Avoid going through vst1_lane_u32 for gcc 14

Prefer a full lane store followed by a memcpy

Author: serge-sans-paille

include/xsimd/arch/xsimd_neon.hpp

@@ -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>

include/xsimd/arch/xsimd_neon64.hpp

@@ -274,15 +274,11 @@ namespace xsimd
          * store<batch_bool> *
          *********************/
 
-#if !defined(__GNUC__) && !defined(__clang__)
-        // FIXME: reproduce the issue and understand why it fails, see
-        // https://github.com/xtensor-stack/xsimd/issues/1232
         template <class A>
         XSIMD_INLINE void store(batch_bool<double, A> b, bool* mem, requires_arch<neon>) noexcept
         {
             store(batch_bool<uint64_t, A>(b.data), mem, A {});
         }
-#endif
 
         /****************
          * load_complex *