mmx: enable over_x888_8_8888 on ARM/iwMMXt

before: over_x888_8_8888 =  L1:   7.63  L2:   7.72  M:  6.44 ( 19.17%)  HT: 6.24  VT:  6.11  R:  5.87  RT:  4.61 (  51Kops/s)
after : over_x888_8_8888 =  L1:  11.88  L2:  11.11  M:  8.70 ( 26.01%)  HT: 8.15  VT:  8.07  R:  7.76  RT:  5.62 (  61Kops/s)

Signed-off-by: Matt Turner <mattst88@gmail.com>

diff --git a/pixman/pixman-mmx.c b/pixman/pixman-mmx.c
index 6e6de5f..d89c3d6 100644 (file)
--- a/pixman/pixman-mmx.c
+++ b/pixman/pixman-mmx.c
@@ -3036,7 +3036,7 @@ mmx_composite_copy_area (pixman_implementation_t *imp,
                     src_x, src_y, dest_x, dest_y, width, height);
 }
 
-#if 0
+#ifdef USE_ARM_IWMMXT
 static void
 mmx_composite_over_x888_8_8888 (pixman_implementation_t *imp,
                                 pixman_composite_info_t *info)
@@ -3123,9 +3123,9 @@ static const pixman_fast_path_t mmx_fast_paths[] =
     PIXMAN_STD_FAST_PATH    (OVER, a8r8g8b8, solid,    x8r8g8b8, mmx_composite_over_8888_n_8888    ),
     PIXMAN_STD_FAST_PATH    (OVER, a8b8g8r8, solid,    a8b8g8r8, mmx_composite_over_8888_n_8888    ),
     PIXMAN_STD_FAST_PATH    (OVER, a8b8g8r8, solid,    x8b8g8r8, mmx_composite_over_8888_n_8888    ),
-#if 0
+#ifdef USE_ARM_IWMMXT
     /* FIXME: This code is commented out since it's apparently
-     * not actually faster than the generic code.
+     * not actually faster than the generic code on x86.
      */
     PIXMAN_STD_FAST_PATH    (OVER, x8r8g8b8, a8,       x8r8g8b8, mmx_composite_over_x888_8_8888    ),
     PIXMAN_STD_FAST_PATH    (OVER, x8r8g8b8, a8,       a8r8g8b8, mmx_composite_over_x888_8_8888    ),