vppinfra: clib_memcpy improvement

In the case where n is a constant 16 bytes, the second load/store is
ignored by the load/store unit - it has neglible/zero cost. In the case
where  n is variable and greater than 512 bytes, the extra if (n == 16)
branch has a very small performance impact.

Change-Id: I04b313cf022c18fee31b1d9bcf6a128414659a99
Signed-off-by: Ray Kinsella <ray.kinsella@intel.com>

2 files changed, 0 insertions, 10 deletions

diff --git a/src/vppinfra/memcpy_avx.h b/src/vppinfra/memcpy_avx.h
index d95bbad72b8..e3feb76b6b7 100644
--- a/src/vppinfra/memcpy_avx.h
+++ b/src/vppinfra/memcpy_avx.h
@@ -185,11 +185,6 @@ clib_memcpy (void *dst, const void *src, size_t n)
 	/**
          * Fast way when copy size doesn't exceed 512 bytes
          */
-  if (n == 16)
-    {
-      clib_mov16 ((u8 *) dst, (const u8 *) src);
-      return ret;
-    }
   if (n <= 32)
     {
       clib_mov16 ((u8 *) dst, (const u8 *) src);
diff --git a/src/vppinfra/memcpy_sse3.h b/src/vppinfra/memcpy_sse3.h
index 49baf5e5d31..4fc48c86c8b 100644
--- a/src/vppinfra/memcpy_sse3.h
+++ b/src/vppinfra/memcpy_sse3.h
@@ -224,11 +224,6 @@ clib_memcpy (void *dst, const void *src, size_t n)
 	/**
 	 * Fast way when copy size doesn't exceed 512 bytes
 	 */
-  if (n == 16)
-    {
-      clib_mov16 ((u8 *) dst, (const u8 *) src);
-      return ret;
-    }
   if (n <= 32)
     {
       clib_mov16 ((u8 *) dst, (const u8 *) src);