i965: Re-enable Z16 on Gen8+.

Improves performance in GLBenchmark 2.7 TRex by 3.88889% +/- 0.336383%
(n=80) at 1280x720 on Broadwell GT3.  Together with the previous patch,
it improves performance by 5.42738% +/- 0.541971% (n=10) at 1920x1080.

Note that without the PMA stall fix, this would instead decrease
performance by 22%.

v2: Update comment (noticed by Kristian Høgsberg).

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

diff --git a/src/mesa/drivers/dri/i965/brw_surface_formats.c b/src/mesa/drivers/dri/i965/brw_surface_formats.c
index 5407ef6..2841f81 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_surface_formats.c
+++ b/src/mesa/drivers/dri/i965/brw_surface_formats.c
@@ -619,6 +619,8 @@ brw_init_surface_formats(struct brw_context *brw)
    brw->format_supported_as_render_target[MESA_FORMAT_S_UINT8] = true;
    brw->format_supported_as_render_target[MESA_FORMAT_Z_FLOAT32] = true;
    brw->format_supported_as_render_target[MESA_FORMAT_Z32_FLOAT_S8X24_UINT] = true;
+   if (brw->gen >= 8)
+      brw->format_supported_as_render_target[MESA_FORMAT_Z_UNORM16] = true;
 
    /* We remap depth formats to a supported texturing format in
     * translate_tex_format().
@@ -638,7 +640,12 @@ brw_init_surface_formats(struct brw_context *brw)
     *
     * Other speculation is that we may be hitting increased fragment shader
     * execution from GL_LEQUAL/GL_EQUAL depth tests at reduced precision.
+    *
+    * With the PMA stall workaround in place, Z16 is faster than Z24, as it
+    * should be.
     */
+   if (brw->gen >= 8)
+      ctx->TextureFormatSupported[MESA_FORMAT_Z_UNORM16] = true;
 
    /* On hardware that lacks support for ETC1, we map ETC1 to RGBX
     * during glCompressedTexImage2D(). See intel_mipmap_tree::wraps_etc1.