[Mesa-dev] [PATCH 10/11] [RFC] mesa: optimize out the realloc from glCopyTexImagexD()

[Miklós Máté]

Apitrace showed this call to be 5ms (9 times per frame),
but in reality it's about 500us. This shortcut makes it 20us.
---
 src/mesa/main/teximage.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/src/mesa/main/teximage.c b/src/mesa/main/teximage.c
index ab60a2f..ba13720 100644
--- a/src/mesa/main/teximage.c
+++ b/src/mesa/main/teximage.c
@@ -3393,6 +3393,21 @@ formats_differ_in_component_sizes(mesa_format f1, mesa_format f2)
    return GL_FALSE;
 }
 
+static GLboolean
+canAvoidRealloc(struct gl_texture_image *texImage, GLenum internalFormat,
+      GLint x, GLint y, GLsizei width, GLsizei height, GLint border)
+{
+   if (texImage->InternalFormat != internalFormat)
+      return false;
+   if (texImage->Border != border)
+      return false;
+   if (texImage->Width2 != width)
+      return false;
+   if (texImage->Height2 != height)
+      return false;
+   return true;
+}
+
 /**
  * Implement the glCopyTexImage1/2D() functions.
  */
@@ -3433,6 +3448,20 @@ copyteximage(struct gl_context *ctx, GLuint dims,
    texObj = _mesa_get_current_tex_object(ctx, target);
    assert(texObj);
 
+   _mesa_lock_texture(ctx, texObj);
+   {
+      texImage = _mesa_select_tex_image(texObj, target, level);
+      if (texImage && canAvoidRealloc(texImage, internalFormat,
+               x, y, width, height, border)) {
+         _mesa_unlock_texture(ctx, texObj);
+         //_mesa_debug(0, "using shortcut\n");
+         return _mesa_copy_texture_sub_image(ctx, dims, texObj, target, level,
+               0, 0, 0, x, y, width, height, "CopyTexImage");
+      }
+      //_mesa_debug(0, "can't shortcut %p, %dx%d\n", texImage, width, height);
+   }
+   _mesa_unlock_texture(ctx, texObj);
+
    texFormat = _mesa_choose_texture_format(ctx, texObj, target, level,
                                            internalFormat, GL_NONE, GL_NONE);
 
-- 
2.6.4