anv/pipeline: More aggressively optimize away color attachments

Instead of just looking at the number of color attachments, look at
which ones are actually used by the subpass.  This lets us potentially
throw away chunks of the fragment shader.  In DXVK, for example, all
subpasses have 8 attachments and most are VK_ATTACHMENT_UNUSED so this
is very helpful in that case.

Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>

diff --git a/src/intel/compiler/brw_compiler.h b/src/intel/compiler/brw_compiler.h
index 9dfcfcc0115ad6854fa84d98d3acc15f5d50aa6e..4797c9cf06d2feef10a13036a7e40471765eb30e 100644 (file)
--- a/src/intel/compiler/brw_compiler.h
+++ b/src/intel/compiler/brw_compiler.h
@@ -403,6 +403,7 @@ struct brw_wm_prog_key {
    bool force_dual_color_blend:1;
    bool coherent_fb_fetch:1;
 
+   uint8_t color_outputs_valid;
    uint64_t input_slots_valid;
    unsigned program_string_id;
    GLenum alpha_test_func;          /* < For Gen4/5 MRT alpha test */

diff --git a/src/intel/vulkan/anv_pipeline.c b/src/intel/vulkan/anv_pipeline.c
index 914e513276392102d3a2e4fd75a5babb5de0adef..d795d77d9ba3e51a1dc38fd74ef6f0fbf12d6a90 100644 (file)
--- a/src/intel/vulkan/anv_pipeline.c
+++ b/src/intel/vulkan/anv_pipeline.c
@@ -339,7 +339,14 @@ populate_wm_prog_key(const struct anv_pipeline *pipeline,
    /* XXX Vulkan doesn't appear to specify */
    key->clamp_fragment_color = false;
 
-   key->nr_color_regions = pipeline->subpass->color_count;
+   assert(pipeline->subpass->color_count <= MAX_RTS);
+   for (uint32_t i = 0; i < pipeline->subpass->color_count; i++) {
+      if (pipeline->subpass->color_attachments[i].attachment !=
+          VK_ATTACHMENT_UNUSED)
+         key->color_outputs_valid |= (1 << i);
+   }
+
+   key->nr_color_regions = _mesa_bitcount(key->color_outputs_valid);
 
    key->replicate_alpha = key->nr_color_regions > 1 &&
                           info->pMultisampleState &&
@@ -904,8 +911,8 @@ anv_pipeline_compile_fs(struct anv_pipeline *pipeline,
             continue;
 
          const unsigned rt = var->data.location - FRAG_RESULT_DATA0;
-         /* Out-of-bounds */
-         if (rt >= key.nr_color_regions)
+         /* Unused or out-of-bounds */
+         if (rt >= MAX_RTS || !(key.color_outputs_valid & (1 << rt)))
             continue;
 
          const unsigned array_len =
@@ -936,8 +943,8 @@ anv_pipeline_compile_fs(struct anv_pipeline *pipeline,
             continue;
 
          const unsigned rt = var->data.location - FRAG_RESULT_DATA0;
-         if (rt >= key.nr_color_regions) {
-            /* Out-of-bounds, throw it away */
+         if (rt >= MAX_RTS || !(key.color_outputs_valid & (1 << rt))) {
+            /* Unused or out-of-bounds, throw it away */
             deleted_output = true;
             var->data.mode = nir_var_local;
             exec_node_remove(&var->node);
@@ -967,6 +974,7 @@ anv_pipeline_compile_fs(struct anv_pipeline *pipeline,
        * the key accordingly.
        */
       key.nr_color_regions = num_rts;
+      key.color_outputs_valid = (1 << num_rts) - 1;
 
       assert(num_rts <= max_rt);
       map.surface_to_descriptor -= num_rts;