benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c

This commit adds more benchmarks for the common memcpy/memmove
benchmarks. The most signifcant cases are the half page offsets. The
current versions leaves dst and src near page aligned which leads to
false 4k aliasing on x86_64. This can add noise due to false
dependencies from one run to the next. As well, this seems like more
of an edge case that common case so it shouldn't be the only thing

Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>

2 files changed, 66 insertions, 9 deletions

diff --git a/benchtests/bench-memcpy.c b/benchtests/bench-memcpy.c
index d9236a2..744bea2 100644
--- a/benchtests/bench-memcpy.c
+++ b/benchtests/bench-memcpy.c
@@ -40,7 +40,10 @@ do_one_test (json_ctx_t *json_ctx, impl_t *impl, char *dst, const char *src,
 {
   size_t i, iters = INNER_LOOP_ITERS;
   timing_t start, stop, cur;
-
+  for (i = 0; i < iters / 64; ++i)
+    {
+      CALL (impl, dst, src, len);
+    }
   TIMING_NOW (start);
   for (i = 0; i < iters; ++i)
     {
@@ -60,11 +63,11 @@ do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len,
   size_t i, j;
   char *s1, *s2;
   size_t repeats;
-  align1 &= 63;
+  align1 &= (getpagesize () - 1);
   if (align1 + len >= page_size)
     return;
 
-  align2 &= 63;
+  align2 &= (getpagesize () - 1);
   if (align2 + len >= page_size)
     return;
 
@@ -99,7 +102,7 @@ test_main (void)
 {
   json_ctx_t json_ctx;
   size_t i;
-
+  size_t half_page = getpagesize () / 2;
   test_init ();
 
   json_init (&json_ctx, 0, stdout);
@@ -121,8 +124,15 @@ test_main (void)
     {
       do_test (&json_ctx, 0, 0, 1 << i, 1);
       do_test (&json_ctx, i, 0, 1 << i, 1);
+      do_test (&json_ctx, i + 32, 0, 1 << i, 1);
       do_test (&json_ctx, 0, i, 1 << i, 1);
+      do_test (&json_ctx, 0, i + 32, 1 << i, 1);
       do_test (&json_ctx, i, i, 1 << i, 1);
+      do_test (&json_ctx, i + 32, i + 32, 1 << i, 1);
+      do_test (&json_ctx, half_page, 0, 1 << i, 1);
+      do_test (&json_ctx, half_page + i, 0, 1 << i, 1);
+      do_test (&json_ctx, half_page, i, 1 << i, 1);
+      do_test (&json_ctx, half_page + i, i, 1 << i, 1);
     }
 
   for (i = 0; i < 32; ++i)
@@ -131,16 +141,26 @@ test_main (void)
       do_test (&json_ctx, i, 0, i, 0);
       do_test (&json_ctx, 0, i, i, 0);
       do_test (&json_ctx, i, i, i, 0);
+      do_test (&json_ctx, half_page, 0, i, 0);
+      do_test (&json_ctx, half_page + i, 0, i, 0);
+      do_test (&json_ctx, half_page, i, i, 0);
+      do_test (&json_ctx, half_page + i, i, i, 0);
+      do_test (&json_ctx, getpagesize () - 1, 0, i, 0);
+      do_test (&json_ctx, 0, getpagesize () - 1, i, 0);
     }
 
   for (i = 3; i < 32; ++i)
     {
       if ((i & (i - 1)) == 0)
-	continue;
+        continue;
       do_test (&json_ctx, 0, 0, 16 * i, 1);
       do_test (&json_ctx, i, 0, 16 * i, 1);
       do_test (&json_ctx, 0, i, 16 * i, 1);
       do_test (&json_ctx, i, i, 16 * i, 1);
+      do_test (&json_ctx, half_page, 0, 16 * i, 1);
+      do_test (&json_ctx, half_page + i, 0, 16 * i, 1);
+      do_test (&json_ctx, half_page, i, 16 * i, 1);
+      do_test (&json_ctx, half_page + i, i, 16 * i, 1);
     }
 
   for (i = 32; i < 64; ++i)
@@ -149,16 +169,33 @@ test_main (void)
       do_test (&json_ctx, i, 0, 32 * i, 1);
       do_test (&json_ctx, 0, i, 32 * i, 1);
       do_test (&json_ctx, i, i, 32 * i, 1);
+      do_test (&json_ctx, half_page, 0, 32 * i, 1);
+      do_test (&json_ctx, half_page + i, 0, 32 * i, 1);
+      do_test (&json_ctx, half_page, i, 32 * i, 1);
+      do_test (&json_ctx, half_page + i, i, 32 * i, 1);
     }
 
   do_test (&json_ctx, 0, 0, getpagesize (), 1);
 
-  for (i = 0; i <= 32; ++i)
+  for (i = 0; i <= 48; ++i)
     {
       do_test (&json_ctx, 0, 0, 2048 + 64 * i, 1);
       do_test (&json_ctx, i, 0, 2048 + 64 * i, 1);
+      do_test (&json_ctx, i + 32, 0, 2048 + 64 * i, 1);
       do_test (&json_ctx, 0, i, 2048 + 64 * i, 1);
+      do_test (&json_ctx, 0, i + 32, 2048 + 64 * i, 1);
       do_test (&json_ctx, i, i, 2048 + 64 * i, 1);
+      do_test (&json_ctx, i + 32, i + 32, 2048 + 64 * i, 1);
+      do_test (&json_ctx, half_page, 0, 2048 + 64 * i, 1);
+      do_test (&json_ctx, half_page + i, 0, 2048 + 64 * i, 1);
+      do_test (&json_ctx, half_page, i, 2048 + 64 * i, 1);
+      do_test (&json_ctx, half_page + i, i, 2048 + 64 * i, 1);
+      do_test (&json_ctx, i, 1, 2048 + 64 * i, 1);
+      do_test (&json_ctx, 1, i, 2048 + 64 * i, 1);
+      do_test (&json_ctx, i + 32, 1, 2048 + 64 * i, 1);
+      do_test (&json_ctx, 1, i + 32, 2048 + 64 * i, 1);
+      do_test (&json_ctx, half_page + i, 1, 2048 + 64 * i, 1);
+      do_test (&json_ctx, half_page + 1, i, 2048 + 64 * i, 1);
     }
 
   json_array_end (&json_ctx);
diff --git a/benchtests/bench-memmove.c b/benchtests/bench-memmove.c
index 6becbf4..855f4d0 100644
--- a/benchtests/bench-memmove.c
+++ b/benchtests/bench-memmove.c
@@ -34,7 +34,10 @@ do_one_test (json_ctx_t *json_ctx, impl_t *impl, char *dst, char *src,
 {
   size_t i, iters = INNER_LOOP_ITERS;
   timing_t start, stop, cur;
-
+  for (i = 0; i < iters / 64; ++i)
+    {
+      CALL (impl, dst, src, len);
+    }
   TIMING_NOW (start);
   for (i = 0; i < iters; ++i)
     {
@@ -53,11 +56,11 @@ do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len)
   size_t i, j;
   char *s1, *s2;
 
-  align1 &= 63;
+  align1 &= (getpagesize () - 1);
   if (align1 + len >= page_size)
     return;
 
-  align2 &= 63;
+  align2 &= (getpagesize () - 1);
   if (align2 + len >= page_size)
     return;
 
@@ -85,6 +88,7 @@ test_main (void)
 {
   json_ctx_t json_ctx;
   size_t i;
+  size_t half_page = getpagesize () / 2;
 
   test_init ();
 
@@ -138,6 +142,22 @@ test_main (void)
       do_test (&json_ctx, i, i, 32 * i);
     }
 
+  for (i = 0; i <= 48; ++i)
+    {
+      do_test (&json_ctx, 0, 0, 2048 + 64 * i);
+      do_test (&json_ctx, i, 0, 2048 + 64 * i);
+      do_test (&json_ctx, 0, i, 2048 + 64 * i);
+      do_test (&json_ctx, i, i, 2048 + 64 * i);
+      do_test (&json_ctx, half_page, 0, 2048 + 64 * i);
+      do_test (&json_ctx, 0, half_page, 2048 + 64 * i);
+      do_test (&json_ctx, half_page + i, 0, 2048 + 64 * i);
+      do_test (&json_ctx, i, half_page, 2048 + 64 * i);
+      do_test (&json_ctx, half_page, i, 2048 + 64 * i);
+      do_test (&json_ctx, 0, half_page + i, 2048 + 64 * i);
+      do_test (&json_ctx, half_page + i, i, 2048 + 64 * i);
+      do_test (&json_ctx, i, half_page + i, 2048 + 64 * i);
+    }
+
   json_array_end (&json_ctx);
   json_attr_object_end (&json_ctx);
   json_attr_object_end (&json_ctx);