BlasKernel.cpp from the pytorch codebase.
Entity Profile
Source Code
aten/src/ATen/native/BlasKernel.cpp lines 671–687
template <typename scalar_t>
static scalar_t dot_impl_floating(int64_t n, const scalar_t* x, int64_t incx, const scalar_t* y, int64_t incy)
{
if (n == 1) {
incx = 1;
incy = 1;
}
#if AT_BUILD_WITH_BLAS()
if ((n <= INT_MAX) && (incx <= INT_MAX) && (incy <= INT_MAX)) {
return blas_impl::dot_fast_path(n, x, incx, y, incy);
} else {
return blas_impl::dot_naive(n, x, incx, y, incy, std::multiplies<scalar_t>{});
}
#else
{ return blas_impl::dot_naive(n, x, incx, y, incy, std::multiplies<scalar_t>{}); }
#endif
}
Source
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free