Merge pull request #2040 from caoyzh/dev-2

Optimize by prefetching on aarch64

lib/compress/zstd_double_fast.c

@@ -198,6 +198,9 @@ size_t ZSTD_compressBlock_doubleFast_generic(
         }   }
 
         ip += ((ip-anchor) >> kSearchStrength) + 1;
+#if defined(__aarch64__)
+        PREFETCH_L1(ip+256);
+#endif
         continue;
 
 _search_next_long:

lib/compress/zstd_fast.c

@@ -102,6 +102,11 @@ ZSTD_compressBlock_fast_generic(
         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 */