i965/fs: Add a sampler program key for whether the texture is 16x MSAA

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.

Acked-by: Ben Widawsky <ben@bwidawsk.net>

diff --git a/src/mesa/drivers/dri/i965/brw_compiler.h b/src/mesa/drivers/dri/i965/brw_compiler.h
index 91eabaf7787a8d0be45aa38d052c2cf7df4e2b02..f022f3829be468e2a50c63c970b8b08f407cc823 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_compiler.h
+++ b/src/mesa/drivers/dri/i965/brw_compiler.h
@@ -142,6 +142,13 @@ 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, ld2dms_w
+    * instead of ld2dms.
+    */
+   uint32_t msaa_16;
+
    /**
     * For Sandybridge, which shader w/a we need for gather quirks.
     */

diff --git a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
index 94a9c1b68f2f03bec6ca3508154d4640cff30ed8..213c9120b5030c762abd533eafb5920c6669110a 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
@@ -295,7 +295,7 @@ 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_wm.c b/src/mesa/drivers/dri/i965/brw_wm.c
index 5c49db9e63eeeb7ae38ab590ef641fb3f625ed15..8d9ed3a6c33c17c52f587d1bba88d956b0a12d16 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_wm.c
+++ b/src/mesa/drivers/dri/i965/brw_wm.c
@@ -212,6 +212,9 @@ 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",
@@ -371,6 +374,11 @@ 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;
+            }
          }
       }
    }