i965/fs: Fix interference calculation of pixel_[xy] in 16-wide.

Fixes glsl-fs-ceil in that mode, which produced the code in the comment.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 17f4435a1ac7683d578118a5390b791bcde2dfd6..aa51d04df330982b7fe7cc90e52b6d5c1bd52e0f 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -3393,6 +3393,29 @@ fs_visitor::virtual_grf_interferes(int a, int b)
          (this->virtual_grf_use[b] != -1 ||
           this->virtual_grf_def[b] == MAX_INSTRUCTION));
 
+   /* If the register is used to store 16 values of less than float
+    * size (only the case for pixel_[xy]), then we can't allocate
+    * another dword-sized thing to that register that would be used in
+    * the same instruction.  This is because when the GPU decodes (for
+    * example):
+    *
+    * (declare (in ) vec4 gl_FragCoord@0x97766a0)
+    * add(16)         g6<1>F          g6<8,8,1>UW     0.5F { align1 compr };
+    *
+    * it's actually processed as:
+    * add(8)         g6<1>F          g6<8,8,1>UW     0.5F { align1 };
+    * add(8)         g7<1>F          g6.8<8,8,1>UW   0.5F { align1 sechalf };
+    *
+    * so our second half values in g6 got overwritten in the first
+    * half.
+    */
+   if (c->dispatch_width == 16 && (this->pixel_x.reg == a ||
+                                  this->pixel_x.reg == b ||
+                                  this->pixel_y.reg == a ||
+                                  this->pixel_y.reg == b)) {
+      return start <= end;
+   }
+
    return start < end;
 }