Skip to content

[ci] Add gcc 14 validation for arm #1241

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 3 commits into from
Apr 25, 2026
+14 −7
Merged

[ci] Add gcc 14 validation for arm #1241

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
f157e00
[ci] Add gcc 14 validation for arm
serge-sans-paille Jan 5, 2026
fc1ca1d
Force alignment of an aligned test
serge-sans-paille Apr 24, 2026
9aa226a
Avoid going through vst1_lane_u32 during batc_bool store on arm
serge-sans-paille Jan 22, 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
1 change: 1 addition & 0 deletions .github/workflows/cross-arm.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ jobs:
- { platform: 'aarch64', arch: 'armv8-a', dir: 'aarch64-linux-gnu', flags: '', full: 'ON' }
sys:
- { compiler: 'gcc', version: '10' }
- { compiler: 'gcc', version: '14' }
steps:
- name: Setup compiler
if: ${{ matrix.sys.compiler == 'gcc' }}
Expand Down
16 changes: 12 additions & 4 deletions include/xsimd/arch/xsimd_neon.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -766,28 +766,36 @@ namespace xsimd
XSIMD_INLINE void store(batch_bool<T, A> b, bool* mem, requires_arch<neon>) noexcept
{
uint8x16_t val = vshrq_n_u8(b.data, 7);
vst1q_u8((uint8_t*)mem, val);
alignas(A::alignment()) uint8_t buffer[batch_bool<T, A>::size];
vst1q_u8(buffer, val);
memcpy(mem, buffer, sizeof(buffer));
}

template <class T, class A, detail::enable_sized_t<T, 2> = 0>
XSIMD_INLINE void store(batch_bool<T, A> b, bool* mem, requires_arch<neon>) noexcept
{
uint8x8_t val = vshr_n_u8(vqmovn_u16(b.data), 7);
vst1_u8((uint8_t*)mem, val);
alignas(A::alignment()) uint8_t buffer[batch_bool<T, A>::size];
vst1_u8(buffer, val);
memcpy(mem, buffer, sizeof(buffer));
}

template <class T, class A, detail::enable_sized_t<T, 4> = 0>
XSIMD_INLINE void store(batch_bool<T, A> b, bool* mem, requires_arch<neon>) noexcept
{
uint8x8_t val = vshr_n_u8(vqmovn_u16(vcombine_u16(vqmovn_u32(b.data), vdup_n_u16(0))), 7);
vst1_lane_u32((uint32_t*)mem, vreinterpret_u32_u8(val), 0);
alignas(A::alignment()) uint8_t buffer[8];
vst1_u8(buffer, val);
memcpy(mem, buffer, batch_bool<T, A>::size);
}

template <class T, class A, detail::enable_sized_t<T, 8> = 0>
XSIMD_INLINE void store(batch_bool<T, A> b, bool* mem, requires_arch<neon>) noexcept
{
uint8x8_t val = vshr_n_u8(vqmovn_u16(vcombine_u16(vqmovn_u32(vcombine_u32(vqmovn_u64(b.data), vdup_n_u32(0))), vdup_n_u16(0))), 7);
vst1_lane_u16((uint16_t*)mem, vreinterpret_u16_u8(val), 0);
alignas(A::alignment()) uint8_t buffer[8];
vst1_u8(buffer, val);
memcpy(mem, buffer, batch_bool<T, A>::size);
}

template <class A>
Expand Down
4 changes: 1 addition & 3 deletions test/test_api.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,7 +138,7 @@ struct xsimd_api_test
batch_type b = batch_type::load(v.data(), xsimd::aligned_mode());
V res(size);

bool* b_data = new bool[size];
alignas(arch_type::alignment()) bool b_data[size];

xsimd::store_as(res.data(), b, xsimd::unaligned_mode());
INFO(name, " unaligned");
Expand All @@ -159,8 +159,6 @@ struct xsimd_api_test
xsimd::store_as(b_data, bb, xsimd::aligned_mode());
INFO(name, " batch_bool aligned");
CHECK_UNARY(std::accumulate(b_data, b_data + size, true, std::logical_and<bool>()));

delete[] b_data;
}

template <class T>
Expand Down
Loading