llvmpipe: increase number of subpixel bits to eight

Unfortunately d3d10 requires a lot higher precision (e.g.
wgf11clipping tests for it). The smallest number of precision
bits with which it passes is 8. That means that we need to
decrease the maximum length of an edge that we can handle without
subdivision by 4 bits. Abstracted the code a bit to make it easier
to change once to switch to 64bit rasterization.

Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>

diff --git a/src/gallium/drivers/llvmpipe/lp_rast.h b/src/gallium/drivers/llvmpipe/lp_rast.h
index c57f2ea..39ff6af 100644 (file)
--- a/src/gallium/drivers/llvmpipe/lp_rast.h
+++ b/src/gallium/drivers/llvmpipe/lp_rast.h
@@ -46,10 +46,20 @@ struct lp_scene;
 struct lp_fence;
 struct cmd_bin;
 
+#define FIXED_TYPE_WIDTH 32
 /** For sub-pixel positioning */
-#define FIXED_ORDER 4
+#define FIXED_ORDER 8
 #define FIXED_ONE (1<<FIXED_ORDER)
 
+/** Maximum length of an edge in a primitive in pixels.
+ *  If the framebuffer is large we have to think about fixed-point
+ *  integer overflow.  Coordinates need ((FIXED_TYPE_WIDTH/2) - 1) bits
+ *  to be able to fit product of two such coordinates inside
+ *  FIXED_TYPE_WIDTH, any larger and we could overflow a
+ *  FIXED_TYPE_WIDTH_-bit int.
+ */
+#define MAX_FIXED_LENGTH (1 << (((FIXED_TYPE_WIDTH/2) - 1) - FIXED_ORDER))
+
 /* Rasterizer output size going to jit fs, width/height */
 #define LP_RASTER_BLOCK_SIZE 4
 

diff --git a/src/gallium/drivers/llvmpipe/lp_setup.c b/src/gallium/drivers/llvmpipe/lp_setup.c
index 5fde01f..d686500 100644 (file)
--- a/src/gallium/drivers/llvmpipe/lp_setup.c
+++ b/src/gallium/drivers/llvmpipe/lp_setup.c
@@ -1007,16 +1007,12 @@ try_update_scene_state( struct lp_setup_context *setup )
                                          &setup->draw_regions[i]);
          }
       }
-      /* If the framebuffer is large we have to think about fixed-point
-       * integer overflow.  For 2K by 2K images, coordinates need 15 bits
-       * (2^11 + 4 subpixel bits).  The product of two such numbers would
-       * use 30 bits.  Any larger and we could overflow a 32-bit int.
-       *
-       * To cope with this problem we check if triangles are large and
-       * subdivide them if needed.
+      /*
+       * Check if subdivision of triangles is needed if the framebuffer
+       * is larger than our MAX_FIXED_LENGTH can accomodate.
        */
-      setup->subdivide_large_triangles = (setup->fb.width > 2048 &&
-                                          setup->fb.height > 2048);
+      setup->subdivide_large_triangles = (setup->fb.width > MAX_FIXED_LENGTH &&
+                                          setup->fb.height > MAX_FIXED_LENGTH);
    }
                                       
    setup->dirty = 0;

diff --git a/src/gallium/drivers/llvmpipe/lp_setup_tri.c b/src/gallium/drivers/llvmpipe/lp_setup_tri.c
index 23bc6e2..8b0fcd0 100644 (file)
--- a/src/gallium/drivers/llvmpipe/lp_setup_tri.c
+++ b/src/gallium/drivers/llvmpipe/lp_setup_tri.c
@@ -995,7 +995,7 @@ check_subdivide_triangle(struct lp_setup_context *setup,
                          const float (*v2)[4],
                          triangle_func_t tri)
 {
-   const float maxLen = 2048.0f;  /* longest permissible edge, in pixels */
+   const float maxLen = MAX_FIXED_LENGTH;  /* longest permissible edge, in pixels */
    float dx10, dy10, len10;
    float dx21, dy21, len21;
    float dx02, dy02, len02;