Extend #1172 approach to arm

Author: serge-sans-paille

include/xsimd/arch/xsimd_neon.hpp

@@ -724,6 +724,28 @@ namespace xsimd
             store_complex_aligned(dst, src, A {});
         }
 
+        /*********************
+         * store<batch_bool> *
+         *********************/
+        template <class T, class A, detail::enable_sized_unsigned_t<T, 1> = 0>
+        XSIMD_INLINE void store(batch_bool<T, A> b, bool* mem, requires_arch<neon>) noexcept
+        {
+            uint8x16_t val = vsubq_u8(vdupq_n_u8(0), b);
+            vst1q_u8((unsigned char*)mem, val);
+        }
+        template <class T, class A, detail::enable_sized_signed_t<T, 1> = 0>
+        XSIMD_INLINE void store(batch_bool<T, A> b, bool* mem, requires_arch<neon>) noexcept
+        {
+            int8x16_t val = vsubq_s8(vdupq_n_s8(0), b);
+            vst1q_s8((signed char*)mem, val);
+        }
+
+        // template <class A>
+        // XSIMD_INLINE void store(batch_bool<float, A> b, bool* mem, requires_arch<sse2>) noexcept
+        //{
+        //     store(batch_bool<uint32_t, A>(b.data), mem, A {});
+        // }
+
         /*******
          * neg *
          *******/