Mesa (staging/19.2): intel/blorp: Disable depth testing for slow depth clears

[GitLab Mirror]

Module: Mesa
Branch: staging/19.2
Commit: 73a9f31b57d60dac870f1663fff3db9225c213f2
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=73a9f31b57d60dac870f1663fff3db9225c213f2

Author: Nanley Chery <nanley.g.chery at intel.com>
Date:   Thu Aug 15 10:17:11 2019 -0700

intel/blorp: Disable depth testing for slow depth clears

We'll start doing slow depth clears more often on HIZ_CCS buffers in a
future commit. Reduce the performance impact by making them use less
bandwidth.

>From the Depth Test section of the BSpec:

   This function is enabled by the Depth Test Enable state variable. If
   enabled, the pixel's ("source") depth value is first computed. After
   computation the pixel's depth value is clamped to the range defined
   by Minimum Depth and Maximum Depth in the selected CC_VIEWPORT state.
   Then the current ("destination") depth buffer value for this pixel is
   read.

and from the Depth Buffer Updates section of the BSpec:

   If depth testing is disabled or the depth test passed, the incoming
   pixel's depth value is written to the Depth Buffer.

Taken together, it's clear that depth testing isn't necessary to perform
a depth buffer clear. Mark Janes and I analyzed this patch with
frameretrace and a depthrange piglit test. I disabled HiZ to ensure we'd
get slow depth clears. We've observed the bandwidth consumption by the
depth buffer access to be cut ~50% on BDW and SKL during depth clears.
On a more graphically intensive workload, the Shadowmapping Sascha
benchmark, I took the average of 3 runs on a BDW with a display
resolution of about 1920x1200 (minus some desktop environment
decorations). I measured a 22.61% FPS improvement when HiZ is disabled.

v2. The BSpec doesn't mandate this behavior, update comment accordingly.
    (Ken)

Fixes: bc4bb5a7e30 ("intel/blorp: Emit more complete DEPTH_STENCIL state")
Reviewed-by: Jason Ekstrand <jason at jlekstrand.net>
Reviewed-by: Kenneth Graunke <kenneth at whitecape.org>
(cherry picked from commit d5fb9cccdce2d44427582ca6d9201d5ec42fedb2)

---

 src/intel/blorp/blorp_genX_exec.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/src/intel/blorp/blorp_genX_exec.h b/src/intel/blorp/blorp_genX_exec.h
index 379d7a59b64..69658786cb4 100644
--- a/src/intel/blorp/blorp_genX_exec.h
+++ b/src/intel/blorp/blorp_genX_exec.h
@@ -1111,11 +1111,6 @@ blorp_emit_depth_stencil_state(struct blorp_batch *batch,
       ds.DepthBufferWriteEnable = true;
 
       switch (params->hiz_op) {
-      case ISL_AUX_OP_NONE:
-         ds.DepthTestEnable = true;
-         ds.DepthTestFunction = COMPAREFUNCTION_ALWAYS;
-         break;
-
       /* See the following sections of the Sandy Bridge PRM, Volume 2, Part1:
        *   - 7.5.3.1 Depth Buffer Clear
        *   - 7.5.3.2 Depth Buffer Resolve
@@ -1126,6 +1121,7 @@ blorp_emit_depth_stencil_state(struct blorp_batch *batch,
          ds.DepthTestFunction = COMPAREFUNCTION_NEVER;
          break;
 
+      case ISL_AUX_OP_NONE:
       case ISL_AUX_OP_FAST_CLEAR:
       case ISL_AUX_OP_AMBIGUATE:
          ds.DepthTestEnable = false;