[Mesa-dev] [PATCH] vl/compositor: fix weave shader bugs

[Maarten Lankhorst]

Writemask was XY instead of YZ (thanks to calim for spotting it).

The pixel calculation resulted in the pixel always being off by one.
If y was .5:

y' = round(y) + 0.5 = 1.5

Fixing this also means the LRP function has to swap the pixels it, since
it's now the other way around for top/bottom.

WIth these fixes only chroma for top and bottom pixel rows are wrongly interpolated
in my test program:

--- nvidia
+++ nouveau
@@ -1,4 +1,4 @@
-YCbCr[0] = 00c080
+YCbCr[0] = 00b070
 YCbCr[1] = 00b070
 YCbCr[2] = 029050
 YCbCr[3] = 207050
@@ -61,4 +61,4 @@
 YCbCr[60] = 0c5070
 YCbCr[61] = c05090
 YCbCr[62] = 0e70b0
-YCbCr[63] = e080c0
+YCbCr[63] = e070b0

Signed-off-by: Maarten Lankhorst <maarten.lankhorst at canonical.com>

---

diff --git a/src/gallium/auxiliary/vl/vl_compositor.c b/src/gallium/auxiliary/vl/vl_compositor.c
index 7ea13bf..bc69669 100644
--- a/src/gallium/auxiliary/vl/vl_compositor.c
+++ b/src/gallium/auxiliary/vl/vl_compositor.c
@@ -199,11 +199,13 @@ create_frag_shader_weave(struct vl_compositor *c)
 
    /* calculate the texture offsets
     * t_tc.x = i_tc.x
-    * t_tc.y = (round(i_tc.y) + 0.5) / height * 2
+    * t_tc.y = (round(i_tc.y - 0.5) + 0.5) / height * 2
     */
    for (i = 0; i < 2; ++i) {
       ureg_MOV(shader, ureg_writemask(t_tc[i], TGSI_WRITEMASK_X), i_tc[i]);
-      ureg_ROUND(shader, ureg_writemask(t_tc[i], TGSI_WRITEMASK_YZ), i_tc[i]);
+      ureg_SUB(shader, ureg_writemask(t_tc[i], TGSI_WRITEMASK_YZ),
+               i_tc[i], ureg_imm1f(shader, 0.5f));
+      ureg_ROUND(shader, ureg_writemask(t_tc[i], TGSI_WRITEMASK_YZ), ureg_src(t_tc[i]));
       ureg_MOV(shader, ureg_writemask(t_tc[i], TGSI_WRITEMASK_W),
                ureg_imm1f(shader, i ? 0.75f : 0.25f));
       ureg_ADD(shader, ureg_writemask(t_tc[i], TGSI_WRITEMASK_YZ),
@@ -234,11 +236,11 @@ create_frag_shader_weave(struct vl_compositor *c)
    ureg_ROUND(shader, ureg_writemask(t_tc[0], TGSI_WRITEMASK_YZ), i_tc[0]);
    ureg_ADD(shader, ureg_writemask(t_tc[0], TGSI_WRITEMASK_YZ),
             ureg_src(t_tc[0]), ureg_negate(i_tc[0]));
-   ureg_MUL(shader, ureg_writemask(t_tc[0], TGSI_WRITEMASK_XY),
+   ureg_MUL(shader, ureg_writemask(t_tc[0], TGSI_WRITEMASK_YZ),
             ureg_abs(ureg_src(t_tc[0])), ureg_imm1f(shader, 2.0f));
    ureg_LRP(shader, t_texel[0], ureg_swizzle(ureg_src(t_tc[0]),
             TGSI_SWIZZLE_Y, TGSI_SWIZZLE_Z, TGSI_SWIZZLE_Z, TGSI_SWIZZLE_Z),
-            ureg_src(t_texel[1]), ureg_src(t_texel[0]));
+            ureg_src(t_texel[0]), ureg_src(t_texel[1]));
 
    /* and finally do colour space transformation
     * fragment = csc * texel