[chunkset_neon] Use vdupq_n_u64.

* Using vdupq_n_u64 duplicates the unsigned 64-bit integer to two consecutive aligned memory locations in stack so compiler can use wider load instructions.
  All different-sized general-purpose registers overlay on ARM/AArch64, so any vector cast is no-op in assembly.

diff --git a/arch/arm/chunkset_neon.c b/arch/arm/chunkset_neon.c
index b1fcb241d079a17d0a6ba10bef685ecd54b2ab07..e0ad3e04ea7ef3976d12b74a0ae432144f3e8785 100644 (file)
--- a/arch/arm/chunkset_neon.c
+++ b/arch/arm/chunkset_neon.c
@@ -37,7 +37,9 @@ static inline void chunkmemset_4(uint8_t *from, chunk_t *chunk) {
 }
 
 static inline void chunkmemset_8(uint8_t *from, chunk_t *chunk) {
-    *chunk = vcombine_u8(vld1_u8(from), vld1_u8(from));
+    uint64_t tmp;
+    memcpy(&tmp, from, 8);
+    *chunk = vreinterpretq_u8_u64(vdupq_n_u64(tmp));
 }
 
 #define CHUNKSIZE        chunksize_neon