Skip to content

Add insert&incr_if&decr_if in avx512 #1096

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 4 commits into from
Mar 24, 2025
Merged

Add insert&incr_if&decr_if in avx512 #1096

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5252a08
support insert in avx512
junparser Mar 18, 2025
b7e46e3
support incr_if&decr_if in avx512
junparser Mar 18, 2025
16633e7
fix build warning as error
junparser Mar 19, 2025
fcb6313
use bit_cast for type convert
junparser Mar 21, 2025
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
56 changes: 56 additions & 0 deletions include/xsimd/arch/xsimd_avx512bw.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -224,6 +224,25 @@ namespace xsimd
}
}

// decr_if
template <class A, class T, class = typename std::enable_if<std::is_integral<T>::value, void>::type>
XSIMD_INLINE batch<T, A> decr_if(batch<T, A> const& self, batch_bool<T, A> const& mask, requires_arch<avx512bw>) noexcept
{

XSIMD_IF_CONSTEXPR(sizeof(T) == 1)
{
return _mm512_mask_sub_epi8(self, mask.data, self, _mm512_set1_epi8(1));
}
else XSIMD_IF_CONSTEXPR(sizeof(T) == 2)
{
return _mm512_mask_sub_epi16(self, mask.data, self, _mm512_set1_epi16(1));
}
else
{
return decr_if(self, mask, avx512dq {});
}
}

// eq
template <class A, class T, class = typename std::enable_if<std::is_integral<T>::value, void>::type>
XSIMD_INLINE batch_bool<T, A> eq(batch<T, A> const& self, batch<T, A> const& other, requires_arch<avx512bw>) noexcept
Expand All @@ -245,6 +264,43 @@ namespace xsimd
return detail::compare_int_avx512bw<A, T, _MM_CMPINT_GT>(self, other);
}

// incr_if
template <class A, class T, class = typename std::enable_if<std::is_integral<T>::value, void>::type>
XSIMD_INLINE batch<T, A> incr_if(batch<T, A> const& self, batch_bool<T, A> const& mask, requires_arch<avx512bw>) noexcept
{

XSIMD_IF_CONSTEXPR(sizeof(T) == 1)
{
return _mm512_mask_add_epi8(self, mask.data, self, _mm512_set1_epi8(1));
}
else XSIMD_IF_CONSTEXPR(sizeof(T) == 2)
{
return _mm512_mask_add_epi16(self, mask.data, self, _mm512_set1_epi16(1));
}
else
{
return incr_if(self, mask, avx512dq {});
}
}

// insert
template <class A, class T, size_t I, class = typename std::enable_if<std::is_integral<T>::value, void>::type>
XSIMD_INLINE batch<T, A> insert(batch<T, A> const& self, T val, index<I> pos, requires_arch<avx512bw>) noexcept
{
XSIMD_IF_CONSTEXPR(sizeof(T) == 1)
{
return _mm512_mask_set1_epi8(self, __mmask64(1ULL << (I & 63)), val);
}
else XSIMD_IF_CONSTEXPR(sizeof(T) == 2)
{
return _mm512_mask_set1_epi16(self, __mmask32(1 << (I & 31)), val);
}
else
{
return insert(self, val, pos, avx512dq {});
}
}

// le
template <class A, class T, class = typename std::enable_if<std::is_integral<T>::value, void>::type>
XSIMD_INLINE batch_bool<T, A> le(batch<T, A> const& self, batch<T, A> const& other, requires_arch<avx512bw>) noexcept
Expand Down
75 changes: 75 additions & 0 deletions include/xsimd/arch/xsimd_avx512f.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,12 @@ namespace xsimd
using namespace types;

// fwd
template <class A, class T, class Mask>
XSIMD_INLINE batch<T, A> decr_if(batch<T, A> const& self, Mask const& mask, requires_arch<generic>) noexcept;
template <class A, class T, class Mask>
XSIMD_INLINE batch<T, A> incr_if(batch<T, A> const& self, Mask const& mask, requires_arch<generic>) noexcept;
template <class A, class T, size_t I>
XSIMD_INLINE batch<T, A> insert(batch<T, A> const& self, T val, index<I>, requires_arch<generic>) noexcept;
template <class A>
XSIMD_INLINE void transpose(batch<uint16_t, A>* matrix_begin, batch<uint16_t, A>* matrix_end, requires_arch<generic>) noexcept;
template <class A>
Expand Down Expand Up @@ -757,6 +763,24 @@ namespace xsimd
return _mm512_permutex2var_pd(self.real(), idx, self.imag());
}
}
// incr_if
template <class A, class T, class = typename std::enable_if<std::is_integral<T>::value, void>::type>
XSIMD_INLINE batch<T, A> decr_if(batch<T, A> const& self, batch_bool<T, A> const& mask, requires_arch<avx512f>) noexcept
{

XSIMD_IF_CONSTEXPR(sizeof(T) == 4)
{
return _mm512_mask_sub_epi32(self, mask.data, self, _mm512_set1_epi32(1));
}
else XSIMD_IF_CONSTEXPR(sizeof(T) == 8)
{
return _mm512_mask_sub_epi64(self, mask.data, self, _mm512_set1_epi64(1));
}
else
{
return decr_if(self, mask, generic {});
}
}

// div
template <class A>
Expand Down Expand Up @@ -1073,6 +1097,57 @@ namespace xsimd
return _mm512_add_pd(tmpx, tmpy);
}

// incr_if
template <class A, class T, class = typename std::enable_if<std::is_integral<T>::value, void>::type>
XSIMD_INLINE batch<T, A> incr_if(batch<T, A> const& self, batch_bool<T, A> const& mask, requires_arch<avx512f>) noexcept
{

XSIMD_IF_CONSTEXPR(sizeof(T) == 4)
{
return _mm512_mask_add_epi32(self, mask.data, self, _mm512_set1_epi32(1));
}
else XSIMD_IF_CONSTEXPR(sizeof(T) == 8)
{
return _mm512_mask_add_epi64(self, mask.data, self, _mm512_set1_epi64(1));
}
else
{
return incr_if(self, mask, generic {});
}
}

// insert
template <class A, size_t I>
XSIMD_INLINE batch<float, A> insert(batch<float, A> const& self, float val, index<I>, requires_arch<avx512f>) noexcept
{

int32_t tmp = bit_cast<int32_t>(val);
return _mm512_castsi512_ps(_mm512_mask_set1_epi32(_mm512_castps_si512(self), __mmask16(1 << (I & 15)), tmp));
}

template <class A, size_t I>
XSIMD_INLINE batch<double, A> insert(batch<double, A> const& self, double val, index<I>, requires_arch<avx512f>) noexcept
{
int64_t tmp = bit_cast<int64_t>(val);
return _mm512_castsi512_pd(_mm512_mask_set1_epi64(_mm512_castpd_si512(self), __mmask8(1 << (I & 7)), tmp));
}
template <class A, class T, size_t I, class = typename std::enable_if<std::is_integral<T>::value, void>::type>
XSIMD_INLINE batch<T, A> insert(batch<T, A> const& self, T val, index<I> pos, requires_arch<avx512f>) noexcept
{
XSIMD_IF_CONSTEXPR(sizeof(T) == 4)
{
return _mm512_mask_set1_epi32(self, __mmask16(1 << (I & 15)), val);
}
else XSIMD_IF_CONSTEXPR(sizeof(T) == 8)
{
return _mm512_mask_set1_epi64(self, __mmask8(1 << (I & 7)), val);
}
else
{
return insert(self, val, pos, generic {});
}
}

// isnan
template <class A>
XSIMD_INLINE batch_bool<float, A> isnan(batch<float, A> const& self, requires_arch<avx512f>) noexcept
Expand Down