[Mesa-dev] [PATCH 11/12] genX/cmd_buffer: Enable fast depth clears

[Nanley Chery]

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

Clears that happen within a render pass via vkCmdClearAttachments are safe
even if the clear color changes. This is because the meta implementation does
not use LOAD_OP_CLEAR which avoids any conflicts with 3DSTATE_CLEAR_PARAMS.

Signed-off-by: Nanley Chery <nanley.g.chery at intel.com>
---
 src/intel/vulkan/anv_pass.c        | 11 +++++++++++
 src/intel/vulkan/gen8_cmd_buffer.c |  6 ++++++
 src/intel/vulkan/genX_cmd_buffer.c |  4 +---
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/src/intel/vulkan/anv_pass.c b/src/intel/vulkan/anv_pass.c
index 69c3c7e..823f9cf 100644
--- a/src/intel/vulkan/anv_pass.c
+++ b/src/intel/vulkan/anv_pass.c
@@ -155,5 +155,16 @@ void anv_GetRenderAreaGranularity(
     VkRenderPass                                renderPass,
     VkExtent2D*                                 pGranularity)
 {
+   ANV_FROM_HANDLE(anv_render_pass, pass, renderPass);
+
+   /* This granularity is needed for HiZ fast clears */
+   for (unsigned i = 0; i < pass->subpass_count; ++i) {
+      if (pass->subpasses[i].depth_stencil_attachment !=
+          VK_ATTACHMENT_UNUSED) {
+         *pGranularity = (VkExtent2D) { 8, 4 };
+         return;
+      }
+   }
+
    *pGranularity = (VkExtent2D) { 1, 1 };
 }
diff --git a/src/intel/vulkan/gen8_cmd_buffer.c b/src/intel/vulkan/gen8_cmd_buffer.c
index 7f65fe2..ec91ecd 100644
--- a/src/intel/vulkan/gen8_cmd_buffer.c
+++ b/src/intel/vulkan/gen8_cmd_buffer.c
@@ -451,6 +451,12 @@ genX(cmd_buffer_do_hz_op)(struct anv_cmd_buffer *cmd_buffer, enum anv_hz_op op)
              cmd_state->render_area.extent.height % align_h)
             return;
       }
+
+      anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_CLEAR_PARAMS), cp) {
+         cp.DepthClearValueValid = true;
+         cp.DepthClearValue =
+            cmd_buffer->state.attachments[ds].clear_value.depthStencil.depth;
+      }
       break;
    case ANV_HZ_OP_DEPTH_RESOLVE:
       if (cmd_buffer->state.pass->attachments[ds].store_op !=
diff --git a/src/intel/vulkan/genX_cmd_buffer.c b/src/intel/vulkan/genX_cmd_buffer.c
index 349d2a4..7d2a6bd 100644
--- a/src/intel/vulkan/genX_cmd_buffer.c
+++ b/src/intel/vulkan/genX_cmd_buffer.c
@@ -1159,9 +1159,6 @@ cmd_buffer_emit_depth_stencil(struct anv_cmd_buffer *cmd_buffer)
    } else {
       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);
 }
 
 /**
@@ -1196,6 +1193,7 @@ void genX(CmdBeginRenderPass)(
 
    genX(cmd_buffer_set_subpass)(cmd_buffer, pass->subpasses);
    genX(cmd_buffer_do_hz_op)(cmd_buffer, ANV_HZ_OP_HIZ_RESOLVE);
+   genX(cmd_buffer_do_hz_op)(cmd_buffer, ANV_HZ_OP_CLEAR);
    anv_cmd_buffer_clear_subpass(cmd_buffer);
 }
 
-- 
2.9.3