Skip to content

Faster reduce_add on avx #1112

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
serge-sans-paille merged 1 commit into from
Apr 27, 2025
Merged

Faster reduce_add on avx #1112

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 2 additions & 20 deletions include/xsimd/arch/xsimd_avx.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1046,31 +1046,13 @@ namespace xsimd
}

// reduce_add
template <class A>
XSIMD_INLINE float reduce_add(batch<float, A> const& rhs, requires_arch<avx>) noexcept
{
// Warning about _mm256_hadd_ps:
// _mm256_hadd_ps(a,b) gives
// (a0+a1,a2+a3,b0+b1,b2+b3,a4+a5,a6+a7,b4+b5,b6+b7). Hence we can't
// rely on a naive use of this method
// rhs = (x0, x1, x2, x3, x4, x5, x6, x7)
// tmp = (x4, x5, x6, x7, x0, x1, x2, x3)
__m256 tmp = _mm256_permute2f128_ps(rhs, rhs, 1);
// tmp = (x4+x0, x5+x1, x6+x2, x7+x3, x0+x4, x1+x5, x2+x6, x3+x7)
tmp = _mm256_add_ps(rhs, tmp);
// tmp = (x4+x0+x5+x1, x6+x2+x7+x3, -, -, -, -, -, -)
tmp = _mm256_hadd_ps(tmp, tmp);
// tmp = (x4+x0+x5+x1+x6+x2+x7+x3, -, -, -, -, -, -, -)
tmp = _mm256_hadd_ps(tmp, tmp);
return _mm_cvtss_f32(_mm256_extractf128_ps(tmp, 0));
}
template <class A, class T, class = typename std::enable_if<std::is_integral<T>::value || std::is_same<T, double>::value, void>::type>
template <class A, class T, class = typename std::enable_if<std::is_integral<T>::value || std::is_same<T, float>::value || std::is_same<T, double>::value, void>::type>
XSIMD_INLINE T reduce_add(batch<T, A> const& self, requires_arch<avx>) noexcept
{
typename batch<T, sse4_2>::register_type low, high;
detail::split_avx(self, low, high);
batch<T, sse4_2> blow(low), bhigh(high);
return reduce_add(blow) + reduce_add(bhigh);
return reduce_add(blow + bhigh);
}

// reduce_max
Expand Down