Skip to content

fix: make the avx512vl_128 and avx512vl_256 arches build and pass #1400

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

Open
DiamonDinoia wants to merge 3 commits into
base: master
Choose a base branch
from
+12 −6
Open

fix: make the avx512vl_128 and avx512vl_256 arches build and pass #1400

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
65ab887
fix: declare incr_if and decr_if in the common forward header
DiamonDinoia Aug 12, 2026
42011ac
fix: correct the tobitset shift for 4 and 2 bool blocks
DiamonDinoia Aug 12, 2026
30140f4
fix: derive the sign mask in avx sadd/ssub from a comparison
DiamonDinoia Aug 12, 2026
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
8 changes: 4 additions & 4 deletions include/xsimd/arch/xsimd_avx.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1477,10 +1477,10 @@ namespace xsimd
{
if (std::is_signed_v<T>)
{
auto mask = (other >> (8 * sizeof(T) - 1));
auto negative = other < batch<T, A>(T(0));
auto self_pos_branch = min(std::numeric_limits<T>::max() - other, self);
auto self_neg_branch = max(std::numeric_limits<T>::min() - other, self);
return other + select(batch_bool<T, A>(mask.data), self_neg_branch, self_pos_branch);
return other + select(negative, self_neg_branch, self_pos_branch);
}
else
{
Expand Down Expand Up @@ -1728,10 +1728,10 @@ namespace xsimd
}
else if (std::is_signed_v<T>)
{
auto mask = (other >> (8 * sizeof(T) - 1));
auto negative = other < batch<T, A>(T(0));
auto self_overflow_branch = min(std::numeric_limits<T>::max() + other, self);
auto self_underflow_branch = max(std::numeric_limits<T>::min() + other, self);
return select(batch_bool<T, A>(mask.data), self_overflow_branch, self_underflow_branch) - other;
return select(negative, self_overflow_branch, self_underflow_branch) - other;
}
else
{
Expand Down
6 changes: 4 additions & 2 deletions include/xsimd/arch/xsimd_avx512f.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1544,6 +1544,8 @@ namespace xsimd
XSIMD_INLINE unsigned char tobitset(unsigned char unpacked[N])
{
static_assert(N == 8 || N == 4 || N == 2, "valid pack size");
// The multiply gathers the N selected bits into the top N bits
// of the 8 * N bit product, so the shift is 8 * N - N.
if constexpr (N == 8)
{
uint64_t data;
Expand All @@ -1561,7 +1563,7 @@ namespace xsimd

const uint32_t magic = (0x80 + 0x4000 + 0x200000 + 0x10000000);

unsigned char res = ((data * magic) >> 24) & 0xFF;
unsigned char res = ((data * magic) >> 28) & 0xFF;
return res;
}
else if constexpr (N == 2)
Expand All @@ -1571,7 +1573,7 @@ namespace xsimd

const uint16_t magic = (0x80 + 0x4000);

unsigned char res = ((data * magic) >> 8) & 0xFF;
unsigned char res = ((data * magic) >> 14) & 0xFF;
return res;
}
}
Expand Down
4 changes: 4 additions & 0 deletions include/xsimd/arch/xsimd_common_fwd.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,8 +60,12 @@ namespace xsimd
XSIMD_INLINE batch<T, A> bitwise_rshift(batch<T, A> const& self, batch<T, A> const& other, requires_arch<common>) noexcept;
template <size_t shift, class A, class T, class = std::enable_if_t<std::is_integral_v<T>>>
XSIMD_INLINE batch<T, A> bitwise_rshift(batch<T, A> const& self, requires_arch<common>) noexcept;
template <class A, class T, class Mask>
XSIMD_INLINE batch<T, A> decr_if(batch<T, A> const& self, Mask const& mask, requires_arch<common>) noexcept;
template <class A, class T>
XSIMD_INLINE batch_bool<T, A> gt(batch<T, A> const& self, batch<T, A> const& other, requires_arch<common>) 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<common>) noexcept;
template <class A, class T, class = std::enable_if_t<std::is_integral_v<T>>>
XSIMD_INLINE batch<T, A> mul(batch<T, A> const& self, batch<T, A> const& other, requires_arch<common>) noexcept;
template <class A, class T, class = std::enable_if_t<std::is_integral_v<T>>>
Expand Down
Loading