Four byte optimized memcpy.

JerryScript-DCO-1.0-Signed-off-by: Zoltan Herczeg zherczeg.u-szeged@partner.samsung.com

jerry-libc/jerry-libc.c

@@ -103,6 +103,24 @@ memcpy (void *s1, /**< destination */
         const void *s2, /**< source */
         size_t n) /**< bytes number */
 {
+  /* Aligned fast case. */
+  if (n >= 4 && !(((uintptr_t) s1) & 0x3) && !(((uintptr_t) s2) & 0x3))
+  {
+    size_t chunks = (n >> 2);
+    uint32_t *area1_p = (uint32_t *) s1;
+    const uint32_t *area2_p = (const uint32_t *) s2;
+
+    do
+    {
+      *area1_p++ = *area2_p++;
+    }
+    while (--chunks);
+
+    n &= 0x3;
+    s1 = area1_p;
+    s2 = area2_p;
+  }
+
   uint8_t *area1_p = (uint8_t *) s1;
   const uint8_t *area2_p = (const uint8_t *) s2;