Francisco Casas : vkd3d-shader/hlsl: Sort synthetic separated samplers first for SM4.

[Alexandre Julliard]

Module: vkd3d
Branch: master
Commit: 37cfbe47d7a7aa5c1d8b65f24f9f985405941d30
URL:    https://gitlab.winehq.org/wine/vkd3d/-/commit/37cfbe47d7a7aa5c1d8b65f24f9f98...

Author: Francisco Casas <fcasas(a)codeweavers.com>
Date:   Fri Aug  4 15:02:39 2023 -0400

vkd3d-shader/hlsl: Sort synthetic separated samplers first for SM4.

---

 libs/vkd3d-shader/hlsl_codegen.c         | 39 ++++++++++++++++++++++++++++++++
 tests/hlsl/combined-samplers.shader_test |  6 ++---
 tests/hlsl/texture-ordering.shader_test  | 10 ++++----
 3 files changed, 47 insertions(+), 8 deletions(-)

diff --git a/libs/vkd3d-shader/hlsl_codegen.c b/libs/vkd3d-shader/hlsl_codegen.c
index 9c1c96ae..8adfea0e 100644
--- a/libs/vkd3d-shader/hlsl_codegen.c
+++ b/libs/vkd3d-shader/hlsl_codegen.c
@@ -2191,6 +2191,44 @@ static bool lower_combined_samples(struct hlsl_ctx *ctx, struct hlsl_ir_node *in
     return true;
 }
 
+static void insert_ensuring_decreasing_bind_count(struct list *list, struct hlsl_ir_var *to_add,
+        enum hlsl_regset regset)
+{
+    struct hlsl_ir_var *var;
+
+    LIST_FOR_EACH_ENTRY(var, list, struct hlsl_ir_var, extern_entry)
+    {
+        if (var->bind_count[regset] < to_add->bind_count[regset])
+        {
+            list_add_before(&var->extern_entry, &to_add->extern_entry);
+            return;
+        }
+    }
+
+    list_add_tail(list, &to_add->extern_entry);
+}
+
+static bool sort_synthetic_separated_samplers_first(struct hlsl_ctx *ctx)
+{
+    struct list separated_resources;
+    struct hlsl_ir_var *var, *next;
+
+    list_init(&separated_resources);
+
+    LIST_FOR_EACH_ENTRY_SAFE(var, next, &ctx->extern_vars, struct hlsl_ir_var, extern_entry)
+    {
+        if (var->is_separated_resource)
+        {
+            list_remove(&var->extern_entry);
+            insert_ensuring_decreasing_bind_count(&separated_resources, var, HLSL_REGSET_TEXTURES);
+        }
+    }
+
+    list_move_head(&ctx->extern_vars, &separated_resources);
+
+    return false;
+}
+
 /* Lower DIV to RCP + MUL. */
 static bool lower_division(struct hlsl_ctx *ctx, struct hlsl_ir_node *instr, void *context)
 {
@@ -4318,6 +4356,7 @@ int hlsl_emit_bytecode(struct hlsl_ctx *ctx, struct hlsl_ir_function_decl *entry
     if (profile->major_version >= 4)
         hlsl_transform_ir(ctx, lower_combined_samples, body, NULL);
     hlsl_transform_ir(ctx, track_object_components_usage, body, NULL);
+    sort_synthetic_separated_samplers_first(ctx);
 
     if (profile->major_version < 4)
     {
diff --git a/tests/hlsl/combined-samplers.shader_test b/tests/hlsl/combined-samplers.shader_test
index 16b5438e..16db3129 100644
--- a/tests/hlsl/combined-samplers.shader_test
+++ b/tests/hlsl/combined-samplers.shader_test
@@ -60,7 +60,7 @@ float4 main() : sv_target
 
 [test]
 draw quad
-todo probe all rgba (10, 10, 10, 11)
+probe all rgba (10, 10, 10, 11)
 
 
 [pixel shader]
@@ -74,7 +74,7 @@ float4 main() : sv_target
 
 [test]
 draw quad
-todo probe all rgba (21, 21, 21, 11)
+probe all rgba (21, 21, 21, 11)
 
 
 [pixel shader]
@@ -105,7 +105,7 @@ float4 main() : sv_target
 
 [test]
 draw quad
-todo probe all rgba (104, 104, 104, 111)
+probe all rgba (104, 104, 104, 111)
 
 
 % Sampler arrays with components that have different usage dimensions are only forbidden in SM4 upwards.
diff --git a/tests/hlsl/texture-ordering.shader_test b/tests/hlsl/texture-ordering.shader_test
index b28fea5d..eb3d5c90 100644
--- a/tests/hlsl/texture-ordering.shader_test
+++ b/tests/hlsl/texture-ordering.shader_test
@@ -131,7 +131,7 @@ float4 main() : sv_target
 
 [test]
 draw quad
-todo probe all rgba (450, 139, 876, 333)
+probe all rgba (450, 139, 876, 333)
 
 
 % Same as the first test, but inverting the declaration order.
@@ -184,7 +184,7 @@ float4 main() : sv_target
 
 [test]
 draw quad
-todo probe all rgba (450, 138, 796, 333)
+probe all rgba (450, 138, 796, 333)
 
 
 % Same as the first test, but inverting the resource loads order.
@@ -237,7 +237,7 @@ float4 main() : sv_target
 
 [test]
 draw quad
-todo probe all rgba (478, 913, 256, 333)
+probe all rgba (478, 913, 256, 333)
 
 
 % We can conclude that for declared texture arrays, if they are used, the "allocation size" is the
@@ -270,7 +270,7 @@ float4 main() : sv_target
 
 [test]
 draw quad
-todo probe all rgba (215, 215, 215, 111)
+probe all rgba (215, 215, 215, 111)
 
 
 % Test that textures created from SM1-style samples allocation order is in decreasing "bind count".
@@ -300,4 +300,4 @@ float4 main() : sv_target
 
 [test]
 draw quad
-todo probe all rgba (5, 4, 2, 0)
+probe all rgba (5, 4, 2, 0)