[Mesa-dev] [PATCH 06/12] i965/fs: Add a sampler program key for whether the texture is 16x MSAA

[Neil Roberts]

When 16x MSAA is used for sampling with texelFetch the compiler needs
to use a different instruction which passes more arguments for the MCS
data. Previously on skl+ it was unconditionally using this new
instruction. However since 16x MSAA is probably going to be pretty
rare, it is probably worthwhile to avoid using this instruction for
the other sample counts. In order to do that this patch adds a new
member to brw_sampler_prog_key_data to track when a sampler refers to
a buffer with 16 samples.

Note that this isn't done for the vec4 backend because it wouldn't
change how many registers it uses.
---
 src/mesa/drivers/dri/i965/brw_fs_visitor.cpp | 2 +-
 src/mesa/drivers/dri/i965/brw_program.h      | 7 +++++++
 src/mesa/drivers/dri/i965/brw_wm.c           | 8 ++++++++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
index ea7b3eb..7937c48 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
@@ -287,7 +287,7 @@ fs_visitor::emit_texture(ir_texture_opcode op,
       opcode = SHADER_OPCODE_TXF_LOGICAL;
       break;
    case ir_txf_ms:
-      if (devinfo->gen >= 9)
+      if ((key_tex->msaa_16 & (1 << sampler)))
          opcode = SHADER_OPCODE_TXF_CMS_W_LOGICAL;
       else
          opcode = SHADER_OPCODE_TXF_CMS_LOGICAL;
diff --git a/src/mesa/drivers/dri/i965/brw_program.h b/src/mesa/drivers/dri/i965/brw_program.h
index 00e8f3f..b27ab7f 100644
--- a/src/mesa/drivers/dri/i965/brw_program.h
+++ b/src/mesa/drivers/dri/i965/brw_program.h
@@ -72,6 +72,13 @@ struct brw_sampler_prog_key_data {
    uint32_t compressed_multisample_layout_mask;
 
    /**
+    * Whether this sampler is using 16x multisampling. If so fetching from
+    * this sampler will be handled with a different instruction, ld2ms_w
+    * instead of ld2ms.
+    */
+   uint32_t msaa_16;
+
+   /**
     * For Sandybridge, which shader w/a we need for gather quirks.
     */
    enum gen6_gather_sampler_wa gen6_gather_wa[MAX_SAMPLERS];
diff --git a/src/mesa/drivers/dri/i965/brw_wm.c b/src/mesa/drivers/dri/i965/brw_wm.c
index 35c0908..2d6f10d 100644
--- a/src/mesa/drivers/dri/i965/brw_wm.c
+++ b/src/mesa/drivers/dri/i965/brw_wm.c
@@ -292,6 +292,9 @@ brw_debug_recompile_sampler_key(struct brw_context *brw,
    found |= key_debug(brw, "compressed multisample layout",
                       old_key->compressed_multisample_layout_mask,
                       key->compressed_multisample_layout_mask);
+   found |= key_debug(brw, "16x msaa",
+                      old_key->msaa_16,
+                      key->msaa_16);
 
    for (unsigned int i = 0; i < MAX_SAMPLERS; i++) {
       found |= key_debug(brw, "textureGather workarounds",
@@ -451,6 +454,11 @@ brw_populate_sampler_prog_key_data(struct gl_context *ctx,
          if (brw->gen >= 7 &&
              intel_tex->mt->msaa_layout == INTEL_MSAA_LAYOUT_CMS) {
             key->compressed_multisample_layout_mask |= 1 << s;
+
+            if (intel_tex->mt->num_samples >= 16) {
+               assert(brw->gen >= 9);
+               key->msaa_16 |= 1 << s;
+            }
          }
       }
    }
-- 
1.9.3