Add some fast paths to convert_pixel()fetchers

All the inlining going on makes gcc generate slightly suboptimal code,
so add some special cases for the common formats a8r8g8b8, x8r8g8b8,
a8, and r5g6b5.

1 files changed, 53 insertions, 0 deletions

diff --git a/pixman/pixman-access.c b/pixman/pixman-access.c
index 189b1915..9ebcc1fa 100644
--- a/pixman/pixman-access.c
+++ b/pixman/pixman-access.c
@@ -271,6 +271,56 @@ convert_channel (uint32_t pixel, uint32_t def_value,
     return (v & ((1 << n_to_bits) - 1)) << to_shift;
 }
 
+static force_inline pixman_bool_t
+convert_special_cases (pixman_format_code_t from, pixman_format_code_t to, uint32_t *pixel)
+{
+    /* A couple of special cases for performance */
+    if ((from == to) || (from == PIXMAN_a8r8g8b8 && to == PIXMAN_x8r8g8b8))
+    {
+	return TRUE;
+    }
+    else if (from == PIXMAN_x8r8g8b8 && to == PIXMAN_a8r8g8b8)
+    {
+	*pixel |= 0xff000000;
+	return TRUE;
+    }
+    else if (from == PIXMAN_a8 && to == PIXMAN_a8r8g8b8)
+    {
+	*pixel <<= 24;
+	return TRUE;
+    }
+    else if (from == PIXMAN_r5g6b5 && to == PIXMAN_a8r8g8b8)
+    {
+	uint32_t r;
+	
+	r = ((*pixel << 3) & 0xf8) |
+	    ((*pixel << 5) & 0xfc00) |
+	    ((*pixel << 8) & 0xf80000);
+	
+	r |= (r >> 5) & 0x70007;
+	r |= (r >> 6) & 0x300;
+	
+	*pixel = r | 0xff000000;
+	return TRUE;
+    }
+    else if (from == PIXMAN_a8r8g8b8 && to == PIXMAN_a8)
+    {
+	*pixel >>= 24;
+	return TRUE;
+    }
+    else if (from == PIXMAN_a8r8g8b8 && to == PIXMAN_r5g6b5)
+    {
+	*pixel =
+	    ((*pixel >> 3) & 0x001f) |
+	    ((*pixel >> 5) & 0x07e0) |
+	    ((*pixel >> 8) & 0xf800);
+	
+	return TRUE;
+    }
+
+    return FALSE;
+}
+
 static force_inline uint32_t
 convert_pixel (pixman_format_code_t from, pixman_format_code_t to, uint32_t pixel)
 {
@@ -278,6 +328,9 @@ convert_pixel (pixman_format_code_t from, pixman_format_code_t to, uint32_t pixe
     int a_to_shift, r_to_shift, g_to_shift, b_to_shift;
     uint32_t a, r, g, b;
 
+    if (convert_special_cases (from, to, &pixel))
+	return pixel;
+
     get_shifts (from, &a_from_shift, &r_from_shift, &g_from_shift, &b_from_shift);
     get_shifts (to, &a_to_shift, &r_to_shift, &g_to_shift, &b_to_shift);