[Pixman] [PATCH 04/15] pixman-filter: reduce amount of malloc/free/memcpy to generate filter

[spitzak at gmail.com]

From: Bill Spitzak <spitzak at gmail.com>

Rearranged so that the entire block of memory for the filter pair
is allocated first, and then filled in. Previous version allocated
and freed two temporary buffers for each filter and did an extra
memcpy.
---
 pixman/pixman-filter.c | 59 +++++++++++++++++++++-----------------------------
 1 file changed, 25 insertions(+), 34 deletions(-)

diff --git a/pixman/pixman-filter.c b/pixman/pixman-filter.c
index 05bc345..15f9069 100644
--- a/pixman/pixman-filter.c
+++ b/pixman/pixman-filter.c
@@ -217,25 +217,25 @@ integral (pixman_kernel_t reconstruct, double x1,
     }
 }
 
-static pixman_fixed_t *
-create_1d_filter (int             *width,
+static int
+filter_width (pixman_kernel_t reconstruct,
+	      pixman_kernel_t sample,
+	      double scale)
+{
+    return ceil (scale * filters[sample].width + filters[reconstruct].width);
+}
+
+static void
+create_1d_filter (int              width,
 		  pixman_kernel_t  reconstruct,
 		  pixman_kernel_t  sample,
 		  double           scale,
-		  int              n_phases)
+		  int              n_phases,
+		  pixman_fixed_t *p)
 {
-    pixman_fixed_t *params, *p;
     double step;
-    double size;
     int i;
 
-    size = scale * filters[sample].width + filters[reconstruct].width;
-    *width = ceil (size);
-
-    p = params = malloc (*width * n_phases * sizeof (pixman_fixed_t));
-    if (!params)
-        return NULL;
-
     step = 1.0 / n_phases;
 
     for (i = 0; i < n_phases; ++i)
@@ -250,8 +250,8 @@ create_1d_filter (int             *width,
 	 * and sample positions.
 	 */
 
-	x1 = ceil (frac - *width / 2.0 - 0.5);
-        x2 = x1 + *width;
+	x1 = ceil (frac - width / 2.0 - 0.5);
+        x2 = x1 + width;
 
 	total = 0;
         for (x = x1; x < x2; ++x)
@@ -279,7 +279,7 @@ create_1d_filter (int             *width,
         }
 
 	/* Normalize */
-	p -= *width;
+	p -= width;
         total = 1 / total;
         new_total = 0;
 	for (x = x1; x < x2; ++x)
@@ -291,10 +291,8 @@ create_1d_filter (int             *width,
 	}
 
 	if (new_total != pixman_fixed_1)
-	    *(p - *width / 2) += (pixman_fixed_1 - new_total);
+	    *(p - width / 2) += (pixman_fixed_1 - new_total);
     }
-
-    return params;
 }
 
 /* Create the parameter list for a SEPARABLE_CONVOLUTION filter
@@ -313,38 +311,31 @@ pixman_filter_create_separable_convolution (int             *n_values,
 {
     double sx = fabs (pixman_fixed_to_double (scale_x));
     double sy = fabs (pixman_fixed_to_double (scale_y));
-    pixman_fixed_t *horz = NULL, *vert = NULL, *params = NULL;
+    pixman_fixed_t *params;
     int subsample_x, subsample_y;
     int width, height;
 
     subsample_x = (1 << subsample_bits_x);
     subsample_y = (1 << subsample_bits_y);
 
-    horz = create_1d_filter (&width, reconstruct_x, sample_x, sx, subsample_x);
-    vert = create_1d_filter (&height, reconstruct_y, sample_y, sy, subsample_y);
+    width = filter_width (reconstruct_x, sample_x, sx);
+    height = filter_width (reconstruct_y, sample_y, sy);
 
-    if (!horz || !vert)
-        goto out;
-    
     *n_values = 4 + width * subsample_x + height * subsample_y;
-    
+
     params = malloc (*n_values * sizeof (pixman_fixed_t));
     if (!params)
-        goto out;
+        return NULL;
 
     params[0] = pixman_int_to_fixed (width);
     params[1] = pixman_int_to_fixed (height);
     params[2] = pixman_int_to_fixed (subsample_bits_x);
     params[3] = pixman_int_to_fixed (subsample_bits_y);
 
-    memcpy (params + 4, horz,
-	    width * subsample_x * sizeof (pixman_fixed_t));
-    memcpy (params + 4 + width * subsample_x, vert,
-	    height * subsample_y * sizeof (pixman_fixed_t));
-
-out:
-    free (horz);
-    free (vert);
+    create_1d_filter (width, reconstruct_x, sample_x, sx, subsample_x,
+		      params + 4);
+    create_1d_filter (height, reconstruct_y, sample_y, sy, subsample_y,
+		      params + 4 + width * subsample_x);
 
     return params;
 }
-- 
1.9.1