Merge pull request #3933 from facebook/fix3819

prevent XXH64 from being autovectorized by XXH512 by default

lib/common/xxhash.h

@@ -3329,6 +3329,23 @@ static xxh_u64 XXH64_round(xxh_u64 acc, xxh_u64 input)
     acc += input * XXH_PRIME64_2;
     acc  = XXH_rotl64(acc, 31);
     acc *= XXH_PRIME64_1;
+#if (defined(__AVX512F__)) && !defined(XXH_ENABLE_AUTOVECTORIZE)
+    /*
+     * DISABLE AUTOVECTORIZATION:
+     * A compiler fence is used to prevent GCC and Clang from
+     * autovectorizing the XXH64 loop (pragmas and attributes don't work for some
+     * reason) without globally disabling AVX512.
+     *
+     * Autovectorization of XXH64 tends to be detrimental,
+     * though the exact outcome may change depending on exact cpu and compiler version.
+     * For information, it has been reported as detrimental for Skylake-X,
+     * but possibly beneficial for Zen4.
+     *
+     * The default is to disable auto-vectorization,
+     * but you can select to enable it instead using `XXH_ENABLE_AUTOVECTORIZE` build variable.
+     */
+    XXH_COMPILER_GUARD(acc);
+#endif
     return acc;
 }