# include <mmintrin.h> /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */
# define PREFETCH_L1(ptr) _mm_prefetch((const char*)(ptr), _MM_HINT_T0)
# define PREFETCH_L2(ptr) _mm_prefetch((const char*)(ptr), _MM_HINT_T1)
+# elif defined(__aarch64__)
+# define PREFETCH_L1(ptr) __asm__ __volatile__("prfm pldl1keep, %0" ::"Q"(*(ptr)))
+# define PREFETCH_L2(ptr) __asm__ __volatile__("prfm pldl2keep, %0" ::"Q"(*(ptr)))
# elif defined(__GNUC__) && ( (__GNUC__ >= 4) || ( (__GNUC__ == 3) && (__GNUC_MINOR__ >= 1) ) )
# define PREFETCH_L1(ptr) __builtin_prefetch((ptr), 0 /* rw==read */, 3 /* locality */)
# define PREFETCH_L2(ptr) __builtin_prefetch((ptr), 0 /* rw==read */, 2 /* locality */)
const BYTE* match0 = base + matchIndex0;
const BYTE* match1 = base + matchIndex1;
U32 offcode;
+
+#if defined(__aarch64__)
+ PREFETCH_L1(ip0+256);
+#endif
+
hashTable[h0] = current0; /* update hash table */
hashTable[h1] = current1; /* update hash table */