Compute pixel values directly into data port

Instead of leaving pixel values in src_sample registers, compute the pixel
values directl to the data port to save 8 moves. This cannot work when no
computation is done as there is both no way to wait for the sampler to
finish and because the sampler returns data in a different order from that
required by the data port (sigh).

1 files changed, 2 insertions, 0 deletions

diff --git a/src/i965_render.c b/src/i965_render.c
index 1b4afcc4..79db41c8 100644
--- a/src/i965_render.c
+++ b/src/i965_render.c
@@ -340,6 +340,7 @@ static const uint32_t ps_kernel_nomask_affine_static [][4] = {
 #include "exa_wm_xy.g4b"
 #include "exa_wm_src_affine.g4b"
 #include "exa_wm_src_sample_argb.g4b"
+#include "exa_wm_src_data.g4b"
 #include "exa_wm_write.g4b"
 };
 
@@ -347,6 +348,7 @@ static const uint32_t ps_kernel_nomask_projective_static [][4] = {
 #include "exa_wm_xy.g4b"
 #include "exa_wm_src_projective.g4b"
 #include "exa_wm_src_sample_argb.g4b"
+#include "exa_wm_src_data.g4b"
 #include "exa_wm_write.g4b"
 };