Load 8 bytes at a time in hash_func. (Sebastian Pop)

diff --git a/Zend/zend_string.h b/Zend/zend_string.h
index 793a519ce21a2b896b1c280ba78128da2924ee4a..4fb3e3b5b3678167ca1ad19f88c5f972e6f04cb7 100644 (file)
--- a/Zend/zend_string.h
+++ b/Zend/zend_string.h
@@ -364,6 +364,25 @@ static zend_always_inline zend_ulong zend_inline_hash_func(const char *str, size
 #if defined(_WIN32) || defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
        /* Version with multiplication works better on modern CPU */
        for (; len >= 8; len -= 8, str += 8) {
+# if defined(__aarch64__)
+               /* On some architectures it is beneficial to load 8 bytes at a
+                  time and extract each byte with a bit field extract instr. */
+               uint64_t chunk;
+
+               memcpy(&chunk, str, sizeof(chunk));
+               hash =
+                       hash                        * 33 * 33 * 33 * 33 +
+                       ((chunk >> (8 * 0)) & 0xff) * 33 * 33 * 33 +
+                       ((chunk >> (8 * 1)) & 0xff) * 33 * 33 +
+                       ((chunk >> (8 * 2)) & 0xff) * 33 +
+                       ((chunk >> (8 * 3)) & 0xff);
+               hash =
+                       hash                        * 33 * 33 * 33 * 33 +
+                       ((chunk >> (8 * 4)) & 0xff) * 33 * 33 * 33 +
+                       ((chunk >> (8 * 5)) & 0xff) * 33 * 33 +
+                       ((chunk >> (8 * 6)) & 0xff) * 33 +
+                       ((chunk >> (8 * 7)) & 0xff);
+# else
                hash =
                        hash   * 33 * 33 * 33 * 33 +
                        str[0] * 33 * 33 * 33 +
@@ -376,6 +395,7 @@ static zend_always_inline zend_ulong zend_inline_hash_func(const char *str, size
                        str[5] * 33 * 33 +
                        str[6] * 33 +
                        str[7];
+# endif
        }
        if (len >= 4) {
                hash =