[Mesa-dev] [PATCH 3/3] anv: Enable MSAA compression

[Jason Ekstrand]

This just enables basic MSAA compression (no fast clears) for all
multisampled surfaces.  This improves the framerate of the Sascha
"multisampling" demo by 76% on my Sky Lake laptop.  Running Talos on
medium settings with 8x MSAA, this improves the framerate in the
benchmark by 80%.
---
 src/intel/vulkan/TODO              |  2 +-
 src/intel/vulkan/anv_blorp.c       |  3 ++-
 src/intel/vulkan/anv_image.c       |  9 +++++++++
 src/intel/vulkan/anv_pipeline.c    | 19 +++++++++++++++++++
 src/intel/vulkan/genX_cmd_buffer.c |  5 +++++
 5 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/src/intel/vulkan/TODO b/src/intel/vulkan/TODO
index f8b73a1..daab39f 100644
--- a/src/intel/vulkan/TODO
+++ b/src/intel/vulkan/TODO
@@ -9,7 +9,7 @@ Missing Features:
 
 Performance:
  - Multi-{sampled/gen8,LOD} HiZ
- - Compressed multisample support
+ - MSAA fast clears
  - Pushing pieces of UBOs?
  - Enable guardband clipping
  - Use soft-pin to avoid relocations
diff --git a/src/intel/vulkan/anv_blorp.c b/src/intel/vulkan/anv_blorp.c
index 4e7078b..902d9af 100644
--- a/src/intel/vulkan/anv_blorp.c
+++ b/src/intel/vulkan/anv_blorp.c
@@ -1397,7 +1397,8 @@ ccs_resolve_attachment(struct anv_cmd_buffer *cmd_buffer,
    struct anv_attachment_state *att_state =
       &cmd_buffer->state.attachments[att];
 
-   if (att_state->aux_usage == ISL_AUX_USAGE_NONE)
+   if (att_state->aux_usage == ISL_AUX_USAGE_NONE ||
+       att_state->aux_usage == ISL_AUX_USAGE_MCS)
       return; /* Nothing to resolve */
 
    assert(att_state->aux_usage == ISL_AUX_USAGE_CCS_E ||
diff --git a/src/intel/vulkan/anv_image.c b/src/intel/vulkan/anv_image.c
index 7eb0f8f..e4be2e5 100644
--- a/src/intel/vulkan/anv_image.c
+++ b/src/intel/vulkan/anv_image.c
@@ -238,6 +238,15 @@ make_surface(const struct anv_device *dev,
             }
          }
       }
+   } else if (aspect == VK_IMAGE_ASPECT_COLOR_BIT && vk_info->samples > 1) {
+      assert(image->aux_surface.isl.size == 0);
+      assert(!(vk_info->usage & VK_IMAGE_USAGE_STORAGE_BIT));
+      ok = isl_surf_get_mcs_surf(&dev->isl_dev, &anv_surf->isl,
+                                 &image->aux_surface.isl);
+      if (ok) {
+         add_surface(image, &image->aux_surface);
+         image->aux_usage = ISL_AUX_USAGE_MCS;
+      }
    }
 
    return VK_SUCCESS;
diff --git a/src/intel/vulkan/anv_pipeline.c b/src/intel/vulkan/anv_pipeline.c
index 4410103..708b05a 100644
--- a/src/intel/vulkan/anv_pipeline.c
+++ b/src/intel/vulkan/anv_pipeline.c
@@ -228,6 +228,25 @@ static void
 populate_sampler_prog_key(const struct gen_device_info *devinfo,
                           struct brw_sampler_prog_key_data *key)
 {
+   /* Almost all multisampled textures are compressed.  The only time when we
+    * don't compress a multisampled texture is for 16x MSAA with a surface
+    * width greater than 8k which is a bit of an edge case.  Since the sampler
+    * just ignores the MCS parameter to ld2ms when MCS is disabled, it's safe
+    * to tell the compiler to always assume compression.
+    */
+   key->compressed_multisample_layout_mask = ~0;
+
+   /* SkyLake added support for 16x MSAA.  With this came a new message for
+    * reading from a 16x MSAA surface with compression.  The new message was
+    * needed because now the MCS data is 64 bits instead of 32 or lower as is
+    * the case for 8x, 4x, and 2x.  The key->msaa_16 bit-field controls which
+    * message we use.  Fortunately, the 16x message works for 8x, 4x, and 2x
+    * so we can just use it unconditionally.  This may not be quite as
+    * efficient but it saves us from recompiling.
+    */
+   if (devinfo->gen >= 9)
+      key->msaa_16 = ~0;
+
    /* XXX: Handle texture swizzle on HSW- */
    for (int i = 0; i < MAX_SAMPLERS; i++) {
       /* Assume color sampler, no swizzling. (Works for BDW+) */
diff --git a/src/intel/vulkan/genX_cmd_buffer.c b/src/intel/vulkan/genX_cmd_buffer.c
index 40a72f4..5d8c3ea 100644
--- a/src/intel/vulkan/genX_cmd_buffer.c
+++ b/src/intel/vulkan/genX_cmd_buffer.c
@@ -222,6 +222,11 @@ color_attachment_compute_aux_usage(struct anv_device *device,
       att_state->input_aux_usage = ISL_AUX_USAGE_NONE;
       att_state->fast_clear = false;
       return;
+   } else if (iview->image->aux_usage == ISL_AUX_USAGE_MCS) {
+      att_state->aux_usage = ISL_AUX_USAGE_MCS;
+      att_state->input_aux_usage = ISL_AUX_USAGE_MCS;
+      att_state->fast_clear = false;
+      return;
    }
 
    assert(iview->image->aux_surface.isl.usage & ISL_SURF_USAGE_CCS_BIT);
-- 
2.5.0.400.gff86faf