++

Author: serge-sans-paille

include/xsimd/arch/xsimd_neon.hpp

@@ -730,24 +730,31 @@ namespace xsimd
         template <class T, class A, detail::enable_sized_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.data);
+            uint8x16_t val = vshrq_n_u8(b.data, 7);
             vst1q_u8((uint8_t*)mem, val);
         }
 
         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 = vsub_u8(vdup_n_u8(0), vqmovn_u16(b.data));
+            uint8x8_t val = vshr_n_u8(vqmovn_u16(b.data), 7);
             vst1_u8((uint8_t*)mem, val);
         }
 
         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 = vsub_u8(vdup_n_u8(0), vqmovn_u16(vcombine_u16(vqmovn_u32(b.data), vdup_n_u16(0))));
+            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);
         }
 
+        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);
+        }
+
         template <class A>
         XSIMD_INLINE void store(batch_bool<float, A> b, bool* mem, requires_arch<neon>) noexcept
         {

include/xsimd/arch/xsimd_neon64.hpp

@@ -177,6 +177,16 @@ namespace xsimd
             return store_aligned<A>(dst, src, A {});
         }
 
+        /*********************
+         * store<batch_bool> *
+         *********************/
+
+        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 {});
+        }
+
         /****************
          * load_complex *
          ****************/