[Mesa-dev] [PATCH v3 09/10] anv: Enable fast depth clears

[Nanley Chery]

Provides an FPS increase of ~30% on the Sascha triangle and multisampling
demos.

Signed-off-by: Nanley Chery <nanley.g.chery at intel.com>
Reviewed-by: Jason Ekstrand <jason at jlekstrand.net> (v2)

---
v3. Emit required clear_params packet (Chad)
    Share clear_params code path IVB+ (Jason)

 src/intel/vulkan/anv_pass.c        | 13 +++++++++++++
 src/intel/vulkan/genX_cmd_buffer.c | 24 ++++++++++++++++++++++--
 2 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/src/intel/vulkan/anv_pass.c b/src/intel/vulkan/anv_pass.c
index 69c3c7e..595c2ea 100644
--- a/src/intel/vulkan/anv_pass.c
+++ b/src/intel/vulkan/anv_pass.c
@@ -155,5 +155,18 @@ void anv_GetRenderAreaGranularity(
     VkRenderPass                                renderPass,
     VkExtent2D*                                 pGranularity)
 {
+   ANV_FROM_HANDLE(anv_render_pass, pass, renderPass);
+
+   /* This granularity satisfies HiZ fast clear alignment requirements
+    * for all sample counts.
+    */
+   for (unsigned i = 0; i < pass->subpass_count; ++i) {
+      if (pass->subpasses[i].depth_stencil_attachment !=
+          VK_ATTACHMENT_UNUSED) {
+         *pGranularity = (VkExtent2D) { .width = 8, .height = 4 };
+         return;
+      }
+   }
+
    *pGranularity = (VkExtent2D) { 1, 1 };
 }
diff --git a/src/intel/vulkan/genX_cmd_buffer.c b/src/intel/vulkan/genX_cmd_buffer.c
index ed6a109..4089fc7 100644
--- a/src/intel/vulkan/genX_cmd_buffer.c
+++ b/src/intel/vulkan/genX_cmd_buffer.c
@@ -1318,8 +1318,27 @@ cmd_buffer_emit_depth_stencil(struct anv_cmd_buffer *cmd_buffer)
       anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_STENCIL_BUFFER), sb);
    }
 
-   /* Clear the clear params. */
-   anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_CLEAR_PARAMS), cp);
+   /* From the IVB PRM Vol2P1, 11.5.5.4 3DSTATE_CLEAR_PARAMS:
+    *
+    *    3DSTATE_CLEAR_PARAMS must always be programmed in the along with
+    *    the other Depth/Stencil state commands(i.e. 3DSTATE_DEPTH_BUFFER,
+    *    3DSTATE_STENCIL_BUFFER, or 3DSTATE_HIER_DEPTH_BUFFER)
+    *
+    * Testing also shows that some variant of this restriction may exist HSW+.
+    * On BDW+, it is not possible to emit 2 of these packets consecutively when
+    * both have DepthClearValueValid set. An analysis of such state programming
+    * on SKL showed that the GPU doesn't register the latter packet's clear
+    * value.
+    */
+   anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_CLEAR_PARAMS), cp) {
+      if (has_hiz) {
+         cp.DepthClearValueValid = true;
+         const uint32_t ds =
+            cmd_buffer->state.subpass->depth_stencil_attachment;
+         cp.DepthClearValue =
+            cmd_buffer->state.attachments[ds].clear_value.depthStencil.depth;
+      }
+   }
 }
 
 static void
@@ -1332,6 +1351,7 @@ genX(cmd_buffer_set_subpass)(struct anv_cmd_buffer *cmd_buffer,
 
    cmd_buffer_emit_depth_stencil(cmd_buffer);
    genX(cmd_buffer_emit_hz_op)(cmd_buffer, BLORP_HIZ_OP_HIZ_RESOLVE);
+   genX(cmd_buffer_emit_hz_op)(cmd_buffer, BLORP_HIZ_OP_DEPTH_CLEAR);
 
    anv_cmd_buffer_clear_subpass(cmd_buffer);
 }
-- 
2.10.0