Patch: Optimizing Matrix routines by hand

[Carl-Philip Haensch]

Hi,

I wrote a patch that optimizes matrix scale and translate because i  
doubt gcc will find the shortest path through an invocation, three  
loops and a memory writeback per strcpy by itself.

diff --git a/compositor/compositor.c b/compositor/compositor.c
index 9d7c330..e571b12 100644
--- a/compositor/compositor.c
+++ b/compositor/compositor.c
@@ -87,21 +87,20 @@ wlsc_matrix_multiply(struct wlsc_matrix *m, const  
struct wlsc_matrix *n)
  static void
  wlsc_matrix_translate(struct wlsc_matrix *matrix, GLfloat x, GLfloat  
y, GLfloat z)
  {
-	struct wlsc_matrix translate = {
-		{ 1, 0, 0, 0,  0, 1, 0, 0,  0, 0, 1, 0,  x, y, z, 1 }
-	};
-
-	wlsc_matrix_multiply(matrix, &translate);
+	matrix->d[12] += x;
+	matrix->d[13] += y;
+	matrix->d[14] += z;
  }

  static void
  wlsc_matrix_scale(struct wlsc_matrix *matrix, GLfloat x, GLfloat y,  
GLfloat z)
  {
-	struct wlsc_matrix scale = {
-		{ x, 0, 0, 0,  0, y, 0, 0,  0, 0, z, 0,  0, 0, 0, 1 }
-	};
-
-	wlsc_matrix_multiply(matrix, &scale);
+	int i;
+	for(i = 0; i < 4; i++) {
+		matrix->d[0 + 4 * i] *= x;
+		matrix->d[1 + 4 * i] *= y;
+		matrix->d[2 + 4 * i] *= z;
+	}
  }

  static void